Merge r329657.

This is the main patch that introduced the new EFLAGS lowering infrastructure.
All the source merges were clean, but the tests required help to merge.
Specifically, I had to regenerate the CHECK lines in the tests (using the trunk
update_llc_test_checks.py script) because trunk has copy propagation that the
branch doesn't. I also had to update the MIR test to use the old MIR syntax for
physical registers (%name instead of $name).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@332933 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/CodeGen/MachineBasicBlock.h b/include/llvm/CodeGen/MachineBasicBlock.h
index 0c9110cbaa876ef9d6a32747a3a508e8dbc76f66..89210e16629e9210ba74533bc8b8a657e248817e 100644 (file)
--- a/include/llvm/CodeGen/MachineBasicBlock.h
+++ b/include/llvm/CodeGen/MachineBasicBlock.h
@@ -449,6 +449,13 @@ public:
   /// Replace successor OLD with NEW and update probability info.
   void replaceSuccessor(MachineBasicBlock *Old, MachineBasicBlock *New);
 
+  /// Copy a successor (and any probability info) from original block to this
+  /// block's. Uses an iterator into the original blocks successors.
+  ///
+  /// This is useful when doing a partial clone of successors. Afterward, the
+  /// probabilities may need to be normalized.
+  void copySuccessor(MachineBasicBlock *Orig, succ_iterator I);
+
   /// Transfers all the successors from MBB to this machine basic block (i.e.,
   /// copies all the successors FromMBB and remove all the successors from
   /// FromMBB).

diff --git a/lib/CodeGen/MachineBasicBlock.cpp b/lib/CodeGen/MachineBasicBlock.cpp
index 209abf34d885b84c31ee0309b003d1cd44503213..cd67449e3acfa6311ae4c1bc1828937b5e1aedcf 100644 (file)
--- a/lib/CodeGen/MachineBasicBlock.cpp
+++ b/lib/CodeGen/MachineBasicBlock.cpp
@@ -646,6 +646,14 @@ void MachineBasicBlock::replaceSuccessor(MachineBasicBlock *Old,
   removeSuccessor(OldI);
 }
 
+void MachineBasicBlock::copySuccessor(MachineBasicBlock *Orig,
+                                      succ_iterator I) {
+  if (Orig->Probs.empty())
+    addSuccessor(*I, Orig->getSuccProbability(I));
+  else
+    addSuccessorWithoutProb(*I);
+}
+
 void MachineBasicBlock::addPredecessor(MachineBasicBlock *Pred) {
   Predecessors.push_back(Pred);
 }

diff --git a/lib/Target/X86/CMakeLists.txt b/lib/Target/X86/CMakeLists.txt
index 23ac9d9936ad8d7e3da0037b8092d00698a09131..44400813094b739316aa2af048614827882edc87 100644 (file)
--- a/lib/Target/X86/CMakeLists.txt
+++ b/lib/Target/X86/CMakeLists.txt
@@ -31,6 +31,7 @@ set(sources
   X86FixupBWInsts.cpp
   X86FixupLEAs.cpp
   X86FixupSetCC.cpp
+  X86FlagsCopyLowering.cpp
   X86FloatingPoint.cpp
   X86FrameLowering.cpp
   X86InstructionSelector.cpp

diff --git a/lib/Target/X86/X86.h b/lib/Target/X86/X86.h
index 36132682429224db50a22c69479f9c164456a6b0..642dda8f42259b9475e6d51988434876f9d127c6 100644 (file)
--- a/lib/Target/X86/X86.h
+++ b/lib/Target/X86/X86.h
@@ -66,6 +66,9 @@ FunctionPass *createX86OptimizeLEAs();
 /// Return a pass that transforms setcc + movzx pairs into xor + setcc.
 FunctionPass *createX86FixupSetCC();
 
+/// Return a pass that lowers EFLAGS copy pseudo instructions.
+FunctionPass *createX86FlagsCopyLoweringPass();
+
 /// Return a pass that expands WinAlloca pseudo-instructions.
 FunctionPass *createX86WinAllocaExpander();
 

diff --git a/lib/Target/X86/X86FlagsCopyLowering.cpp b/lib/Target/X86/X86FlagsCopyLowering.cpp
new file mode 100644 (file)
index 0000000..1f4bd7f
--- /dev/null
+++ b/lib/Target/X86/X86FlagsCopyLowering.cpp
@@ -0,0 +1,734 @@
+//====- X86FlagsCopyLowering.cpp - Lowers COPY nodes of EFLAGS ------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+/// \file
+///
+/// Lowers COPY nodes of EFLAGS by directly extracting and preserving individual
+/// flag bits.
+///
+/// We have to do this by carefully analyzing and rewriting the usage of the
+/// copied EFLAGS register because there is no general way to rematerialize the
+/// entire EFLAGS register safely and efficiently. Using `popf` both forces
+/// dynamic stack adjustment and can create correctness issues due to IF, TF,
+/// and other non-status flags being overwritten. Using sequences involving
+/// SAHF don't work on all x86 processors and are often quite slow compared to
+/// directly testing a single status preserved in its own GPR.
+///
+//===----------------------------------------------------------------------===//
+
+#include "X86.h"
+#include "X86InstrBuilder.h"
+#include "X86InstrInfo.h"
+#include "X86Subtarget.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/ScopeExit.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/SparseBitVector.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/CodeGen/MachineOperand.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSSAUpdater.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
+#include "llvm/CodeGen/TargetRegisterInfo.h"
+#include "llvm/CodeGen/TargetSchedule.h"
+#include "llvm/CodeGen/TargetSubtargetInfo.h"
+#include "llvm/IR/DebugLoc.h"
+#include "llvm/MC/MCSchedule.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
+#include <algorithm>
+#include <cassert>
+#include <iterator>
+#include <utility>
+
+using namespace llvm;
+
+#define PASS_KEY "x86-flags-copy-lowering"
+#define DEBUG_TYPE PASS_KEY
+
+STATISTIC(NumCopiesEliminated, "Number of copies of EFLAGS eliminated");
+STATISTIC(NumSetCCsInserted, "Number of setCC instructions inserted");
+STATISTIC(NumTestsInserted, "Number of test instructions inserted");
+STATISTIC(NumAddsInserted, "Number of adds instructions inserted");
+
+namespace llvm {
+
+void initializeX86FlagsCopyLoweringPassPass(PassRegistry &);
+
+} // end namespace llvm
+
+namespace {
+
+// Convenient array type for storing registers associated with each condition.
+using CondRegArray = std::array<unsigned, X86::LAST_VALID_COND + 1>;
+
+class X86FlagsCopyLoweringPass : public MachineFunctionPass {
+public:
+  X86FlagsCopyLoweringPass() : MachineFunctionPass(ID) {
+    initializeX86FlagsCopyLoweringPassPass(*PassRegistry::getPassRegistry());
+  }
+
+  StringRef getPassName() const override { return "X86 EFLAGS copy lowering"; }
+  bool runOnMachineFunction(MachineFunction &MF) override;
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+
+  /// Pass identification, replacement for typeid.
+  static char ID;
+
+private:
+  MachineRegisterInfo *MRI;
+  const X86InstrInfo *TII;
+  const TargetRegisterInfo *TRI;
+  const TargetRegisterClass *PromoteRC;
+
+  CondRegArray collectCondsInRegs(MachineBasicBlock &MBB,
+                                  MachineInstr &CopyDefI);
+
+  unsigned promoteCondToReg(MachineBasicBlock &MBB,
+                            MachineBasicBlock::iterator TestPos,
+                            DebugLoc TestLoc, X86::CondCode Cond);
+  std::pair<unsigned, bool>
+  getCondOrInverseInReg(MachineBasicBlock &TestMBB,
+                        MachineBasicBlock::iterator TestPos, DebugLoc TestLoc,
+                        X86::CondCode Cond, CondRegArray &CondRegs);
+  void insertTest(MachineBasicBlock &MBB, MachineBasicBlock::iterator Pos,
+                  DebugLoc Loc, unsigned Reg);
+
+  void rewriteArithmetic(MachineBasicBlock &TestMBB,
+                         MachineBasicBlock::iterator TestPos, DebugLoc TestLoc,
+                         MachineInstr &MI, MachineOperand &FlagUse,
+                         CondRegArray &CondRegs);
+  void rewriteCMov(MachineBasicBlock &TestMBB,
+                   MachineBasicBlock::iterator TestPos, DebugLoc TestLoc,
+                   MachineInstr &CMovI, MachineOperand &FlagUse,
+                   CondRegArray &CondRegs);
+  void rewriteCondJmp(MachineBasicBlock &TestMBB,
+                      MachineBasicBlock::iterator TestPos, DebugLoc TestLoc,
+                      MachineInstr &JmpI, CondRegArray &CondRegs);
+  void rewriteCopy(MachineInstr &MI, MachineOperand &FlagUse,
+                   MachineInstr &CopyDefI);
+  void rewriteSetCC(MachineBasicBlock &TestMBB,
+                    MachineBasicBlock::iterator TestPos, DebugLoc TestLoc,
+                    MachineInstr &SetCCI, MachineOperand &FlagUse,
+                    CondRegArray &CondRegs);
+};
+
+} // end anonymous namespace
+
+INITIALIZE_PASS_BEGIN(X86FlagsCopyLoweringPass, DEBUG_TYPE,
+                      "X86 EFLAGS copy lowering", false, false)
+INITIALIZE_PASS_END(X86FlagsCopyLoweringPass, DEBUG_TYPE,
+                    "X86 EFLAGS copy lowering", false, false)
+
+FunctionPass *llvm::createX86FlagsCopyLoweringPass() {
+  return new X86FlagsCopyLoweringPass();
+}
+
+char X86FlagsCopyLoweringPass::ID = 0;
+
+void X86FlagsCopyLoweringPass::getAnalysisUsage(AnalysisUsage &AU) const {
+  MachineFunctionPass::getAnalysisUsage(AU);
+}
+
+namespace {
+/// An enumeration of the arithmetic instruction mnemonics which have
+/// interesting flag semantics.
+///
+/// We can map instruction opcodes into these mnemonics to make it easy to
+/// dispatch with specific functionality.
+enum class FlagArithMnemonic {
+  ADC,
+  ADCX,
+  ADOX,
+  RCL,
+  RCR,
+  SBB,
+};
+} // namespace
+
+static FlagArithMnemonic getMnemonicFromOpcode(unsigned Opcode) {
+  switch (Opcode) {
+  default:
+    report_fatal_error("No support for lowering a copy into EFLAGS when used "
+                       "by this instruction!");
+
+#define LLVM_EXPAND_INSTR_SIZES(MNEMONIC, SUFFIX)                              \
+  case X86::MNEMONIC##8##SUFFIX:                                               \
+  case X86::MNEMONIC##16##SUFFIX:                                              \
+  case X86::MNEMONIC##32##SUFFIX:                                              \
+  case X86::MNEMONIC##64##SUFFIX:
+
+#define LLVM_EXPAND_ADC_SBB_INSTR(MNEMONIC)                                    \
+  LLVM_EXPAND_INSTR_SIZES(MNEMONIC, rr)                                        \
+  LLVM_EXPAND_INSTR_SIZES(MNEMONIC, rr_REV)                                    \
+  LLVM_EXPAND_INSTR_SIZES(MNEMONIC, rm)                                        \
+  LLVM_EXPAND_INSTR_SIZES(MNEMONIC, mr)                                        \
+  case X86::MNEMONIC##8ri:                                                     \
+  case X86::MNEMONIC##16ri8:                                                   \
+  case X86::MNEMONIC##32ri8:                                                   \
+  case X86::MNEMONIC##64ri8:                                                   \
+  case X86::MNEMONIC##16ri:                                                    \
+  case X86::MNEMONIC##32ri:                                                    \
+  case X86::MNEMONIC##64ri32:                                                  \
+  case X86::MNEMONIC##8mi:                                                     \
+  case X86::MNEMONIC##16mi8:                                                   \
+  case X86::MNEMONIC##32mi8:                                                   \
+  case X86::MNEMONIC##64mi8:                                                   \
+  case X86::MNEMONIC##16mi:                                                    \
+  case X86::MNEMONIC##32mi:                                                    \
+  case X86::MNEMONIC##64mi32:                                                  \
+  case X86::MNEMONIC##8i8:                                                     \
+  case X86::MNEMONIC##16i16:                                                   \
+  case X86::MNEMONIC##32i32:                                                   \
+  case X86::MNEMONIC##64i32:
+
+    LLVM_EXPAND_ADC_SBB_INSTR(ADC)
+    return FlagArithMnemonic::ADC;
+
+    LLVM_EXPAND_ADC_SBB_INSTR(SBB)
+    return FlagArithMnemonic::SBB;
+
+#undef LLVM_EXPAND_ADC_SBB_INSTR
+
+    LLVM_EXPAND_INSTR_SIZES(RCL, rCL)
+    LLVM_EXPAND_INSTR_SIZES(RCL, r1)
+    LLVM_EXPAND_INSTR_SIZES(RCL, ri)
+    return FlagArithMnemonic::RCL;
+
+    LLVM_EXPAND_INSTR_SIZES(RCR, rCL)
+    LLVM_EXPAND_INSTR_SIZES(RCR, r1)
+    LLVM_EXPAND_INSTR_SIZES(RCR, ri)
+    return FlagArithMnemonic::RCR;
+
+#undef LLVM_EXPAND_INSTR_SIZES
+
+  case X86::ADCX32rr:
+  case X86::ADCX64rr:
+  case X86::ADCX32rm:
+  case X86::ADCX64rm:
+    return FlagArithMnemonic::ADCX;
+
+  case X86::ADOX32rr:
+  case X86::ADOX64rr:
+  case X86::ADOX32rm:
+  case X86::ADOX64rm:
+    return FlagArithMnemonic::ADOX;
+  }
+}
+
+static MachineBasicBlock &splitBlock(MachineBasicBlock &MBB,
+                                     MachineInstr &SplitI,
+                                     const X86InstrInfo &TII) {
+  MachineFunction &MF = *MBB.getParent();
+
+  assert(SplitI.getParent() == &MBB &&
+         "Split instruction must be in the split block!");
+  assert(SplitI.isBranch() &&
+         "Only designed to split a tail of branch instructions!");
+  assert(X86::getCondFromBranchOpc(SplitI.getOpcode()) != X86::COND_INVALID &&
+         "Must split on an actual jCC instruction!");
+
+  // Dig out the previous instruction to the split point.
+  MachineInstr &PrevI = *std::prev(SplitI.getIterator());
+  assert(PrevI.isBranch() && "Must split after a branch!");
+  assert(X86::getCondFromBranchOpc(PrevI.getOpcode()) != X86::COND_INVALID &&
+         "Must split after an actual jCC instruction!");
+  assert(!std::prev(PrevI.getIterator())->isTerminator() &&
+         "Must only have this one terminator prior to the split!");
+
+  // Grab the one successor edge that will stay in `MBB`.
+  MachineBasicBlock &UnsplitSucc = *PrevI.getOperand(0).getMBB();
+
+  // Analyze the original block to see if we are actually splitting an edge
+  // into two edges. This can happen when we have multiple conditional jumps to
+  // the same successor.
+  bool IsEdgeSplit =
+      std::any_of(SplitI.getIterator(), MBB.instr_end(),
+                  [&](MachineInstr &MI) {
+                    assert(MI.isTerminator() &&
+                           "Should only have spliced terminators!");
+                    return llvm::any_of(
+                        MI.operands(), [&](MachineOperand &MOp) {
+                          return MOp.isMBB() && MOp.getMBB() == &UnsplitSucc;
+                        });
+                  }) ||
+      MBB.getFallThrough() == &UnsplitSucc;
+
+  MachineBasicBlock &NewMBB = *MF.CreateMachineBasicBlock();
+
+  // Insert the new block immediately after the current one. Any existing
+  // fallthrough will be sunk into this new block anyways.
+  MF.insert(std::next(MachineFunction::iterator(&MBB)), &NewMBB);
+
+  // Splice the tail of instructions into the new block.
+  NewMBB.splice(NewMBB.end(), &MBB, SplitI.getIterator(), MBB.end());
+
+  // Copy the necessary succesors (and their probability info) into the new
+  // block.
+  for (auto SI = MBB.succ_begin(), SE = MBB.succ_end(); SI != SE; ++SI)
+    if (IsEdgeSplit || *SI != &UnsplitSucc)
+      NewMBB.copySuccessor(&MBB, SI);
+  // Normalize the probabilities if we didn't end up splitting the edge.
+  if (!IsEdgeSplit)
+    NewMBB.normalizeSuccProbs();
+
+  // Now replace all of the moved successors in the original block with the new
+  // block. This will merge their probabilities.
+  for (MachineBasicBlock *Succ : NewMBB.successors())
+    if (Succ != &UnsplitSucc)
+      MBB.replaceSuccessor(Succ, &NewMBB);
+
+  // We should always end up replacing at least one successor.
+  assert(MBB.isSuccessor(&NewMBB) &&
+         "Failed to make the new block a successor!");
+
+  // Now update all the PHIs.
+  for (MachineBasicBlock *Succ : NewMBB.successors()) {
+    for (MachineInstr &MI : *Succ) {
+      if (!MI.isPHI())
+        break;
+
+      for (int OpIdx = 1, NumOps = MI.getNumOperands(); OpIdx < NumOps;
+           OpIdx += 2) {
+        MachineOperand &OpV = MI.getOperand(OpIdx);
+        MachineOperand &OpMBB = MI.getOperand(OpIdx + 1);
+        assert(OpMBB.isMBB() && "Block operand to a PHI is not a block!");
+        if (OpMBB.getMBB() != &MBB)
+          continue;
+
+        // Replace the operand for unsplit successors
+        if (!IsEdgeSplit || Succ != &UnsplitSucc) {
+          OpMBB.setMBB(&NewMBB);
+
+          // We have to continue scanning as there may be multiple entries in
+          // the PHI.
+          continue;
+        }
+
+        // When we have split the edge append a new successor.
+        MI.addOperand(MF, OpV);
+        MI.addOperand(MF, MachineOperand::CreateMBB(&NewMBB));
+        break;
+      }
+    }
+  }
+
+  return NewMBB;
+}
+
+bool X86FlagsCopyLoweringPass::runOnMachineFunction(MachineFunction &MF) {
+  DEBUG(dbgs() << "********** " << getPassName() << " : " << MF.getName()
+               << " **********\n");
+
+  auto &Subtarget = MF.getSubtarget<X86Subtarget>();
+  MRI = &MF.getRegInfo();
+  TII = Subtarget.getInstrInfo();
+  TRI = Subtarget.getRegisterInfo();
+  PromoteRC = &X86::GR8RegClass;
+
+  if (MF.begin() == MF.end())
+    // Nothing to do for a degenerate empty function...
+    return false;
+
+  SmallVector<MachineInstr *, 4> Copies;
+  for (MachineBasicBlock &MBB : MF)
+    for (MachineInstr &MI : MBB)
+      if (MI.getOpcode() == TargetOpcode::COPY &&
+          MI.getOperand(0).getReg() == X86::EFLAGS)
+        Copies.push_back(&MI);
+
+  for (MachineInstr *CopyI : Copies) {
+    MachineBasicBlock &MBB = *CopyI->getParent();
+
+    MachineOperand &VOp = CopyI->getOperand(1);
+    assert(VOp.isReg() &&
+           "The input to the copy for EFLAGS should always be a register!");
+    MachineInstr &CopyDefI = *MRI->getVRegDef(VOp.getReg());
+    if (CopyDefI.getOpcode() != TargetOpcode::COPY) {
+      // FIXME: The big likely candidate here are PHI nodes. We could in theory
+      // handle PHI nodes, but it gets really, really hard. Insanely hard. Hard
+      // enough that it is probably better to change every other part of LLVM
+      // to avoid creating them. The issue is that once we have PHIs we won't
+      // know which original EFLAGS value we need to capture with our setCCs
+      // below. The end result will be computing a complete set of setCCs that
+      // we *might* want, computing them in every place where we copy *out* of
+      // EFLAGS and then doing SSA formation on all of them to insert necessary
+      // PHI nodes and consume those here. Then hoping that somehow we DCE the
+      // unnecessary ones. This DCE seems very unlikely to be successful and so
+      // we will almost certainly end up with a glut of dead setCC
+      // instructions. Until we have a motivating test case and fail to avoid
+      // it by changing other parts of LLVM's lowering, we refuse to handle
+      // this complex case here.
+      DEBUG(dbgs() << "ERROR: Encountered unexpected def of an eflags copy: ";
+            CopyDefI.dump());
+      report_fatal_error(
+          "Cannot lower EFLAGS copy unless it is defined in turn by a copy!");
+    }
+
+    auto Cleanup = make_scope_exit([&] {
+      // All uses of the EFLAGS copy are now rewritten, kill the copy into
+      // eflags and if dead the copy from.
+      CopyI->eraseFromParent();
+      if (MRI->use_empty(CopyDefI.getOperand(0).getReg()))
+        CopyDefI.eraseFromParent();
+      ++NumCopiesEliminated;
+    });
+
+    MachineOperand &DOp = CopyI->getOperand(0);
+    assert(DOp.isDef() && "Expected register def!");
+    assert(DOp.getReg() == X86::EFLAGS && "Unexpected copy def register!");
+    if (DOp.isDead())
+      continue;
+
+    MachineBasicBlock &TestMBB = *CopyDefI.getParent();
+    auto TestPos = CopyDefI.getIterator();
+    DebugLoc TestLoc = CopyDefI.getDebugLoc();
+
+    DEBUG(dbgs() << "Rewriting copy: "; CopyI->dump());
+
+    // Scan for usage of newly set EFLAGS so we can rewrite them. We just buffer
+    // jumps because their usage is very constrained.
+    bool FlagsKilled = false;
+    SmallVector<MachineInstr *, 4> JmpIs;
+
+    // Gather the condition flags that have already been preserved in
+    // registers. We do this from scratch each time as we expect there to be
+    // very few of them and we expect to not revisit the same copy definition
+    // many times. If either of those change sufficiently we could build a map
+    // of these up front instead.
+    CondRegArray CondRegs = collectCondsInRegs(TestMBB, CopyDefI);
+
+    for (auto MII = std::next(CopyI->getIterator()), MIE = MBB.instr_end();
+         MII != MIE;) {
+      MachineInstr &MI = *MII++;
+      MachineOperand *FlagUse = MI.findRegisterUseOperand(X86::EFLAGS);
+      if (!FlagUse) {
+        if (MI.findRegisterDefOperand(X86::EFLAGS)) {
+          // If EFLAGS are defined, it's as-if they were killed. We can stop
+          // scanning here.
+          //
+          // NB!!! Many instructions only modify some flags. LLVM currently
+          // models this as clobbering all flags, but if that ever changes this
+          // will need to be carefully updated to handle that more complex
+          // logic.
+          FlagsKilled = true;
+          break;
+        }
+        continue;
+      }
+
+      DEBUG(dbgs() << "  Rewriting use: "; MI.dump());
+
+      // Check the kill flag before we rewrite as that may change it.
+      if (FlagUse->isKill())
+        FlagsKilled = true;
+
+      // Once we encounter a branch, the rest of the instructions must also be
+      // branches. We can't rewrite in place here, so we handle them below.
+      //
+      // Note that we don't have to handle tail calls here, even conditional
+      // tail calls, as those are not introduced into the X86 MI until post-RA
+      // branch folding or black placement. As a consequence, we get to deal
+      // with the simpler formulation of conditional branches followed by tail
+      // calls.
+      if (X86::getCondFromBranchOpc(MI.getOpcode()) != X86::COND_INVALID) {
+        auto JmpIt = MI.getIterator();
+        do {
+          JmpIs.push_back(&*JmpIt);
+          ++JmpIt;
+        } while (JmpIt != MBB.instr_end() &&
+                 X86::getCondFromBranchOpc(JmpIt->getOpcode()) !=
+                     X86::COND_INVALID);
+        break;
+      }
+
+      // Otherwise we can just rewrite in-place.
+      if (X86::getCondFromCMovOpc(MI.getOpcode()) != X86::COND_INVALID) {
+        rewriteCMov(TestMBB, TestPos, TestLoc, MI, *FlagUse, CondRegs);
+      } else if (X86::getCondFromSETOpc(MI.getOpcode()) != X86::COND_INVALID) {
+        rewriteSetCC(TestMBB, TestPos, TestLoc, MI, *FlagUse, CondRegs);
+      } else if (MI.getOpcode() == TargetOpcode::COPY) {
+        rewriteCopy(MI, *FlagUse, CopyDefI);
+      } else {
+        // We assume that arithmetic instructions that use flags also def them.
+        assert(MI.findRegisterDefOperand(X86::EFLAGS) &&
+               "Expected a def of EFLAGS for this instruction!");
+
+        // NB!!! Several arithmetic instructions only *partially* update
+        // flags. Theoretically, we could generate MI code sequences that
+        // would rely on this fact and observe different flags independently.
+        // But currently LLVM models all of these instructions as clobbering
+        // all the flags in an undef way. We rely on that to simplify the
+        // logic.
+        FlagsKilled = true;
+
+        rewriteArithmetic(TestMBB, TestPos, TestLoc, MI, *FlagUse, CondRegs);
+        break;
+      }
+
+      // If this was the last use of the flags, we're done.
+      if (FlagsKilled)
+        break;
+    }
+
+    // If we didn't find a kill (or equivalent) check that the flags don't
+    // live-out of the basic block. Currently we don't support lowering copies
+    // of flags that live out in this fashion.
+    if (!FlagsKilled &&
+        llvm::any_of(MBB.successors(), [](MachineBasicBlock *SuccMBB) {
+          return SuccMBB->isLiveIn(X86::EFLAGS);
+        })) {
+      DEBUG({
+        dbgs() << "ERROR: Found a copied EFLAGS live-out from basic block:\n"
+               << "----\n";
+        MBB.dump();
+        dbgs() << "----\n"
+               << "ERROR: Cannot lower this EFLAGS copy!\n";
+      });
+      report_fatal_error(
+          "Cannot lower EFLAGS copy that lives out of a basic block!");
+    }
+
+    // Now rewrite the jumps that use the flags. These we handle specially
+    // because if there are multiple jumps we'll have to do surgery on the CFG.
+    for (MachineInstr *JmpI : JmpIs) {
+      // Past the first jump we need to split the blocks apart.
+      if (JmpI != JmpIs.front())
+        splitBlock(*JmpI->getParent(), *JmpI, *TII);
+
+      rewriteCondJmp(TestMBB, TestPos, TestLoc, *JmpI, CondRegs);
+    }
+
+    // FIXME: Mark the last use of EFLAGS before the copy's def as a kill if
+    // the copy's def operand is itself a kill.
+  }
+
+#ifndef NDEBUG
+  for (MachineBasicBlock &MBB : MF)
+    for (MachineInstr &MI : MBB)
+      if (MI.getOpcode() == TargetOpcode::COPY &&
+          (MI.getOperand(0).getReg() == X86::EFLAGS ||
+           MI.getOperand(1).getReg() == X86::EFLAGS)) {
+        DEBUG(dbgs() << "ERROR: Found a COPY involving EFLAGS: "; MI.dump());
+        llvm_unreachable("Unlowered EFLAGS copy!");
+      }
+#endif
+
+  return true;
+}
+
+/// Collect any conditions that have already been set in registers so that we
+/// can re-use them rather than adding duplicates.
+CondRegArray
+X86FlagsCopyLoweringPass::collectCondsInRegs(MachineBasicBlock &MBB,
+                                             MachineInstr &CopyDefI) {
+  CondRegArray CondRegs = {};
+
+  // Scan backwards across the range of instructions with live EFLAGS.
+  for (MachineInstr &MI : llvm::reverse(
+           llvm::make_range(MBB.instr_begin(), CopyDefI.getIterator()))) {
+    X86::CondCode Cond = X86::getCondFromSETOpc(MI.getOpcode());
+    if (Cond != X86::COND_INVALID && MI.getOperand(0).isReg() &&
+        TRI->isVirtualRegister(MI.getOperand(0).getReg()))
+      CondRegs[Cond] = MI.getOperand(0).getReg();
+
+    // Stop scanning when we see the first definition of the EFLAGS as prior to
+    // this we would potentially capture the wrong flag state.
+    if (MI.findRegisterDefOperand(X86::EFLAGS))
+      break;
+  }
+  return CondRegs;
+}
+
+unsigned X86FlagsCopyLoweringPass::promoteCondToReg(
+    MachineBasicBlock &TestMBB, MachineBasicBlock::iterator TestPos,
+    DebugLoc TestLoc, X86::CondCode Cond) {
+  unsigned Reg = MRI->createVirtualRegister(PromoteRC);
+  auto SetI = BuildMI(TestMBB, TestPos, TestLoc,
+                      TII->get(X86::getSETFromCond(Cond)), Reg);
+  (void)SetI;
+  DEBUG(dbgs() << "    save cond: "; SetI->dump());
+  ++NumSetCCsInserted;
+  return Reg;
+}
+
+std::pair<unsigned, bool> X86FlagsCopyLoweringPass::getCondOrInverseInReg(
+    MachineBasicBlock &TestMBB, MachineBasicBlock::iterator TestPos,
+    DebugLoc TestLoc, X86::CondCode Cond, CondRegArray &CondRegs) {
+  unsigned &CondReg = CondRegs[Cond];
+  unsigned &InvCondReg = CondRegs[X86::GetOppositeBranchCondition(Cond)];
+  if (!CondReg && !InvCondReg)
+    CondReg = promoteCondToReg(TestMBB, TestPos, TestLoc, Cond);
+
+  if (CondReg)
+    return {CondReg, false};
+  else
+    return {InvCondReg, true};
+}
+
+void X86FlagsCopyLoweringPass::insertTest(MachineBasicBlock &MBB,
+                                          MachineBasicBlock::iterator Pos,
+                                          DebugLoc Loc, unsigned Reg) {
+  // We emit test instructions as register/immediate test against -1. This
+  // allows register allocation to fold a memory operand if needed (that will
+  // happen often due to the places this code is emitted). But hopefully will
+  // also allow us to select a shorter encoding of `testb %reg, %reg` when that
+  // would be equivalent.
+  auto TestI =
+      BuildMI(MBB, Pos, Loc, TII->get(X86::TEST8ri)).addReg(Reg).addImm(-1);
+  (void)TestI;
+  DEBUG(dbgs() << "    test cond: "; TestI->dump());
+  ++NumTestsInserted;
+}
+
+void X86FlagsCopyLoweringPass::rewriteArithmetic(
+    MachineBasicBlock &TestMBB, MachineBasicBlock::iterator TestPos,
+    DebugLoc TestLoc, MachineInstr &MI, MachineOperand &FlagUse,
+    CondRegArray &CondRegs) {
+  // Arithmetic is either reading CF or OF. Figure out which condition we need
+  // to preserve in a register.
+  X86::CondCode Cond;
+
+  // The addend to use to reset CF or OF when added to the flag value.
+  int Addend;
+
+  switch (getMnemonicFromOpcode(MI.getOpcode())) {
+  case FlagArithMnemonic::ADC:
+  case FlagArithMnemonic::ADCX:
+  case FlagArithMnemonic::RCL:
+  case FlagArithMnemonic::RCR:
+  case FlagArithMnemonic::SBB:
+    Cond = X86::COND_B; // CF == 1
+    // Set up an addend that when one is added will need a carry due to not
+    // having a higher bit available.
+    Addend = 255;
+    break;
+
+  case FlagArithMnemonic::ADOX:
+    Cond = X86::COND_O; // OF == 1
+    // Set up an addend that when one is added will turn from positive to
+    // negative and thus overflow in the signed domain.
+    Addend = 127;
+    break;
+  }
+
+  // Now get a register that contains the value of the flag input to the
+  // arithmetic. We require exactly this flag to simplify the arithmetic
+  // required to materialize it back into the flag.
+  unsigned &CondReg = CondRegs[Cond];
+  if (!CondReg)
+    CondReg = promoteCondToReg(TestMBB, TestPos, TestLoc, Cond);
+
+  MachineBasicBlock &MBB = *MI.getParent();
+
+  // Insert an instruction that will set the flag back to the desired value.
+  unsigned TmpReg = MRI->createVirtualRegister(PromoteRC);
+  auto AddI =
+      BuildMI(MBB, MI.getIterator(), MI.getDebugLoc(), TII->get(X86::ADD8ri))
+          .addDef(TmpReg, RegState::Dead)
+          .addReg(CondReg)
+          .addImm(Addend);
+  (void)AddI;
+  DEBUG(dbgs() << "    add cond: "; AddI->dump());
+  ++NumAddsInserted;
+  FlagUse.setIsKill(true);
+}
+
+void X86FlagsCopyLoweringPass::rewriteCMov(MachineBasicBlock &TestMBB,
+                                           MachineBasicBlock::iterator TestPos,
+                                           DebugLoc TestLoc,
+                                           MachineInstr &CMovI,
+                                           MachineOperand &FlagUse,
+                                           CondRegArray &CondRegs) {
+  // First get the register containing this specific condition.
+  X86::CondCode Cond = X86::getCondFromCMovOpc(CMovI.getOpcode());
+  unsigned CondReg;
+  bool Inverted;
+  std::tie(CondReg, Inverted) =
+      getCondOrInverseInReg(TestMBB, TestPos, TestLoc, Cond, CondRegs);
+
+  MachineBasicBlock &MBB = *CMovI.getParent();
+
+  // Insert a direct test of the saved register.
+  insertTest(MBB, CMovI.getIterator(), CMovI.getDebugLoc(), CondReg);
+
+  // Rewrite the CMov to use the !ZF flag from the test (but match register
+  // size and memory operand), and then kill its use of the flags afterward.
+  auto &CMovRC = *MRI->getRegClass(CMovI.getOperand(0).getReg());
+  CMovI.setDesc(TII->get(X86::getCMovFromCond(
+      Inverted ? X86::COND_E : X86::COND_NE, TRI->getRegSizeInBits(CMovRC) / 8,
+      !CMovI.memoperands_empty())));
+  FlagUse.setIsKill(true);
+  DEBUG(dbgs() << "    fixed cmov: "; CMovI.dump());
+}
+
+void X86FlagsCopyLoweringPass::rewriteCondJmp(
+    MachineBasicBlock &TestMBB, MachineBasicBlock::iterator TestPos,
+    DebugLoc TestLoc, MachineInstr &JmpI, CondRegArray &CondRegs) {
+  // First get the register containing this specific condition.
+  X86::CondCode Cond = X86::getCondFromBranchOpc(JmpI.getOpcode());
+  unsigned CondReg;
+  bool Inverted;
+  std::tie(CondReg, Inverted) =
+      getCondOrInverseInReg(TestMBB, TestPos, TestLoc, Cond, CondRegs);
+
+  MachineBasicBlock &JmpMBB = *JmpI.getParent();
+
+  // Insert a direct test of the saved register.
+  insertTest(JmpMBB, JmpI.getIterator(), JmpI.getDebugLoc(), CondReg);
+
+  // Rewrite the jump to use the !ZF flag from the test, and kill its use of
+  // flags afterward.
+  JmpI.setDesc(TII->get(
+      X86::GetCondBranchFromCond(Inverted ? X86::COND_E : X86::COND_NE)));
+  const int ImplicitEFLAGSOpIdx = 1;
+  JmpI.getOperand(ImplicitEFLAGSOpIdx).setIsKill(true);
+  DEBUG(dbgs() << "    fixed jCC: "; JmpI.dump());
+}
+
+void X86FlagsCopyLoweringPass::rewriteCopy(MachineInstr &MI,
+                                           MachineOperand &FlagUse,
+                                           MachineInstr &CopyDefI) {
+  // Just replace this copy with the the original copy def.
+  MRI->replaceRegWith(MI.getOperand(0).getReg(),
+                      CopyDefI.getOperand(0).getReg());
+  MI.eraseFromParent();
+}
+
+void X86FlagsCopyLoweringPass::rewriteSetCC(MachineBasicBlock &TestMBB,
+                                            MachineBasicBlock::iterator TestPos,
+                                            DebugLoc TestLoc,
+                                            MachineInstr &SetCCI,
+                                            MachineOperand &FlagUse,
+                                            CondRegArray &CondRegs) {
+  X86::CondCode Cond = X86::getCondFromSETOpc(SetCCI.getOpcode());
+  // Note that we can't usefully rewrite this to the inverse without complex
+  // analysis of the users of the setCC. Largely we rely on duplicates which
+  // could have been avoided already being avoided here.
+  unsigned &CondReg = CondRegs[Cond];
+  if (!CondReg)
+    CondReg = promoteCondToReg(TestMBB, TestPos, TestLoc, Cond);
+
+  // Rewriting this is trivial: we just replace the register and remove the
+  // setcc.
+  MRI->replaceRegWith(SetCCI.getOperand(0).getReg(), CondReg);
+  SetCCI.eraseFromParent();
+}

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 10e19f92b4a6349312ec0714ac0ecdfb0c4eae89..685989b774e67d2ce2c08f88a5c3c760af6396f7 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -37829,25 +37829,6 @@ bool X86TargetLowering::isTypeDesirableForOp(unsigned Opc, EVT VT) const {
   }
 }
 
-/// This function checks if any of the users of EFLAGS copies the EFLAGS. We
-/// know that the code that lowers COPY of EFLAGS has to use the stack, and if
-/// we don't adjust the stack we clobber the first frame index.
-/// See X86InstrInfo::copyPhysReg.
-static bool hasCopyImplyingStackAdjustment(const MachineFunction &MF) {
-  const MachineRegisterInfo &MRI = MF.getRegInfo();
-  return any_of(MRI.reg_instructions(X86::EFLAGS),
-                [](const MachineInstr &RI) { return RI.isCopy(); });
-}
-
-void X86TargetLowering::finalizeLowering(MachineFunction &MF) const {
-  if (hasCopyImplyingStackAdjustment(MF)) {
-    MachineFrameInfo &MFI = MF.getFrameInfo();
-    MFI.setHasCopyImplyingStackAdjustment(true);
-  }
-
-  TargetLoweringBase::finalizeLowering(MF);
-}
-
 /// This method query the target whether it is beneficial for dag combiner to
 /// promote the specified node. If true, it should return the desired promotion
 /// type by reference.

diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index 3aa9d01bff20c71509d62c52803880076e102277..7820c3e032e55f15ef1cf520ebae99b9a907f3d3 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -1099,9 +1099,6 @@ namespace llvm {
     bool lowerInterleavedStore(StoreInst *SI, ShuffleVectorInst *SVI,
                                unsigned Factor) const override;
 
-
-    void finalizeLowering(MachineFunction &MF) const override;
-
   protected:
     std::pair<const TargetRegisterClass *, uint8_t>
     findRepresentativeClass(const TargetRegisterInfo *TRI,

diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp
index 2b629c488d2dfb66f0311cdfeaddb28590ef4856..ba830dbb13efc69ad9024e481eac75ac5dee8944 100644 (file)
--- a/lib/Target/X86/X86InstrInfo.cpp
+++ b/lib/Target/X86/X86InstrInfo.cpp
@@ -6710,102 +6710,12 @@ void X86InstrInfo::copyPhysReg(MachineBasicBlock &MBB,
     return;
   }
 
-  bool FromEFLAGS = SrcReg == X86::EFLAGS;
-  bool ToEFLAGS = DestReg == X86::EFLAGS;
-  int Reg = FromEFLAGS ? DestReg : SrcReg;
-  bool is32 = X86::GR32RegClass.contains(Reg);
-  bool is64 = X86::GR64RegClass.contains(Reg);
-
-  if ((FromEFLAGS || ToEFLAGS) && (is32 || is64)) {
-    int Mov = is64 ? X86::MOV64rr : X86::MOV32rr;
-    int Push = is64 ? X86::PUSH64r : X86::PUSH32r;
-    int PushF = is64 ? X86::PUSHF64 : X86::PUSHF32;
-    int Pop = is64 ? X86::POP64r : X86::POP32r;
-    int PopF = is64 ? X86::POPF64 : X86::POPF32;
-    int AX = is64 ? X86::RAX : X86::EAX;
-
-    if (!Subtarget.hasLAHFSAHF()) {
-      assert(Subtarget.is64Bit() &&
-             "Not having LAHF/SAHF only happens on 64-bit.");
-      // Moving EFLAGS to / from another register requires a push and a pop.
-      // Notice that we have to adjust the stack if we don't want to clobber the
-      // first frame index. See X86FrameLowering.cpp - usesTheStack.
-      if (FromEFLAGS) {
-        BuildMI(MBB, MI, DL, get(PushF));
-        BuildMI(MBB, MI, DL, get(Pop), DestReg);
-      }
-      if (ToEFLAGS) {
-        BuildMI(MBB, MI, DL, get(Push))
-            .addReg(SrcReg, getKillRegState(KillSrc));
-        BuildMI(MBB, MI, DL, get(PopF));
-      }
-      return;
-    }
-
-    // The flags need to be saved, but saving EFLAGS with PUSHF/POPF is
-    // inefficient. Instead:
-    //   - Save the overflow flag OF into AL using SETO, and restore it using a
-    //     signed 8-bit addition of AL and INT8_MAX.
-    //   - Save/restore the bottom 8 EFLAGS bits (CF, PF, AF, ZF, SF) to/from AH
-    //     using LAHF/SAHF.
-    //   - When RAX/EAX is live and isn't the destination register, make sure it
-    //     isn't clobbered by PUSH/POP'ing it before and after saving/restoring
-    //     the flags.
-    // This approach is ~2.25x faster than using PUSHF/POPF.
-    //
-    // This is still somewhat inefficient because we don't know which flags are
-    // actually live inside EFLAGS. Were we able to do a single SETcc instead of
-    // SETO+LAHF / ADDB+SAHF the code could be 1.02x faster.
-    //
-    // PUSHF/POPF is also potentially incorrect because it affects other flags
-    // such as TF/IF/DF, which LLVM doesn't model.
-    //
-    // Notice that we have to adjust the stack if we don't want to clobber the
-    // first frame index.
-    // See X86ISelLowering.cpp - X86::hasCopyImplyingStackAdjustment.
-
-    const TargetRegisterInfo &TRI = getRegisterInfo();
-    MachineBasicBlock::LivenessQueryResult LQR =
-        MBB.computeRegisterLiveness(&TRI, AX, MI);
-    // We do not want to save and restore AX if we do not have to.
-    // Moreover, if we do so whereas AX is dead, we would need to set
-    // an undef flag on the use of AX, otherwise the verifier will
-    // complain that we read an undef value.
-    // We do not want to change the behavior of the machine verifier
-    // as this is usually wrong to read an undef value.
-    if (MachineBasicBlock::LQR_Unknown == LQR) {
-      LivePhysRegs LPR(TRI);
-      LPR.addLiveOuts(MBB);
-      MachineBasicBlock::iterator I = MBB.end();
-      while (I != MI) {
-        --I;
-        LPR.stepBackward(*I);
-      }
-      // AX contains the top most register in the aliasing hierarchy.
-      // It may not be live, but one of its aliases may be.
-      for (MCRegAliasIterator AI(AX, &TRI, true);
-           AI.isValid() && LQR != MachineBasicBlock::LQR_Live; ++AI)
-        LQR = LPR.contains(*AI) ? MachineBasicBlock::LQR_Live
-                                : MachineBasicBlock::LQR_Dead;
-    }
-    bool AXDead = (Reg == AX) || (MachineBasicBlock::LQR_Dead == LQR);
-    if (!AXDead)
-      BuildMI(MBB, MI, DL, get(Push)).addReg(AX, getKillRegState(true));
-    if (FromEFLAGS) {
-      BuildMI(MBB, MI, DL, get(X86::SETOr), X86::AL);
-      BuildMI(MBB, MI, DL, get(X86::LAHF));
-      BuildMI(MBB, MI, DL, get(Mov), Reg).addReg(AX);
-    }
-    if (ToEFLAGS) {
-      BuildMI(MBB, MI, DL, get(Mov), AX).addReg(Reg, getKillRegState(KillSrc));
-      BuildMI(MBB, MI, DL, get(X86::ADD8ri), X86::AL)
-          .addReg(X86::AL)
-          .addImm(INT8_MAX);
-      BuildMI(MBB, MI, DL, get(X86::SAHF));
-    }
-    if (!AXDead)
-      BuildMI(MBB, MI, DL, get(Pop), AX);
-    return;
+  if (SrcReg == X86::EFLAGS || DestReg == X86::EFLAGS) {
+    // FIXME: We use a fatal error here because historically LLVM has tried
+    // lower some of these physreg copies and we want to ensure we get
+    // reasonable bug reports if someone encounters a case no other testing
+    // found. This path should be removed after the LLVM 7 release.
+    report_fatal_error("Unable to copy EFLAGS physical register!");
   }
 
   DEBUG(dbgs() << "Cannot copy " << RI.getName(SrcReg)

diff --git a/lib/Target/X86/X86TargetMachine.cpp b/lib/Target/X86/X86TargetMachine.cpp
index ac242e1c00e0485c7763bea96a8faac058bbc32c..e41e16d82d83bb247a104a6bac887451fe9a0922 100644 (file)
--- a/lib/Target/X86/X86TargetMachine.cpp
+++ b/lib/Target/X86/X86TargetMachine.cpp
@@ -62,6 +62,7 @@ void initializeX86CallFrameOptimizationPass(PassRegistry &);
 void initializeX86CmovConverterPassPass(PassRegistry &);
 void initializeX86ExecutionDepsFixPass(PassRegistry &);
 void initializeX86DomainReassignmentPass(PassRegistry &);
+void initializeX86FlagsCopyLoweringPassPass(PassRegistry &);
 
 } // end namespace llvm
 
@@ -80,6 +81,7 @@ extern "C" void LLVMInitializeX86Target() {
   initializeX86CmovConverterPassPass(PR);
   initializeX86ExecutionDepsFixPass(PR);
   initializeX86DomainReassignmentPass(PR);
+  initializeX86FlagsCopyLoweringPassPass(PR);
 }
 
 static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
@@ -415,6 +417,7 @@ void X86PassConfig::addPreRegAlloc() {
     addPass(createX86CallFrameOptimization());
   }
 
+  addPass(createX86FlagsCopyLoweringPass());
   addPass(createX86WinAllocaExpander());
 }
 void X86PassConfig::addMachineSSAOptimization() {

diff --git a/test/CodeGen/X86/GlobalISel/add-scalar.ll b/test/CodeGen/X86/GlobalISel/add-scalar.ll
index 0ef7c956d4934470cba9bcdd9d6b217336595920..3d41d759409d51b536fc4d2af5c5f9c2f29fcac2 100644 (file)
--- a/test/CodeGen/X86/GlobalISel/add-scalar.ll
+++ b/test/CodeGen/X86/GlobalISel/add-scalar.ll
@@ -10,16 +10,10 @@ define i64 @test_add_i64(i64 %arg1, i64 %arg2) {
 ;
 ; X32-LABEL: test_add_i64:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %ebp
-; X32-NEXT:    .cfi_def_cfa_offset 8
-; X32-NEXT:    .cfi_offset %ebp, -8
-; X32-NEXT:    movl %esp, %ebp
-; X32-NEXT:    .cfi_def_cfa_register %ebp
-; X32-NEXT:    movl 16(%ebp), %eax
-; X32-NEXT:    movl 20(%ebp), %edx
-; X32-NEXT:    addl 8(%ebp), %eax
-; X32-NEXT:    adcl 12(%ebp), %edx
-; X32-NEXT:    popl %ebp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    addl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    adcl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    retl
   %ret = add i64 %arg1, %arg2
   ret i64 %ret

diff --git a/test/CodeGen/X86/O0-pipeline.ll b/test/CodeGen/X86/O0-pipeline.ll
index 3a720a5288a27dc148303534be94b221a493c296..f1f0d340c3e9aad7f539a4f7abf9b88d49797c33 100644 (file)
--- a/test/CodeGen/X86/O0-pipeline.ll
+++ b/test/CodeGen/X86/O0-pipeline.ll
@@ -37,6 +37,7 @@
 ; CHECK-NEXT:       X86 PIC Global Base Reg Initialization
 ; CHECK-NEXT:       Expand ISel Pseudo-instructions
 ; CHECK-NEXT:       Local Stack Slot Allocation
+; CHECK-NEXT:       X86 EFLAGS copy lowering
 ; CHECK-NEXT:       X86 WinAlloca Expander
 ; CHECK-NEXT:       Eliminate PHI nodes for register allocation
 ; CHECK-NEXT:       Two-Address instruction pass

diff --git a/test/CodeGen/X86/clobber-fi0.ll b/test/CodeGen/X86/clobber-fi0.ll
deleted file mode 100644 (file)
index b69b185..0000000
--- a/test/CodeGen/X86/clobber-fi0.ll
+++ /dev/null
@@ -1,37 +0,0 @@
-; RUN: llc < %s -verify-machineinstrs -mcpu=generic -mtriple=x86_64-linux | FileCheck %s
-
-target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
-target triple = "x86_64-apple-macosx10.7.0"
-
-; In the code below we need to copy the EFLAGS because of scheduling constraints.
-; When copying the EFLAGS we need to write to the stack with push/pop. This forces
-; us to emit the prolog.
-
-; CHECK: main
-; CHECK: subq{{.*}}rsp
-; CHECK: ret
-define i32 @main(i32 %arg, i8** %arg1) nounwind {
-bb:
-  %tmp = alloca i32, align 4                      ; [#uses=3 type=i32*]
-  %tmp2 = alloca i32, align 4                     ; [#uses=3 type=i32*]
-  %tmp3 = alloca i32                              ; [#uses=1 type=i32*]
-  store volatile i32 1, i32* %tmp, align 4
-  store volatile i32 1, i32* %tmp2, align 4
-  br label %bb4
-
-bb4:                                              ; preds = %bb4, %bb
-  %tmp6 = load volatile i32, i32* %tmp2, align 4                ; [#uses=1 type=i32]
-  %tmp7 = add i32 %tmp6, -1                       ; [#uses=2 type=i32]
-  store volatile i32 %tmp7, i32* %tmp2, align 4
-  %tmp8 = icmp eq i32 %tmp7, 0                    ; [#uses=1 type=i1]
-  %tmp9 = load volatile i32, i32* %tmp                          ; [#uses=1 type=i32]
-  %tmp10 = add i32 %tmp9, -1              ; [#uses=1 type=i32]
-  store volatile i32 %tmp10, i32* %tmp3
-  br i1 %tmp8, label %bb11, label %bb4
-
-bb11:                                             ; preds = %bb4
-  %tmp12 = load volatile i32, i32* %tmp, align 4                ; [#uses=1 type=i32]
-  ret i32 %tmp12
-}
-
-

diff --git a/test/CodeGen/X86/cmpxchg-clobber-flags.ll b/test/CodeGen/X86/cmpxchg-clobber-flags.ll
index 9f90446b54017ad04e858b00d701084c74bd3196..7786fb50fe2154506c3639cb67b03c9d7c769e2b 100644 (file)
--- a/test/CodeGen/X86/cmpxchg-clobber-flags.ll
+++ b/test/CodeGen/X86/cmpxchg-clobber-flags.ll
@@ -1,15 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=i386-linux-gnu %s -o - | FileCheck %s --check-prefixes=32-ALL,32-GOOD-RA
-; RUN: llc -mtriple=i386-linux-gnu -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=32-ALL,32-FAST-RA
+; RUN: llc -mtriple=i386-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=32-ALL,32-GOOD-RA
+; RUN: llc -mtriple=i386-linux-gnu -verify-machineinstrs -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=32-ALL,32-FAST-RA
 
-; RUN: llc -mtriple=x86_64-linux-gnu %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA
-; RUN: llc -mtriple=x86_64-linux-gnu -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA
-; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
-; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA-SAHF
-; RUN: llc -mtriple=x86_64-linux-gnu -mcpu=corei7 %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
-
-; TODO: Reenable verify-machineinstr once the if (!AXDead) // FIXME
-; in X86InstrInfo::copyPhysReg() is resolved.
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mattr=+sahf %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mattr=+sahf -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA-SAHF
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mcpu=corei7 %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
 
 declare i32 @foo()
 declare i32 @bar(i64)
@@ -22,37 +19,29 @@ declare i32 @bar(i64)
 ; ...
 ; use of eax
 ; During PEI the adjcallstackdown32 is replaced with the subl which
-; clobbers eflags, effectively interfering in the liveness interval.
-; Is this a case we care about? Maybe no, considering this issue
-; happens with the fast pre-regalloc scheduler enforced. A more
-; performant scheduler would move the adjcallstackdown32 out of the
-; eflags liveness interval.
+; clobbers eflags, effectively interfering in the liveness interval. However,
+; we then promote these copies into independent conditions in GPRs that avoids
+; repeated saving and restoring logic and can be trivially managed by the
+; register allocator.
 define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
 ; 32-GOOD-RA-LABEL: test_intervening_call:
 ; 32-GOOD-RA:       # %bb.0: # %entry
-; 32-GOOD-RA-NEXT:    pushl %ebp
-; 32-GOOD-RA-NEXT:    movl %esp, %ebp
 ; 32-GOOD-RA-NEXT:    pushl %ebx
 ; 32-GOOD-RA-NEXT:    pushl %esi
-; 32-GOOD-RA-NEXT:    movl 12(%ebp), %eax
-; 32-GOOD-RA-NEXT:    movl 16(%ebp), %edx
-; 32-GOOD-RA-NEXT:    movl 20(%ebp), %ebx
-; 32-GOOD-RA-NEXT:    movl 24(%ebp), %ecx
-; 32-GOOD-RA-NEXT:    movl 8(%ebp), %esi
-; 32-GOOD-RA-NEXT:    lock cmpxchg8b (%esi)
 ; 32-GOOD-RA-NEXT:    pushl %eax
-; 32-GOOD-RA-NEXT:    seto %al
-; 32-GOOD-RA-NEXT:    lahf
-; 32-GOOD-RA-NEXT:    movl %eax, %esi
-; 32-GOOD-RA-NEXT:    popl %eax
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; 32-GOOD-RA-NEXT:    lock cmpxchg8b (%esi)
+; 32-GOOD-RA-NEXT:    setne %bl
 ; 32-GOOD-RA-NEXT:    subl $8, %esp
 ; 32-GOOD-RA-NEXT:    pushl %edx
 ; 32-GOOD-RA-NEXT:    pushl %eax
 ; 32-GOOD-RA-NEXT:    calll bar
 ; 32-GOOD-RA-NEXT:    addl $16, %esp
-; 32-GOOD-RA-NEXT:    movl %esi, %eax
-; 32-GOOD-RA-NEXT:    addb $127, %al
-; 32-GOOD-RA-NEXT:    sahf
+; 32-GOOD-RA-NEXT:    testb $-1, %bl
 ; 32-GOOD-RA-NEXT:    jne .LBB0_3
 ; 32-GOOD-RA-NEXT:  # %bb.1: # %t
 ; 32-GOOD-RA-NEXT:    movl $42, %eax
@@ -61,46 +50,29 @@ define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
 ; 32-GOOD-RA-NEXT:    xorl %eax, %eax
 ; 32-GOOD-RA-NEXT:  .LBB0_2: # %t
 ; 32-GOOD-RA-NEXT:    xorl %edx, %edx
+; 32-GOOD-RA-NEXT:    addl $4, %esp
 ; 32-GOOD-RA-NEXT:    popl %esi
 ; 32-GOOD-RA-NEXT:    popl %ebx
-; 32-GOOD-RA-NEXT:    popl %ebp
 ; 32-GOOD-RA-NEXT:    retl
 ;
 ; 32-FAST-RA-LABEL: test_intervening_call:
 ; 32-FAST-RA:       # %bb.0: # %entry
-; 32-FAST-RA-NEXT:    pushl %ebp
-; 32-FAST-RA-NEXT:    movl %esp, %ebp
 ; 32-FAST-RA-NEXT:    pushl %ebx
 ; 32-FAST-RA-NEXT:    pushl %esi
-; 32-FAST-RA-NEXT:    movl 8(%ebp), %esi
-; 32-FAST-RA-NEXT:    movl 20(%ebp), %ebx
-; 32-FAST-RA-NEXT:    movl 24(%ebp), %ecx
-; 32-FAST-RA-NEXT:    movl 12(%ebp), %eax
-; 32-FAST-RA-NEXT:    movl 16(%ebp), %edx
-; 32-FAST-RA-NEXT:    lock cmpxchg8b (%esi)
 ; 32-FAST-RA-NEXT:    pushl %eax
-; 32-FAST-RA-NEXT:    seto %al
-; 32-FAST-RA-NEXT:    lahf
-; 32-FAST-RA-NEXT:    movl %eax, %ecx
-; 32-FAST-RA-NEXT:    popl %eax
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; 32-FAST-RA-NEXT:    lock cmpxchg8b (%esi)
+; 32-FAST-RA-NEXT:    setne %bl
 ; 32-FAST-RA-NEXT:    subl $8, %esp
-; 32-FAST-RA-NEXT:    pushl %eax
-; 32-FAST-RA-NEXT:    movl %ecx, %eax
-; 32-FAST-RA-NEXT:    addb $127, %al
-; 32-FAST-RA-NEXT:    sahf
-; 32-FAST-RA-NEXT:    popl %eax
-; 32-FAST-RA-NEXT:    pushl %eax
-; 32-FAST-RA-NEXT:    seto %al
-; 32-FAST-RA-NEXT:    lahf
-; 32-FAST-RA-NEXT:    movl %eax, %esi
-; 32-FAST-RA-NEXT:    popl %eax
 ; 32-FAST-RA-NEXT:    pushl %edx
 ; 32-FAST-RA-NEXT:    pushl %eax
 ; 32-FAST-RA-NEXT:    calll bar
 ; 32-FAST-RA-NEXT:    addl $16, %esp
-; 32-FAST-RA-NEXT:    movl %esi, %eax
-; 32-FAST-RA-NEXT:    addb $127, %al
-; 32-FAST-RA-NEXT:    sahf
+; 32-FAST-RA-NEXT:    testb $-1, %bl
 ; 32-FAST-RA-NEXT:    jne .LBB0_3
 ; 32-FAST-RA-NEXT:  # %bb.1: # %t
 ; 32-FAST-RA-NEXT:    movl $42, %eax
@@ -109,122 +81,29 @@ define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
 ; 32-FAST-RA-NEXT:    xorl %eax, %eax
 ; 32-FAST-RA-NEXT:  .LBB0_2: # %t
 ; 32-FAST-RA-NEXT:    xorl %edx, %edx
+; 32-FAST-RA-NEXT:    addl $4, %esp
 ; 32-FAST-RA-NEXT:    popl %esi
 ; 32-FAST-RA-NEXT:    popl %ebx
-; 32-FAST-RA-NEXT:    popl %ebp
 ; 32-FAST-RA-NEXT:    retl
 ;
-; 64-GOOD-RA-LABEL: test_intervening_call:
-; 64-GOOD-RA:       # %bb.0: # %entry
-; 64-GOOD-RA-NEXT:    pushq %rbp
-; 64-GOOD-RA-NEXT:    movq %rsp, %rbp
-; 64-GOOD-RA-NEXT:    pushq %rbx
-; 64-GOOD-RA-NEXT:    pushq %rax
-; 64-GOOD-RA-NEXT:    movq %rsi, %rax
-; 64-GOOD-RA-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; 64-GOOD-RA-NEXT:    pushfq
-; 64-GOOD-RA-NEXT:    popq %rbx
-; 64-GOOD-RA-NEXT:    movq %rax, %rdi
-; 64-GOOD-RA-NEXT:    callq bar
-; 64-GOOD-RA-NEXT:    pushq %rbx
-; 64-GOOD-RA-NEXT:    popfq
-; 64-GOOD-RA-NEXT:    jne .LBB0_3
-; 64-GOOD-RA-NEXT:  # %bb.1: # %t
-; 64-GOOD-RA-NEXT:    movl $42, %eax
-; 64-GOOD-RA-NEXT:    jmp .LBB0_2
-; 64-GOOD-RA-NEXT:  .LBB0_3: # %f
-; 64-GOOD-RA-NEXT:    xorl %eax, %eax
-; 64-GOOD-RA-NEXT:  .LBB0_2: # %t
-; 64-GOOD-RA-NEXT:    addq $8, %rsp
-; 64-GOOD-RA-NEXT:    popq %rbx
-; 64-GOOD-RA-NEXT:    popq %rbp
-; 64-GOOD-RA-NEXT:    retq
-;
-; 64-FAST-RA-LABEL: test_intervening_call:
-; 64-FAST-RA:       # %bb.0: # %entry
-; 64-FAST-RA-NEXT:    pushq %rbp
-; 64-FAST-RA-NEXT:    movq %rsp, %rbp
-; 64-FAST-RA-NEXT:    pushq %rbx
-; 64-FAST-RA-NEXT:    pushq %rax
-; 64-FAST-RA-NEXT:    movq %rsi, %rax
-; 64-FAST-RA-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; 64-FAST-RA-NEXT:    pushfq
-; 64-FAST-RA-NEXT:    popq %rbx
-; 64-FAST-RA-NEXT:    movq %rax, %rdi
-; 64-FAST-RA-NEXT:    callq bar
-; 64-FAST-RA-NEXT:    pushq %rbx
-; 64-FAST-RA-NEXT:    popfq
-; 64-FAST-RA-NEXT:    jne .LBB0_3
-; 64-FAST-RA-NEXT:  # %bb.1: # %t
-; 64-FAST-RA-NEXT:    movl $42, %eax
-; 64-FAST-RA-NEXT:    jmp .LBB0_2
-; 64-FAST-RA-NEXT:  .LBB0_3: # %f
-; 64-FAST-RA-NEXT:    xorl %eax, %eax
-; 64-FAST-RA-NEXT:  .LBB0_2: # %t
-; 64-FAST-RA-NEXT:    addq $8, %rsp
-; 64-FAST-RA-NEXT:    popq %rbx
-; 64-FAST-RA-NEXT:    popq %rbp
-; 64-FAST-RA-NEXT:    retq
-;
-; 64-GOOD-RA-SAHF-LABEL: test_intervening_call:
-; 64-GOOD-RA-SAHF:       # %bb.0: # %entry
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rbp
-; 64-GOOD-RA-SAHF-NEXT:    movq %rsp, %rbp
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rbx
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rax
-; 64-GOOD-RA-SAHF-NEXT:    movq %rsi, %rax
-; 64-GOOD-RA-SAHF-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rax
-; 64-GOOD-RA-SAHF-NEXT:    seto %al
-; 64-GOOD-RA-SAHF-NEXT:    lahf
-; 64-GOOD-RA-SAHF-NEXT:    movq %rax, %rbx
-; 64-GOOD-RA-SAHF-NEXT:    popq %rax
-; 64-GOOD-RA-SAHF-NEXT:    movq %rax, %rdi
-; 64-GOOD-RA-SAHF-NEXT:    callq bar
-; 64-GOOD-RA-SAHF-NEXT:    movq %rbx, %rax
-; 64-GOOD-RA-SAHF-NEXT:    addb $127, %al
-; 64-GOOD-RA-SAHF-NEXT:    sahf
-; 64-GOOD-RA-SAHF-NEXT:    jne .LBB0_3
-; 64-GOOD-RA-SAHF-NEXT:  # %bb.1: # %t
-; 64-GOOD-RA-SAHF-NEXT:    movl $42, %eax
-; 64-GOOD-RA-SAHF-NEXT:    jmp .LBB0_2
-; 64-GOOD-RA-SAHF-NEXT:  .LBB0_3: # %f
-; 64-GOOD-RA-SAHF-NEXT:    xorl %eax, %eax
-; 64-GOOD-RA-SAHF-NEXT:  .LBB0_2: # %t
-; 64-GOOD-RA-SAHF-NEXT:    addq $8, %rsp
-; 64-GOOD-RA-SAHF-NEXT:    popq %rbx
-; 64-GOOD-RA-SAHF-NEXT:    popq %rbp
-; 64-GOOD-RA-SAHF-NEXT:    retq
-;
-; 64-FAST-RA-SAHF-LABEL: test_intervening_call:
-; 64-FAST-RA-SAHF:       # %bb.0: # %entry
-; 64-FAST-RA-SAHF-NEXT:    pushq %rbp
-; 64-FAST-RA-SAHF-NEXT:    movq %rsp, %rbp
-; 64-FAST-RA-SAHF-NEXT:    pushq %rbx
-; 64-FAST-RA-SAHF-NEXT:    pushq %rax
-; 64-FAST-RA-SAHF-NEXT:    movq %rsi, %rax
-; 64-FAST-RA-SAHF-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; 64-FAST-RA-SAHF-NEXT:    pushq %rax
-; 64-FAST-RA-SAHF-NEXT:    seto %al
-; 64-FAST-RA-SAHF-NEXT:    lahf
-; 64-FAST-RA-SAHF-NEXT:    movq %rax, %rbx
-; 64-FAST-RA-SAHF-NEXT:    popq %rax
-; 64-FAST-RA-SAHF-NEXT:    movq %rax, %rdi
-; 64-FAST-RA-SAHF-NEXT:    callq bar
-; 64-FAST-RA-SAHF-NEXT:    movq %rbx, %rax
-; 64-FAST-RA-SAHF-NEXT:    addb $127, %al
-; 64-FAST-RA-SAHF-NEXT:    sahf
-; 64-FAST-RA-SAHF-NEXT:    jne .LBB0_3
-; 64-FAST-RA-SAHF-NEXT:  # %bb.1: # %t
-; 64-FAST-RA-SAHF-NEXT:    movl $42, %eax
-; 64-FAST-RA-SAHF-NEXT:    jmp .LBB0_2
-; 64-FAST-RA-SAHF-NEXT:  .LBB0_3: # %f
-; 64-FAST-RA-SAHF-NEXT:    xorl %eax, %eax
-; 64-FAST-RA-SAHF-NEXT:  .LBB0_2: # %t
-; 64-FAST-RA-SAHF-NEXT:    addq $8, %rsp
-; 64-FAST-RA-SAHF-NEXT:    popq %rbx
-; 64-FAST-RA-SAHF-NEXT:    popq %rbp
-; 64-FAST-RA-SAHF-NEXT:    retq
+; 64-ALL-LABEL: test_intervening_call:
+; 64-ALL:       # %bb.0: # %entry
+; 64-ALL-NEXT:    pushq %rbx
+; 64-ALL-NEXT:    movq %rsi, %rax
+; 64-ALL-NEXT:    lock cmpxchgq %rdx, (%rdi)
+; 64-ALL-NEXT:    setne %bl
+; 64-ALL-NEXT:    movq %rax, %rdi
+; 64-ALL-NEXT:    callq bar
+; 64-ALL-NEXT:    testb $-1, %bl
+; 64-ALL-NEXT:    jne .LBB0_2
+; 64-ALL-NEXT:  # %bb.1: # %t
+; 64-ALL-NEXT:    movl $42, %eax
+; 64-ALL-NEXT:    popq %rbx
+; 64-ALL-NEXT:    retq
+; 64-ALL-NEXT:  .LBB0_2: # %f
+; 64-ALL-NEXT:    xorl %eax, %eax
+; 64-ALL-NEXT:    popq %rbx
+; 64-ALL-NEXT:    retq
 entry:
   %cx = cmpxchg i64* %foo, i64 %bar, i64 %baz seq_cst seq_cst
   %v = extractvalue { i64, i1 } %cx, 0
@@ -331,149 +210,64 @@ cond.end:
 define i32 @test_feed_cmov(i32* %addr, i32 %desired, i32 %new) nounwind {
 ; 32-GOOD-RA-LABEL: test_feed_cmov:
 ; 32-GOOD-RA:       # %bb.0: # %entry
-; 32-GOOD-RA-NEXT:    pushl %ebp
-; 32-GOOD-RA-NEXT:    movl %esp, %ebp
-; 32-GOOD-RA-NEXT:    pushl %edi
+; 32-GOOD-RA-NEXT:    pushl %ebx
 ; 32-GOOD-RA-NEXT:    pushl %esi
-; 32-GOOD-RA-NEXT:    movl 12(%ebp), %eax
-; 32-GOOD-RA-NEXT:    movl 16(%ebp), %esi
-; 32-GOOD-RA-NEXT:    movl 8(%ebp), %ecx
+; 32-GOOD-RA-NEXT:    pushl %eax
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; 32-GOOD-RA-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; 32-GOOD-RA-NEXT:    lock cmpxchgl %esi, (%ecx)
-; 32-GOOD-RA-NEXT:    seto %al
-; 32-GOOD-RA-NEXT:    lahf
-; 32-GOOD-RA-NEXT:    movl %eax, %edi
+; 32-GOOD-RA-NEXT:    sete %bl
 ; 32-GOOD-RA-NEXT:    calll foo
-; 32-GOOD-RA-NEXT:    pushl %eax
-; 32-GOOD-RA-NEXT:    movl %edi, %eax
-; 32-GOOD-RA-NEXT:    addb $127, %al
-; 32-GOOD-RA-NEXT:    sahf
-; 32-GOOD-RA-NEXT:    popl %eax
-; 32-GOOD-RA-NEXT:    je .LBB2_2
+; 32-GOOD-RA-NEXT:    testb $-1, %bl
+; 32-GOOD-RA-NEXT:    jne .LBB2_2
 ; 32-GOOD-RA-NEXT:  # %bb.1: # %entry
 ; 32-GOOD-RA-NEXT:    movl %eax, %esi
 ; 32-GOOD-RA-NEXT:  .LBB2_2: # %entry
 ; 32-GOOD-RA-NEXT:    movl %esi, %eax
+; 32-GOOD-RA-NEXT:    addl $4, %esp
 ; 32-GOOD-RA-NEXT:    popl %esi
-; 32-GOOD-RA-NEXT:    popl %edi
-; 32-GOOD-RA-NEXT:    popl %ebp
+; 32-GOOD-RA-NEXT:    popl %ebx
 ; 32-GOOD-RA-NEXT:    retl
 ;
 ; 32-FAST-RA-LABEL: test_feed_cmov:
 ; 32-FAST-RA:       # %bb.0: # %entry
-; 32-FAST-RA-NEXT:    pushl %ebp
-; 32-FAST-RA-NEXT:    movl %esp, %ebp
-; 32-FAST-RA-NEXT:    pushl %edi
+; 32-FAST-RA-NEXT:    pushl %ebx
 ; 32-FAST-RA-NEXT:    pushl %esi
-; 32-FAST-RA-NEXT:    movl 8(%ebp), %ecx
-; 32-FAST-RA-NEXT:    movl 16(%ebp), %esi
-; 32-FAST-RA-NEXT:    movl 12(%ebp), %eax
+; 32-FAST-RA-NEXT:    pushl %eax
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; 32-FAST-RA-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; 32-FAST-RA-NEXT:    lock cmpxchgl %esi, (%ecx)
-; 32-FAST-RA-NEXT:    seto %al
-; 32-FAST-RA-NEXT:    lahf
-; 32-FAST-RA-NEXT:    movl %eax, %edi
+; 32-FAST-RA-NEXT:    sete %bl
 ; 32-FAST-RA-NEXT:    calll foo
-; 32-FAST-RA-NEXT:    pushl %eax
-; 32-FAST-RA-NEXT:    movl %edi, %eax
-; 32-FAST-RA-NEXT:    addb $127, %al
-; 32-FAST-RA-NEXT:    sahf
-; 32-FAST-RA-NEXT:    popl %eax
-; 32-FAST-RA-NEXT:    je .LBB2_2
+; 32-FAST-RA-NEXT:    testb $-1, %bl
+; 32-FAST-RA-NEXT:    jne .LBB2_2
 ; 32-FAST-RA-NEXT:  # %bb.1: # %entry
 ; 32-FAST-RA-NEXT:    movl %eax, %esi
 ; 32-FAST-RA-NEXT:  .LBB2_2: # %entry
 ; 32-FAST-RA-NEXT:    movl %esi, %eax
+; 32-FAST-RA-NEXT:    addl $4, %esp
 ; 32-FAST-RA-NEXT:    popl %esi
-; 32-FAST-RA-NEXT:    popl %edi
-; 32-FAST-RA-NEXT:    popl %ebp
+; 32-FAST-RA-NEXT:    popl %ebx
 ; 32-FAST-RA-NEXT:    retl
 ;
-; 64-GOOD-RA-LABEL: test_feed_cmov:
-; 64-GOOD-RA:       # %bb.0: # %entry
-; 64-GOOD-RA-NEXT:    pushq %rbp
-; 64-GOOD-RA-NEXT:    movq %rsp, %rbp
-; 64-GOOD-RA-NEXT:    pushq %r14
-; 64-GOOD-RA-NEXT:    pushq %rbx
-; 64-GOOD-RA-NEXT:    movl %edx, %ebx
-; 64-GOOD-RA-NEXT:    movl %esi, %eax
-; 64-GOOD-RA-NEXT:    lock cmpxchgl %ebx, (%rdi)
-; 64-GOOD-RA-NEXT:    pushfq
-; 64-GOOD-RA-NEXT:    popq %r14
-; 64-GOOD-RA-NEXT:    callq foo
-; 64-GOOD-RA-NEXT:    pushq %r14
-; 64-GOOD-RA-NEXT:    popfq
-; 64-GOOD-RA-NEXT:    cmovel %ebx, %eax
-; 64-GOOD-RA-NEXT:    popq %rbx
-; 64-GOOD-RA-NEXT:    popq %r14
-; 64-GOOD-RA-NEXT:    popq %rbp
-; 64-GOOD-RA-NEXT:    retq
-;
-; 64-FAST-RA-LABEL: test_feed_cmov:
-; 64-FAST-RA:       # %bb.0: # %entry
-; 64-FAST-RA-NEXT:    pushq %rbp
-; 64-FAST-RA-NEXT:    movq %rsp, %rbp
-; 64-FAST-RA-NEXT:    pushq %r14
-; 64-FAST-RA-NEXT:    pushq %rbx
-; 64-FAST-RA-NEXT:    movl %edx, %ebx
-; 64-FAST-RA-NEXT:    movl %esi, %eax
-; 64-FAST-RA-NEXT:    lock cmpxchgl %ebx, (%rdi)
-; 64-FAST-RA-NEXT:    pushfq
-; 64-FAST-RA-NEXT:    popq %r14
-; 64-FAST-RA-NEXT:    callq foo
-; 64-FAST-RA-NEXT:    pushq %r14
-; 64-FAST-RA-NEXT:    popfq
-; 64-FAST-RA-NEXT:    cmovel %ebx, %eax
-; 64-FAST-RA-NEXT:    popq %rbx
-; 64-FAST-RA-NEXT:    popq %r14
-; 64-FAST-RA-NEXT:    popq %rbp
-; 64-FAST-RA-NEXT:    retq
-;
-; 64-GOOD-RA-SAHF-LABEL: test_feed_cmov:
-; 64-GOOD-RA-SAHF:       # %bb.0: # %entry
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rbp
-; 64-GOOD-RA-SAHF-NEXT:    movq %rsp, %rbp
-; 64-GOOD-RA-SAHF-NEXT:    pushq %r14
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rbx
-; 64-GOOD-RA-SAHF-NEXT:    movl %edx, %ebx
-; 64-GOOD-RA-SAHF-NEXT:    movl %esi, %eax
-; 64-GOOD-RA-SAHF-NEXT:    lock cmpxchgl %ebx, (%rdi)
-; 64-GOOD-RA-SAHF-NEXT:    seto %al
-; 64-GOOD-RA-SAHF-NEXT:    lahf
-; 64-GOOD-RA-SAHF-NEXT:    movq %rax, %r14
-; 64-GOOD-RA-SAHF-NEXT:    callq foo
-; 64-GOOD-RA-SAHF-NEXT:    pushq %rax
-; 64-GOOD-RA-SAHF-NEXT:    movq %r14, %rax
-; 64-GOOD-RA-SAHF-NEXT:    addb $127, %al
-; 64-GOOD-RA-SAHF-NEXT:    sahf
-; 64-GOOD-RA-SAHF-NEXT:    popq %rax
-; 64-GOOD-RA-SAHF-NEXT:    cmovel %ebx, %eax
-; 64-GOOD-RA-SAHF-NEXT:    popq %rbx
-; 64-GOOD-RA-SAHF-NEXT:    popq %r14
-; 64-GOOD-RA-SAHF-NEXT:    popq %rbp
-; 64-GOOD-RA-SAHF-NEXT:    retq
-;
-; 64-FAST-RA-SAHF-LABEL: test_feed_cmov:
-; 64-FAST-RA-SAHF:       # %bb.0: # %entry
-; 64-FAST-RA-SAHF-NEXT:    pushq %rbp
-; 64-FAST-RA-SAHF-NEXT:    movq %rsp, %rbp
-; 64-FAST-RA-SAHF-NEXT:    pushq %r14
-; 64-FAST-RA-SAHF-NEXT:    pushq %rbx
-; 64-FAST-RA-SAHF-NEXT:    movl %edx, %ebx
-; 64-FAST-RA-SAHF-NEXT:    movl %esi, %eax
-; 64-FAST-RA-SAHF-NEXT:    lock cmpxchgl %ebx, (%rdi)
-; 64-FAST-RA-SAHF-NEXT:    seto %al
-; 64-FAST-RA-SAHF-NEXT:    lahf
-; 64-FAST-RA-SAHF-NEXT:    movq %rax, %r14
-; 64-FAST-RA-SAHF-NEXT:    callq foo
-; 64-FAST-RA-SAHF-NEXT:    pushq %rax
-; 64-FAST-RA-SAHF-NEXT:    movq %r14, %rax
-; 64-FAST-RA-SAHF-NEXT:    addb $127, %al
-; 64-FAST-RA-SAHF-NEXT:    sahf
-; 64-FAST-RA-SAHF-NEXT:    popq %rax
-; 64-FAST-RA-SAHF-NEXT:    cmovel %ebx, %eax
-; 64-FAST-RA-SAHF-NEXT:    popq %rbx
-; 64-FAST-RA-SAHF-NEXT:    popq %r14
-; 64-FAST-RA-SAHF-NEXT:    popq %rbp
-; 64-FAST-RA-SAHF-NEXT:    retq
+; 64-ALL-LABEL: test_feed_cmov:
+; 64-ALL:       # %bb.0: # %entry
+; 64-ALL-NEXT:    pushq %rbp
+; 64-ALL-NEXT:    pushq %rbx
+; 64-ALL-NEXT:    pushq %rax
+; 64-ALL-NEXT:    movl %edx, %ebx
+; 64-ALL-NEXT:    movl %esi, %eax
+; 64-ALL-NEXT:    lock cmpxchgl %ebx, (%rdi)
+; 64-ALL-NEXT:    sete %bpl
+; 64-ALL-NEXT:    callq foo
+; 64-ALL-NEXT:    testb $-1, %bpl
+; 64-ALL-NEXT:    cmovnel %ebx, %eax
+; 64-ALL-NEXT:    addq $8, %rsp
+; 64-ALL-NEXT:    popq %rbx
+; 64-ALL-NEXT:    popq %rbp
+; 64-ALL-NEXT:    retq
 entry:
   %res = cmpxchg i32* %addr, i32 %desired, i32 %new seq_cst seq_cst
   %success = extractvalue { i32, i1 } %res, 1

diff --git a/test/CodeGen/X86/copy-eflags.ll b/test/CodeGen/X86/copy-eflags.ll
index 1e4fca5d10ab6608905ba5a691c5e23eb7a08bb1..07d13fe2e098a1c43b06622ece0fa5ee86cfb92f 100644 (file)
--- a/test/CodeGen/X86/copy-eflags.ll
+++ b/test/CodeGen/X86/copy-eflags.ll
@@ -19,35 +19,24 @@ define i32 @test1() nounwind {
 ; X32-LABEL: test1:
 ; X32:       # %bb.0: # %entry
 ; X32-NEXT:    movb b, %cl
-; X32-NEXT:    movb %cl, %al
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    incb %al
 ; X32-NEXT:    movb %al, b
 ; X32-NEXT:    incl c
-; X32-NEXT:    pushl %eax
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %edx
-; X32-NEXT:    popl %eax
+; X32-NEXT:    sete %dl
 ; X32-NEXT:    movb a, %ah
 ; X32-NEXT:    movb %ah, %ch
 ; X32-NEXT:    incb %ch
 ; X32-NEXT:    cmpb %cl, %ah
 ; X32-NEXT:    sete d
 ; X32-NEXT:    movb %ch, a
-; X32-NEXT:    pushl %eax
-; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    popl %eax
-; X32-NEXT:    je .LBB0_2
+; X32-NEXT:    testb $-1, %dl
+; X32-NEXT:    jne .LBB0_2
 ; X32-NEXT:  # %bb.1: # %if.then
-; X32-NEXT:    pushl %ebp
-; X32-NEXT:    movl %esp, %ebp
 ; X32-NEXT:    movsbl %al, %eax
 ; X32-NEXT:    pushl %eax
 ; X32-NEXT:    calll external
 ; X32-NEXT:    addl $4, %esp
-; X32-NEXT:    popl %ebp
 ; X32-NEXT:  .LBB0_2: # %if.end
 ; X32-NEXT:    xorl %eax, %eax
 ; X32-NEXT:    retl
@@ -59,23 +48,20 @@ define i32 @test1() nounwind {
 ; X64-NEXT:    incb %al
 ; X64-NEXT:    movb %al, {{.*}}(%rip)
 ; X64-NEXT:    incl {{.*}}(%rip)
-; X64-NEXT:    pushfq
-; X64-NEXT:    popq %rsi
+; X64-NEXT:    sete %sil
 ; X64-NEXT:    movb {{.*}}(%rip), %cl
 ; X64-NEXT:    movl %ecx, %edx
 ; X64-NEXT:    incb %dl
 ; X64-NEXT:    cmpb %dil, %cl
 ; X64-NEXT:    sete {{.*}}(%rip)
 ; X64-NEXT:    movb %dl, {{.*}}(%rip)
-; X64-NEXT:    pushq %rsi
-; X64-NEXT:    popfq
-; X64-NEXT:    je .LBB0_2
+; X64-NEXT:    testb $-1, %sil
+; X64-NEXT:    jne .LBB0_2
 ; X64-NEXT:  # %bb.1: # %if.then
-; X64-NEXT:    pushq %rbp
-; X64-NEXT:    movq %rsp, %rbp
+; X64-NEXT:    pushq %rax
 ; X64-NEXT:    movsbl %al, %edi
 ; X64-NEXT:    callq external
-; X64-NEXT:    popq %rbp
+; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:  .LBB0_2: # %if.end
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    retq
@@ -108,54 +94,40 @@ if.end:
 define i32 @test2(i32* %ptr) nounwind {
 ; X32-LABEL: test2:
 ; X32:       # %bb.0: # %entry
-; X32-NEXT:    pushl %ebp
-; X32-NEXT:    movl %esp, %ebp
-; X32-NEXT:    pushl %esi
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    pushl %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    incl (%eax)
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    setne %bl
 ; X32-NEXT:    pushl $42
 ; X32-NEXT:    calll external
 ; X32-NEXT:    addl $4, %esp
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
+; X32-NEXT:    testb $-1, %bl
 ; X32-NEXT:    je .LBB1_1
-; X32-NEXT:  # %bb.3: # %else
+; X32-NEXT:  # %bb.2: # %else
 ; X32-NEXT:    xorl %eax, %eax
-; X32-NEXT:    jmp .LBB1_2
+; X32-NEXT:    popl %ebx
+; X32-NEXT:    retl
 ; X32-NEXT:  .LBB1_1: # %then
 ; X32-NEXT:    movl $64, %eax
-; X32-NEXT:  .LBB1_2: # %then
-; X32-NEXT:    popl %esi
-; X32-NEXT:    popl %ebp
+; X32-NEXT:    popl %ebx
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test2:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rbp
-; X64-NEXT:    movq %rsp, %rbp
 ; X64-NEXT:    pushq %rbx
-; X64-NEXT:    pushq %rax
 ; X64-NEXT:    incl (%rdi)
-; X64-NEXT:    pushfq
-; X64-NEXT:    popq %rbx
+; X64-NEXT:    setne %bl
 ; X64-NEXT:    movl $42, %edi
 ; X64-NEXT:    callq external
-; X64-NEXT:    pushq %rbx
-; X64-NEXT:    popfq
+; X64-NEXT:    testb $-1, %bl
 ; X64-NEXT:    je .LBB1_1
-; X64-NEXT:  # %bb.3: # %else
+; X64-NEXT:  # %bb.2: # %else
 ; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    jmp .LBB1_2
+; X64-NEXT:    popq %rbx
+; X64-NEXT:    retq
 ; X64-NEXT:  .LBB1_1: # %then
 ; X64-NEXT:    movl $64, %eax
-; X64-NEXT:  .LBB1_2: # %then
-; X64-NEXT:    addq $8, %rsp
 ; X64-NEXT:    popq %rbx
-; X64-NEXT:    popq %rbp
 ; X64-NEXT:    retq
 entry:
   %val = load i32, i32* %ptr
@@ -183,43 +155,25 @@ declare void @external_b()
 define void @test_tail_call(i32* %ptr) nounwind optsize {
 ; X32-LABEL: test_tail_call:
 ; X32:       # %bb.0: # %entry
-; X32-NEXT:    pushl %ebp
-; X32-NEXT:    movl %esp, %ebp
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    incl (%eax)
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %eax
+; X32-NEXT:    setne %al
 ; X32-NEXT:    incb a
 ; X32-NEXT:    sete d
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    je .LBB2_1
-; X32-NEXT:  # %bb.2: # %else
-; X32-NEXT:    popl %ebp
-; X32-NEXT:    jmp external_b # TAILCALL
-; X32-NEXT:  .LBB2_1: # %then
-; X32-NEXT:    popl %ebp
+; X32-NEXT:    testb $-1, %al
+; X32-NEXT:    jne external_b # TAILCALL
+; X32-NEXT:  # %bb.1: # %then
 ; X32-NEXT:    jmp external_a # TAILCALL
 ;
 ; X64-LABEL: test_tail_call:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    pushq %rbp
-; X64-NEXT:    movq %rsp, %rbp
 ; X64-NEXT:    incl (%rdi)
-; X64-NEXT:    pushfq
-; X64-NEXT:    popq %rax
+; X64-NEXT:    setne %al
 ; X64-NEXT:    incb {{.*}}(%rip)
 ; X64-NEXT:    sete {{.*}}(%rip)
-; X64-NEXT:    pushq %rax
-; X64-NEXT:    popfq
-; X64-NEXT:    je .LBB2_1
-; X64-NEXT:  # %bb.2: # %else
-; X64-NEXT:    popq %rbp
-; X64-NEXT:    jmp external_b # TAILCALL
-; X64-NEXT:  .LBB2_1: # %then
-; X64-NEXT:    popq %rbp
+; X64-NEXT:    testb $-1, %al
+; X64-NEXT:    jne external_b # TAILCALL
+; X64-NEXT:  # %bb.1: # %then
 ; X64-NEXT:    jmp external_a # TAILCALL
 entry:
   %val = load i32, i32* %ptr

diff --git a/test/CodeGen/X86/eflags-copy-expansion.mir b/test/CodeGen/X86/eflags-copy-expansion.mir
deleted file mode 100644 (file)
index 11d4c81..0000000
--- a/test/CodeGen/X86/eflags-copy-expansion.mir
+++ /dev/null
@@ -1,64 +0,0 @@
-# RUN: llc -run-pass postrapseudos -mtriple=i386-apple-macosx -o - %s | FileCheck %s
-
-# Verify that we correctly save and restore eax when copying eflags,
-# even when only a smaller alias of eax is used. We used to check only
-# eax and not its aliases.
-# PR27624.
-
---- |
-  target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
-
-  define void @foo() {
-  entry:
-    br label %false
-  false:
-    ret void
-  }
-
-...
-
----
-name:            foo
-tracksRegLiveness: true
-liveins:
-  - { reg: '%edi' }
-body:             |
-  bb.0.entry:
-    liveins: %edi
-    NOOP implicit-def %al
-
-    ; The bug was triggered only when LivePhysReg is used, which
-    ; happens only when the heuristic for the liveness computation
-    ; failed. The liveness computation heuristic looks at 10 instructions
-    ; before and after the copy. Make sure we do not reach the definition of
-    ; AL in 10 instructions, otherwise the heuristic will see that it is live.
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    NOOP
-    ; Save AL.
-    ; CHECK: PUSH32r killed %eax
-
-    ; Copy edi into EFLAGS
-    ; CHECK-NEXT: %eax = MOV32rr %edi
-    ; CHECK-NEXT: %al = ADD8ri %al, 127, implicit-def %eflags
-    ; CHECK-NEXT: SAHF implicit-def %eflags, implicit %ah
-    %eflags = COPY %edi
-
-    ; Restore AL.
-    ; CHECK-NEXT: %eax = POP32r
-  bb.1.false:
-    liveins: %al
-    NOOP implicit %al
-    RETQ
-
-...

diff --git a/test/CodeGen/X86/flags-copy-lowering.mir b/test/CodeGen/X86/flags-copy-lowering.mir
new file mode 100644 (file)
index 0000000..8198044
--- /dev/null
+++ b/test/CodeGen/X86/flags-copy-lowering.mir
@@ -0,0 +1,485 @@
+# RUN: llc -run-pass x86-flags-copy-lowering -verify-machineinstrs -o - %s | FileCheck %s
+#
+# Lower various interesting copy patterns of EFLAGS without using LAHF/SAHF.
+
+--- |
+  target triple = "x86_64-unknown-unknown"
+  
+  declare void @foo()
+  
+  define i32 @test_branch(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret i32 0
+  }
+
+  define i32 @test_branch_fallthrough(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret i32 0
+  }
+
+  define void @test_setcc(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_cmov(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_adc(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_sbb(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_adcx(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_adox(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_rcl(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+
+  define void @test_rcr(i64 %a, i64 %b) {
+  entry:
+    call void @foo()
+    ret void
+  }
+...
+---
+name:            test_branch
+# CHECK-LABEL: name: test_branch
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    successors: %bb.1, %bb.2, %bb.3
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    CMP64rr %0, %1, implicit-def %eflags
+    %2:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[A_REG:[^:]*]]:gr8 = SETAr implicit %eflags
+  ; CHECK-NEXT: %[[B_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %2
+    JA_1 %bb.1, implicit %eflags
+    JB_1 %bb.2, implicit %eflags
+    JMP_1 %bb.3
+  ; CHECK-NOT: %eflags =
+  ;
+  ; CHECK:        TEST8ri %[[A_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:   JNE_1 %bb.1, implicit killed %eflags
+  ; CHECK-SAME: {{$[[:space:]]}}
+  ; CHECK-NEXT: bb.4:
+  ; CHECK-NEXT:   successors: {{.*$}}
+  ; CHECK-SAME: {{$[[:space:]]}}
+  ; CHECK-NEXT:   TEST8ri %[[B_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:   JNE_1 %bb.2, implicit killed %eflags
+  ; CHECK-NEXT:   JMP_1 %bb.3
+  
+  bb.1:
+    %3:gr32 = MOV32ri64 42
+    %eax = COPY %3
+    RET 0, %eax
+  
+  bb.2:
+    %4:gr32 = MOV32ri64 43
+    %eax = COPY %4
+    RET 0, %eax
+  
+  bb.3:
+    %5:gr32 = MOV32r0 implicit-def dead %eflags
+    %eax = COPY %5
+    RET 0, %eax
+
+...
+---
+name:            test_branch_fallthrough
+# CHECK-LABEL: name: test_branch_fallthrough
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    successors: %bb.1, %bb.2, %bb.3
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    CMP64rr %0, %1, implicit-def %eflags
+    %2:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[A_REG:[^:]*]]:gr8 = SETAr implicit %eflags
+  ; CHECK-NEXT: %[[B_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %2
+    JA_1 %bb.2, implicit %eflags
+    JB_1 %bb.3, implicit %eflags
+  ; CHECK-NOT: %eflags =
+  ;
+  ; CHECK:        TEST8ri %[[A_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:   JNE_1 %bb.2, implicit killed %eflags
+  ; CHECK-SAME: {{$[[:space:]]}}
+  ; CHECK-NEXT: bb.4:
+  ; CHECK-NEXT:   successors: {{.*$}}
+  ; CHECK-SAME: {{$[[:space:]]}}
+  ; CHECK-NEXT:   TEST8ri %[[B_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:   JNE_1 %bb.3, implicit killed %eflags
+  ; CHECK-SAME: {{$[[:space:]]}}
+  ; CHECK-NEXT:   bb.1:
+
+  bb.1:
+    %5:gr32 = MOV32r0 implicit-def dead %eflags
+    %eax = COPY %5
+    RET 0, %eax
+  
+  bb.2:
+    %3:gr32 = MOV32ri64 42
+    %eax = COPY %3
+    RET 0, %eax
+  
+  bb.3:
+    %4:gr32 = MOV32ri64 43
+    %eax = COPY %4
+    RET 0, %eax
+  
+...
+---
+name:            test_setcc
+# CHECK-LABEL: name: test_setcc
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    CMP64rr %0, %1, implicit-def %eflags
+    %2:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[A_REG:[^:]*]]:gr8 = SETAr implicit %eflags
+  ; CHECK-NEXT: %[[B_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NEXT: %[[E_REG:[^:]*]]:gr8 = SETEr implicit %eflags
+  ; CHECK-NEXT: %[[NE_REG:[^:]*]]:gr8 = SETNEr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %2
+    %3:gr8 = SETAr implicit %eflags
+    %4:gr8 = SETBr implicit %eflags
+    %5:gr8 = SETEr implicit %eflags
+    %6:gr8 = SETNEr implicit killed %eflags
+    MOV8mr %rsp, 1, %noreg, -16, %noreg, killed %3
+    MOV8mr %rsp, 1, %noreg, -16, %noreg, killed %4
+    MOV8mr %rsp, 1, %noreg, -16, %noreg, killed %5
+    MOV8mr %rsp, 1, %noreg, -16, %noreg, killed %6
+  ; CHECK-NOT:     %eflags =
+  ; CHECK-NOT:             = SET{{.*}}
+  ; CHECK:         MOV8mr {{.*}}, killed %[[A_REG]]
+  ; CHECK-CHECK:   MOV8mr {{.*}}, killed %[[B_REG]]
+  ; CHECK-CHECK:   MOV8mr {{.*}}, killed %[[E_REG]]
+  ; CHECK-CHECK:   MOV8mr {{.*}}, killed %[[NE_REG]]
+
+    RET 0
+
+...
+---
+name:            test_cmov
+# CHECK-LABEL: name: test_cmov
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    CMP64rr %0, %1, implicit-def %eflags
+    %2:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[A_REG:[^:]*]]:gr8 = SETAr implicit %eflags
+  ; CHECK-NEXT: %[[B_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NEXT: %[[E_REG:[^:]*]]:gr8 = SETEr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %2
+    %3:gr64 = CMOVA64rr %0, %1, implicit %eflags
+    %4:gr64 = CMOVB64rr %0, %1, implicit %eflags
+    %5:gr64 = CMOVE64rr %0, %1, implicit %eflags
+    %6:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         TEST8ri %[[A_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %3:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NEXT:    TEST8ri %[[B_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NEXT:    TEST8ri %[[E_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %5:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NEXT:    TEST8ri %[[E_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %6:gr64 = CMOVE64rr %0, %1, implicit killed %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %3
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %4
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %5
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %6
+
+    RET 0
+
+...
+---
+name:            test_adc
+# CHECK-LABEL: name: test_adc
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = ADD64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[CF_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = ADC64ri32 %2:gr64, 42, implicit-def %eflags, implicit %eflags
+    %5:gr64 = ADC64ri32 %4:gr64, 42, implicit-def %eflags, implicit %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         dead %{{[^:]*}}:gr8 = ADD8ri %[[CF_REG]], 255, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = ADC64ri32 %2, 42, implicit-def %eflags, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = ADC64ri32 %4, 42, implicit-def{{( dead)?}} %eflags, implicit{{( killed)?}} %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %5
+
+    RET 0
+
+...
+---
+name:            test_sbb
+# CHECK-LABEL: name: test_sbb
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = SUB64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY killed %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[CF_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = SBB64ri32 %2:gr64, 42, implicit-def %eflags, implicit killed %eflags
+    %5:gr64 = SBB64ri32 %4:gr64, 42, implicit-def dead %eflags, implicit killed %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         dead %{{[^:]*}}:gr8 = ADD8ri %[[CF_REG]], 255, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = SBB64ri32 %2, 42, implicit-def %eflags, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = SBB64ri32 %4, 42, implicit-def{{( dead)?}} %eflags, implicit{{( killed)?}} %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %5
+
+    RET 0
+
+...
+---
+name:            test_adcx
+# CHECK-LABEL: name: test_adcx
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = ADD64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY %eflags
+  ; CHECK-NOT:    COPY{{( killed)?}} %eflags
+  ; CHECK:        %[[E_REG:[^:]*]]:gr8 = SETEr implicit %eflags
+  ; CHECK-NEXT:   %[[CF_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:    COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = CMOVE64rr %0, %1, implicit %eflags
+    %5:gr64 = MOV64ri32 42
+    %6:gr64 = ADCX64rr %2, %5, implicit-def %eflags, implicit %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         TEST8ri %[[E_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = MOV64ri32 42
+  ; CHECK-NEXT:    dead %{{[^:]*}}:gr8 = ADD8ri %[[CF_REG]], 255, implicit-def %eflags
+  ; CHECK-NEXT:    %6:gr64 = ADCX64rr %2, %5, implicit-def{{( dead)?}} %eflags, implicit killed %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %4
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %6
+
+    RET 0
+
+...
+---
+name:            test_adox
+# CHECK-LABEL: name: test_adox
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = ADD64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY %eflags
+  ; CHECK-NOT:    COPY{{( killed)?}} %eflags
+  ; CHECK:        %[[E_REG:[^:]*]]:gr8 = SETEr implicit %eflags
+  ; CHECK-NEXT:   %[[OF_REG:[^:]*]]:gr8 = SETOr implicit %eflags
+  ; CHECK-NOT:    COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = CMOVE64rr %0, %1, implicit %eflags
+    %5:gr64 = MOV64ri32 42
+    %6:gr64 = ADOX64rr %2, %5, implicit-def %eflags, implicit %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         TEST8ri %[[E_REG]], -1, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = CMOVNE64rr %0, %1, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = MOV64ri32 42
+  ; CHECK-NEXT:    dead %{{[^:]*}}:gr8 = ADD8ri %[[OF_REG]], 127, implicit-def %eflags
+  ; CHECK-NEXT:    %6:gr64 = ADOX64rr %2, %5, implicit-def{{( dead)?}} %eflags, implicit killed %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %4
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %6
+
+    RET 0
+
+...
+---
+name:            test_rcl
+# CHECK-LABEL: name: test_rcl
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = ADD64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[CF_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = RCL64r1 %2:gr64, implicit-def %eflags, implicit %eflags
+    %5:gr64 = RCL64r1 %4:gr64, implicit-def %eflags, implicit %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         dead %{{[^:]*}}:gr8 = ADD8ri %[[CF_REG]], 255, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = RCL64r1 %2, implicit-def %eflags, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = RCL64r1 %4, implicit-def{{( dead)?}} %eflags, implicit{{( killed)?}} %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %5
+
+    RET 0
+
+...
+---
+name:            test_rcr
+# CHECK-LABEL: name: test_rcr
+liveins:         
+  - { reg: '%rdi', virtual-reg: '%0' }
+  - { reg: '%rsi', virtual-reg: '%1' }
+body:             |
+  bb.0:
+    liveins: %rdi, %rsi
+  
+    %0:gr64 = COPY %rdi
+    %1:gr64 = COPY %rsi
+    %2:gr64 = ADD64rr %0, %1, implicit-def %eflags
+    %3:gr64 = COPY %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+  ; CHECK:      %[[CF_REG:[^:]*]]:gr8 = SETBr implicit %eflags
+  ; CHECK-NOT:  COPY{{( killed)?}} %eflags
+
+    ADJCALLSTACKDOWN64 0, 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+    CALL64pcrel32 @foo, csr_64, implicit %rsp, implicit %ssp, implicit %rdi, implicit-def %rsp, implicit-def %ssp, implicit-def %eax
+    ADJCALLSTACKUP64 0, 0, implicit-def dead %rsp, implicit-def dead %eflags, implicit-def dead %ssp, implicit %rsp, implicit %ssp
+
+    %eflags = COPY %3
+    %4:gr64 = RCR64r1 %2:gr64, implicit-def %eflags, implicit %eflags
+    %5:gr64 = RCR64r1 %4:gr64, implicit-def %eflags, implicit %eflags
+  ; CHECK-NOT:     %eflags =
+  ; CHECK:         dead %{{[^:]*}}:gr8 = ADD8ri %[[CF_REG]], 255, implicit-def %eflags
+  ; CHECK-NEXT:    %4:gr64 = RCR64r1 %2, implicit-def %eflags, implicit killed %eflags
+  ; CHECK-NEXT:    %5:gr64 = RCR64r1 %4, implicit-def{{( dead)?}} %eflags, implicit{{( killed)?}} %eflags
+    MOV64mr %rsp, 1, %noreg, -16, %noreg, killed %5
+
+    RET 0
+
+...

diff --git a/test/CodeGen/X86/mul-i1024.ll b/test/CodeGen/X86/mul-i1024.ll
index 2f28c0a1708ef6204aa68ac6467264a723e5b114..16fb112efadb2d79b4ca251491aefd844d079edf 100644 (file)
--- a/test/CodeGen/X86/mul-i1024.ll
+++ b/test/CodeGen/X86/mul-i1024.ll
@@ -6,202 +6,195 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-LABEL: test_1024:
 ; X32:       # %bb.0:
 ; X32-NEXT:    pushl %ebp
-; X32-NEXT:    movl %esp, %ebp
 ; X32-NEXT:    pushl %ebx
 ; X32-NEXT:    pushl %edi
 ; X32-NEXT:    pushl %esi
-; X32-NEXT:    subl $996, %esp # imm = 0x3E4
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 32(%eax), %eax
+; X32-NEXT:    subl $1000, %esp # imm = 0x3E8
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 48(%eax), %ecx
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl 32(%edx), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %ecx, %ecx
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    xorl %edi, %edi
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl 8(%ebp), %esi
-; X32-NEXT:    movl 48(%esi), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    xorl %ecx, %ecx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    adcl %edi, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl 32(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl %ebx, %ecx
 ; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    adcl %edi, %eax
-; X32-NEXT:    movl %edi, %ecx
-; X32-NEXT:    movl %ecx, -204(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %eax, -892(%ebp) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    adcl %ebp, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 36(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %edx, %edx
-; X32-NEXT:    mull %edx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    movl %edi, -304(%ebp) # 4-byte Spill
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %eax
 ; X32-NEXT:    adcl $0, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl 36(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %ecx, %ecx
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %ecx, -124(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %eax, -184(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %eax, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, %edx
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    leal (%ebx,%edi), %eax
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    leal (%ecx,%edi), %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    leal (%ebx,%eax), %eax
+; X32-NEXT:    leal (%ecx,%ebp), %edx
 ; X32-NEXT:    adcl %eax, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl %esi, %ebx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl (%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl 8(%ebp), %ecx
-; X32-NEXT:    movl 16(%ecx), %eax
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X32-NEXT:    movl 16(%ebp), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %edx, %edx
-; X32-NEXT:    mull %edx
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    adcl %ebx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl (%ecx), %eax
+; X32-NEXT:    movl (%ebp), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %esi, %ebp
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movl %esi, %ecx
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %ebx
-; X32-NEXT:    movl %ebx, -256(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -100(%ebp), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, -80(%ebp) # 4-byte Folded Spill
-; X32-NEXT:    movl -204(%ebp), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, -220(%ebp) # 4-byte Folded Spill
-; X32-NEXT:    setb -388(%ebp) # 1-byte Folded Spill
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 4(%eax), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %edx, %edx
-; X32-NEXT:    mull %edx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ebx, %edi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
-; X32-NEXT:    setb %bh
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movzbl %bh, %eax
-; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    movl %edi, -72(%ebp) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 8(%eax), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %ebx, %ebx
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 52(%eax), %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl 4(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    movl %ecx, %edi
+; X32-NEXT:    xorl %ecx, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %ebp, %ecx
+; X32-NEXT:    movl %ebp, %esi
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    movl %ebx, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb %cl
-; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, (%esp) # 4-byte Spill
 ; X32-NEXT:    movzbl %cl, %eax
 ; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 56(%eax), %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 8(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %ecx
-; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %edi
+; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    adcl %edx, %ebp
+; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X32-NEXT:    movl 52(%ebp), %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    xorl %ecx, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    setb %bl
+; X32-NEXT:    addl %eax, %ecx
+; X32-NEXT:    movzbl %bl, %ebx
+; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    movl 56(%ebp), %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    xorl %edx, %edx
+; X32-NEXT:    mull %edx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %ebp
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %edi
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
@@ -210,64 +203,60 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 1-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 40(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %ebx, -396(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -324(%ebp), %edx # 4-byte Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    addl %esi, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl 16(%ecx), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %esi, -84(%ebp) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl 20(%ecx), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    addl %ebp, %ebx
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    addl %edi, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %ebp, %ecx
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movzbl %bl, %esi
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 24(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
@@ -276,55 +265,54 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %ebx
 ; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %eax, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %ebx, -56(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %eax, -780(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -132(%ebp), %edx # 4-byte Reload
-; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %ebx, %eax
+; X32-NEXT:    adcl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 20(%eax), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl 20(%edi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
@@ -333,31 +321,30 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %ebx, %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movzbl %bl, %esi
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 24(%eax), %eax
+; X32-NEXT:    movl 24(%edi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    movl %ebp, %edi
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -367,7 +354,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl 4(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
@@ -377,8 +365,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %ecx, %esi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %ecx, %edi
 ; X32-NEXT:    setb %cl
@@ -386,66 +374,64 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movzbl %cl, %eax
 ; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 8(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    movl %ecx, -160(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %edx, -268(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %esi
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %esi
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %ecx
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    movl %esi, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %edx
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    pushl %eax
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %edx
-; X32-NEXT:    popl %eax
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %edx
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %edx
-; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %edx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -458,82 +444,78 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %edx, %eax
-; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    adcl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %edx, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 40(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %edi
-; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    addl %esi, %edi
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, %edx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %ebp
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl %ebx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edi, %eax
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    adcl %ebp, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    seto %al
-; X32-NEXT:    lahf
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X32-NEXT:    movl 48(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    movl %ebx, -336(%ebp) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ebp
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl 52(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -542,38 +524,37 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %edi, %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl %ebx, %esi
+; X32-NEXT:    addl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movzbl %bl, %esi
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 56(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebp, %ebx
 ; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    movl %edi, %edx
-; X32-NEXT:    movl %edx, -176(%ebp) # 4-byte Spill
-; X32-NEXT:    adcl -360(%ebp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl %edx, %edi
 ; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %edx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
@@ -584,67 +565,65 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 64(%eax), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl 64(%edi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %esi, -384(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -116(%ebp), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %ecx
-; X32-NEXT:    movl %eax, %edx
-; X32-NEXT:    movl %edx, -480(%ebp) # 4-byte Spill
-; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %esi, %ecx
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 80(%eax), %eax
+; X32-NEXT:    movl 80(%edi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %ebp, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %esi, %edi
 ; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %ecx
+; X32-NEXT:    addl %ebp, %esi
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl 80(%ecx), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    xorl %ebx, %ebx
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    xorl %edi, %edi
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl 64(%ecx), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl %esi, %ecx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %esi, -496(%ebp) # 4-byte Spill
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %ecx
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
@@ -654,15 +633,16 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %eax
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
@@ -677,122 +657,116 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    pushl %eax
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    popl %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movb {{[-0-9]+}}(%e{{[sb]}}p), %al # 1-byte Reload
+; X32-NEXT:    addb $255, %al
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %edx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    adcl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 68(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    addl %ebx, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebp, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edx, %edi
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    adcl %edx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 72(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl %esi, -484(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %edx, -488(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %edx
+; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    adcl %edi, %ebp
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl %esi, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %eax, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %ebx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %ebp, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl %edx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl 84(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -807,48 +781,46 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %edi, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %ebx, %ecx
-; X32-NEXT:    setb %bl
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    movzbl %bl, %esi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 1-byte Folded Reload
+; X32-NEXT:    adcl %edx, %ebp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 88(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %ebx
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, %esi
+; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    addl %ecx, %esi
+; X32-NEXT:    adcl %ebp, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    adcl %ebx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl %esi, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl %edi, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 84(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
@@ -858,100 +830,97 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %esi, %edi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movzbl %bl, %edi
 ; X32-NEXT:    adcl %edx, %edi
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 88(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl %esi, -556(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %edx, -560(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -524(%ebp), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %ebx
+; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    movl %esi, %edx
-; X32-NEXT:    movl %edx, -728(%ebp) # 4-byte Spill
-; X32-NEXT:    addl -136(%ebp), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, -712(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -668(%ebp), %ecx # 4-byte Reload
-; X32-NEXT:    adcl -276(%ebp), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, -968(%ebp) # 4-byte Spill
 ; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %ecx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl 68(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    xorl %ebx, %ebx
 ; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    addl %ebx, %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 72(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    xorl %edx, %edx
+; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %ebx, -568(%ebp) # 4-byte Spill
-; X32-NEXT:    movl -500(%ebp), %edx # 4-byte Reload
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %ebx, %eax
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %edx
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl %esi, %ebx
 ; X32-NEXT:    movl %edx, %eax
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %esi
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ecx, %esi
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl %ebp, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    addl %edx, %eax
@@ -962,9 +931,9 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %edx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    adcl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 12(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
@@ -985,136 +954,132 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, %edx
 ; X32-NEXT:    addl %edx, %ebx
 ; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl (%esp), %edi # 4-byte Reload
+; X32-NEXT:    addl %ebp, %edi
+; X32-NEXT:    movl %edi, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %edi, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %ebx, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %ebp, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %edx
-; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl (%esp), %esi # 4-byte Reload
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    addl %ecx, %esi
+; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    setb %dl
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movzbl %dl, %edx
 ; X32-NEXT:    adcl %ebx, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl (%esp), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 44(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    movl %ebx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl %esi, %ecx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    addl %ebx, %edx
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl %esi, %edx
-; X32-NEXT:    adcl %ecx, %ebx
+; X32-NEXT:    setb %bl
+; X32-NEXT:    addl %eax, %edx
+; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    adcl %ecx, %eax
+; X32-NEXT:    movl %edi, %ecx
+; X32-NEXT:    addl %ecx, %edx
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %edi
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebp, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    adcl %edi, %ebx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 1-byte Folded Reload
+; X32-NEXT:    adcl %edx, %ebp
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    addl %eax, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    pushl %eax
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    popl %eax
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addb $255, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -1124,76 +1089,74 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 12(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edx
-; X32-NEXT:    setb %cl
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    addl %eax, %edx
-; X32-NEXT:    movzbl %cl, %eax
-; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    movl %edi, %esi
-; X32-NEXT:    addl %esi, %edx
-; X32-NEXT:    adcl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    movzbl %bl, %ebp
+; X32-NEXT:    adcl %ecx, %ebp
+; X32-NEXT:    movl %esi, %ecx
+; X32-NEXT:    addl %ecx, %edx
+; X32-NEXT:    adcl %edi, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %eax, %esi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %ecx, %edi
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %ebp, %esi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebx, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl %ebx, %eax
-; X32-NEXT:    setb %bl
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movzbl %bl, %esi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
+; X32-NEXT:    addb $255, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -1204,59 +1167,60 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 44(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %edi, %ebx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    setb %bl
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ebp
+; X32-NEXT:    setb %cl
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    movzbl %cl, %eax
 ; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    movl %ecx, %edx
-; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    adcl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %edx
+; X32-NEXT:    addl %edx, %ebp
+; X32-NEXT:    adcl %esi, %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %edx
+; X32-NEXT:    movl %ebp, %edx
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %edi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %eax
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    addl %edx, %eax
+; X32-NEXT:    adcl %edi, %ecx
 ; X32-NEXT:    setb %dl
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movzbl %dl, %edx
-; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl %edi, %ebx
+; X32-NEXT:    movzbl %dl, %eax
+; X32-NEXT:    adcl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl %esi, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
@@ -1264,67 +1228,60 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edi
+; X32-NEXT:    adcl %ebp, %esi
+; X32-NEXT:    addb $255, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %eax
-; X32-NEXT:    addb $127, %al
-; X32-NEXT:    sahf
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addb $255, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl (%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 60(%eax), %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 60(%eax), %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %ebx
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -1333,64 +1290,64 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl (%esp), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -1398,38 +1355,38 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
+; X32-NEXT:    movzbl (%esp), %edi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
@@ -1452,193 +1409,192 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %edi, %ebx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl (%esp), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movzbl (%esp), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %ebp
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -1648,35 +1604,37 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -1686,132 +1644,131 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 28(%eax), %ebx
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %ebx, %esi
-; X32-NEXT:    movl %esi, -48(%ebp) # 4-byte Spill
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl %ebp, %ebx
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    addl %eax, %ebp
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    movzbl %bl, %esi
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edx
+; X32-NEXT:    addl %ebp, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, (%esp) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ecx, %esi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    setb %bl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -1821,81 +1778,81 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %esi, %ebp
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    addl %eax, %ebp
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -1906,42 +1863,40 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edx
+; X32-NEXT:    addl %ebp, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
@@ -1951,8 +1906,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %ebx
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %eax, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl $0, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -1966,41 +1920,42 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 28(%eax), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 28(%eax), %ecx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -2011,62 +1966,63 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %esi, %ebx
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -2074,36 +2030,36 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %edi, %edx
@@ -2128,31 +2084,31 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %bl, %esi
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -2161,160 +2117,158 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %edi
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    movzbl %cl, %esi
 ; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl %ebp, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl %eax, %esi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -2324,62 +2278,64 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl %ebp, %esi
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    addl %ebp, %ecx
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    adcl %esi, %ebp
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -2388,8 +2344,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %ebx
@@ -2397,24 +2352,25 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
@@ -2423,43 +2379,41 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
@@ -2467,21 +2421,22 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ecx, %esi
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %ebp, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -2500,167 +2455,162 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %edi, %esi
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %esi, %ebx
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, %edi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl %eax, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -2669,29 +2619,30 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    addl %ebp, %ebx
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -2702,81 +2653,82 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %edi, %ebp
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
+; X32-NEXT:    addl %eax, %ebp
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -2787,67 +2739,66 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edx
+; X32-NEXT:    addl %ebp, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    movzbl (%esp), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    addl (%esp), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -2855,65 +2806,65 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    movzbl %cl, %eax
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
@@ -2921,38 +2872,38 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl (%esp), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
 ; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
@@ -2960,7 +2911,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    adcl %edx, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X32-NEXT:    movl (%esp), %edx # 4-byte Reload
 ; X32-NEXT:    addl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
@@ -2972,7 +2923,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
@@ -2983,30 +2934,31 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %edi, %ecx
 ; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %ecx
-; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -3016,106 +2968,107 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %esi, %edi
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 60(%eax), %esi
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebp, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 60(%eax), %ebp
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -3123,17 +3076,17 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -3142,13 +3095,13 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
@@ -3156,28 +3109,29 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ecx, %esi
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -3193,7 +3147,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
@@ -3207,107 +3162,104 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl (%esp), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %esi, %ebp
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %edx, %ebp
+; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    addl (%esp), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl (%esp), %ecx # 1-byte Folded Reload
+; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    adcl %edx, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl %ebx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ebx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl %ecx, %esi
+; X32-NEXT:    adcl %ebp, %edx
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    adcl %eax, %esi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, %ebx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
@@ -3319,9 +3271,47 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl (%esp), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -3332,84 +3322,40 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebx, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %ebx
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -3420,64 +3366,64 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb %bl
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
@@ -3485,8 +3431,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %ebx
@@ -3494,7 +3439,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -3505,133 +3451,133 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %ebx
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %edi, %ebp
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb %cl
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -3639,16 +3585,16 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -3659,18 +3605,18 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
 ; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
@@ -3701,29 +3647,30 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %ebp, %edi
 ; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -3736,61 +3683,61 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %edi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -3799,8 +3746,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %ebx
@@ -3808,24 +3754,25 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
@@ -3834,43 +3781,41 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
@@ -3878,21 +3823,22 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, %esi
 ; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebp, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -3911,56 +3857,57 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    adcl %esi, %ebx
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -3969,7 +3916,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %esi
@@ -3979,23 +3926,24 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
@@ -4011,15 +3959,15 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %esi
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %ebp
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -4033,23 +3981,21 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -4063,47 +4009,49 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %edx
+; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -4114,28 +4062,28 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl %ecx, %ebx
@@ -4148,70 +4096,72 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 76(%eax), %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 76(%eax), %ecx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %ecx, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %edi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movzbl (%esp), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    adcl %edx, %esi
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl (%esp), %ebx # 4-byte Folded Reload
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movzbl (%esp), %esi # 1-byte Folded Reload
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -4219,245 +4169,245 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ecx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, (%esp) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl (%esp), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
-; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ebx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    movl (%esp), %edx # 4-byte Reload
+; X32-NEXT:    addl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl $0, %eax
+; X32-NEXT:    adcl %eax, %edi
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, (%esp) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %ebp, %esi
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edx, %edi
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %edi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -4468,67 +4418,66 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl 8(%ebp), %eax
-; X32-NEXT:    movl 92(%eax), %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 92(%eax), %ebp
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %ebx, %esi
-; X32-NEXT:    movl %esi, -140(%ebp) # 4-byte Spill
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
+; X32-NEXT:    adcl %edi, %esi
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -4536,17 +4485,17 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl (%esp), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
@@ -4555,42 +4504,43 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ecx, %esi
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    setb (%esp) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
-; X32-NEXT:    setb %cl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movzbl (%esp), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
@@ -4600,63 +4550,63 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %eax, (%esp) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    adcl %esi, %ebp
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edi, %ebx
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -4665,8 +4615,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %esi
@@ -4682,7 +4631,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
@@ -4695,7 +4645,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -4708,56 +4658,59 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, %ebp
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %esi
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %eax, (%esp) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl $0, %ebp
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -4766,41 +4719,43 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %esi, %ebp
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %edx, %esi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -4809,7 +4764,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
@@ -4823,7 +4778,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -4845,31 +4800,32 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    setb %bl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %ebp
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
@@ -4887,15 +4843,14 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %edi, %ecx
-; X32-NEXT:    imull %eax, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    imull %eax, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    movl %ecx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl %eax, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -4909,7 +4864,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %edx, %esi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebp, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl %edi, %esi
@@ -4919,20 +4874,20 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    adcl %ebp, %esi
 ; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
@@ -4940,9 +4895,10 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    imull %eax, %esi
+; X32-NEXT:    imull %ebp, %esi
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -4951,62 +4907,62 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %edx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %esi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    imull %edi, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %esi, %edx
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    imull %eax, %ecx
 ; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebp, %edi
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
-; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %esi
-; X32-NEXT:    movl 104(%esi), %ebx
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl 104(%esi), %ebp
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -5015,274 +4971,274 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ebx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    xorl %ecx, %ecx
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %ecx
-; X32-NEXT:    movl 96(%ecx), %edi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT:    movl 96(%edi), %ebx
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 100(%ecx), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl 100(%edi), %edi
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    xorl %edx, %edx
-; X32-NEXT:    mull %edx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    xorl %ecx, %ecx
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl %ebp, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    addl %ecx, %edi
-; X32-NEXT:    adcl %esi, %eax
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %eax
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    addl %eax, %ebp
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    addl %ebp, %ebx
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    adcl %edi, %ecx
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
-; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %eax, %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 8(%ebp), %ecx
-; X32-NEXT:    movl 112(%ecx), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    imull %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT:    movl 112(%esi), %edi
+; X32-NEXT:    imull %edi, %ebp
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %esi, %edx
-; X32-NEXT:    movl 116(%ecx), %eax
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    movl 116(%esi), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    imull %eax, %edi
-; X32-NEXT:    addl %edx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 120(%ecx), %eax
+; X32-NEXT:    imull %eax, %ecx
+; X32-NEXT:    addl %edx, %ecx
 ; X32-NEXT:    movl %ecx, %ebx
-; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    movl 120(%esi), %eax
+; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    imull %esi, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    imull %esi, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    addl %ecx, %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl 124(%ecx), %ecx
+; X32-NEXT:    imull %ebp, %ecx
+; X32-NEXT:    addl %edx, %ecx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %edi, %edx
-; X32-NEXT:    movl 124(%ebx), %ebx
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    imull %eax, %ebx
-; X32-NEXT:    addl %edx, %ebx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ebp, %ebx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %ebp
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %esi
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edx
+; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    imull %eax, %edi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    imull %eax, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl %edi, %edx
-; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %esi, %edx
+; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    addl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    imull %ebp, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    imull %edi, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %esi, %edx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    imull %eax, %ecx
 ; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl %edi, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %ebx, %esi
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    setb %bl
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %esi, %edi
+; X32-NEXT:    adcl %ebp, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %esi, %eax
-; X32-NEXT:    movzbl %bl, %esi
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, %ecx
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
@@ -5293,7 +5249,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
@@ -5306,10 +5262,9 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    addl (%esp), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -5321,37 +5276,38 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 92(%eax), %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 92(%eax), %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %edi, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -5362,62 +5318,62 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %edi, %ebp
+; X32-NEXT:    movzbl %bl, %eax
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -5425,36 +5381,36 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %ecx
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
 ; X32-NEXT:    adcl %edi, %edx
@@ -5479,32 +5435,32 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %eax
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl 76(%eax), %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -5514,157 +5470,158 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %edi
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ebp
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %edi
-; X32-NEXT:    adcl %edx, %ebx
+; X32-NEXT:    adcl %edx, %ebp
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %esi, %edx
+; X32-NEXT:    addl %ebx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
-; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %esi, %ecx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %edi, %esi
+; X32-NEXT:    setb %cl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
@@ -5674,104 +5631,105 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl %ebp, %esi
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    adcl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %edi, %ecx
-; X32-NEXT:    adcl $0, %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    adcl %esi, %ebx
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %ecx
-; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %ebp
+; X32-NEXT:    adcl %edx, %ecx
+; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl $0, %ebp
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %eax, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl $0, %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
-; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %bl, %esi
+; X32-NEXT:    adcl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -5779,14 +5737,14 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    adcl %edx, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    addl %ebp, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
@@ -5798,42 +5756,43 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %edx
-; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, %esi
 ; X32-NEXT:    addl %ecx, %esi
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %esi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    adcl %ebx, %ecx
+; X32-NEXT:    setb %bl
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X32-NEXT:    movzbl %bl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
@@ -5843,61 +5802,64 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %ecx, %edi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl %edi, %esi
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %ecx, %ebx
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %ebx
 ; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %ebp, %ecx
+; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    adcl %esi, %ebp
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -5906,7 +5868,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    addl %eax, %esi
 ; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    addl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    addl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, %esi
@@ -5916,28 +5878,29 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
@@ -5974,74 +5937,77 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %ebx
-; X32-NEXT:    movl 96(%ebx), %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl 100(%ebx), %ebx
-; X32-NEXT:    movl %esi, %eax
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT:    movl 96(%ecx), %ebx
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %esi, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT:    movl 100(%eax), %esi
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %ecx
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl %ebx, %esi
+; X32-NEXT:    setb %bl
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %esi, %ebx
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %esi, %edi
+; X32-NEXT:    movzbl %bl, %eax
 ; X32-NEXT:    adcl %eax, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    xorl %edx, %edx
 ; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    addl %eax, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %esi
-; X32-NEXT:    addl %ebx, %edi
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %ecx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ecx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %edi
-; X32-NEXT:    setb %cl
+; X32-NEXT:    adcl %esi, %ecx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ebx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %cl, %ecx
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
@@ -6055,37 +6021,35 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 104(%eax), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; X32-NEXT:    movl 104(%ebp), %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %esi, %eax
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl 12(%ebp), %eax
-; X32-NEXT:    movl 108(%eax), %edx
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %ebx, -112(%ebp) # 4-byte Spill
-; X32-NEXT:    mull %ebx
-; X32-NEXT:    movl %edx, %esi
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl 108(%ebp), %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %edi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %esi
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    adcl %ebx, %edi
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl %esi, %edi
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
+; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    movzbl %bl, %eax
 ; X32-NEXT:    adcl %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
@@ -6093,20 +6057,20 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %edx
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl %eax, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl %eax, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl %edx, %eax
-; X32-NEXT:    addl %edi, %esi
+; X32-NEXT:    addl %esi, %edi
 ; X32-NEXT:    adcl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl $0, %esi
+; X32-NEXT:    adcl $0, %edi
 ; X32-NEXT:    adcl $0, %eax
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
@@ -6114,25 +6078,26 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl %ebx, %esi
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ebx, %ebp
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movl %eax, %ebp
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl %ebx, %edi
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
@@ -6144,15 +6109,15 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %ebx, %ecx
+; X32-NEXT:    movl %edi, %ecx
 ; X32-NEXT:    imull %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
@@ -6160,51 +6125,50 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %ecx, %edx
 ; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    imull %edi, %esi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %eax, %ebp
 ; X32-NEXT:    addl %esi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    imull %edi, %esi
+; X32-NEXT:    imull %ecx, %esi
 ; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl %ebx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %ecx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
+; X32-NEXT:    movl %eax, %edi
+; X32-NEXT:    addl %ebx, %edi
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    addl %edi, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %ecx
-; X32-NEXT:    setb %bl
+; X32-NEXT:    adcl %esi, %ebx
+; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 12(%ebp), %edx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl 124(%edx), %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    imull %eax, %ecx
@@ -6215,84 +6179,86 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    addl %ecx, %edx
 ; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    addl %edx, %esi
-; X32-NEXT:    movl 112(%edi), %ebx
-; X32-NEXT:    movl 116(%edi), %ecx
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl 112(%edi), %ebp
+; X32-NEXT:    movl 116(%edi), %ebx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    imull %ecx, %edi
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    imull %ebx, %edi
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %ecx
+; X32-NEXT:    imull %ebp, %ecx
 ; X32-NEXT:    addl %edx, %ecx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %ecx
-; X32-NEXT:    adcl %edi, %ebx
-; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ebx, %ebp
+; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    setb %bl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
-; X32-NEXT:    addl %ebx, %eax
-; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 1-byte Folded Reload
-; X32-NEXT:    adcl %esi, %edx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %edi, %ebx
+; X32-NEXT:    adcl $0, %ecx
+; X32-NEXT:    movl %ebp, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    mull %edi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ecx, %ebp
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %edi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -6301,41 +6267,43 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    adcl $0, %edi
-; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
-; X32-NEXT:    addl %ebx, %eax
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ebx
+; X32-NEXT:    movl %edx, %ebx
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
+; X32-NEXT:    adcl $0, %ebx
+; X32-NEXT:    movl %edi, %eax
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %edi, %ecx
+; X32-NEXT:    adcl %ebx, %edi
 ; X32-NEXT:    setb %bl
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movzbl %bl, %ecx
-; X32-NEXT:    adcl %ecx, %edx
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    movl %esi, %ebp
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movzbl %bl, %edi
+; X32-NEXT:    adcl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    addl %eax, %esi
-; X32-NEXT:    adcl %edx, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    addl %eax, %edi
+; X32-NEXT:    adcl %edx, %esi
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
@@ -6344,7 +6312,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
@@ -6358,7 +6326,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -6384,25 +6352,25 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %ecx, %eax
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    movl %ebx, %eax
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %edi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %edi
 ; X32-NEXT:    adcl $0, %esi
 ; X32-NEXT:    movl %ecx, %eax
-; X32-NEXT:    mull {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    movl %edx, %ecx
 ; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    adcl %esi, %ecx
 ; X32-NEXT:    setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
+; X32-NEXT:    mull %ebp
 ; X32-NEXT:    addl %ecx, %eax
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X32-NEXT:    adcl %ecx, %edx
@@ -6414,61 +6382,62 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    adcl %edx, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
 ; X32-NEXT:    adcl %eax, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %edi, %ecx
+; X32-NEXT:    movl %ebp, %ecx
 ; X32-NEXT:    imull %eax, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    mull %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    addl %ecx, %edx
-; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    imull %ebp, %esi
 ; X32-NEXT:    addl %edx, %esi
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, %esi
+; X32-NEXT:    movl %eax, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    mull %edi
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %esi, %edx
+; X32-NEXT:    imull %ebx, %edi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    imull %edi, %esi
-; X32-NEXT:    addl %edx, %esi
+; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    addl %edi, %edx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    imull %eax, %edi
+; X32-NEXT:    addl %edx, %edi
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ecx
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    movl %eax, %ebx
-; X32-NEXT:    addl %ecx, %ebx
-; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, %ebx
+; X32-NEXT:    addl %esi, %ebx
+; X32-NEXT:    adcl $0, %edi
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    mull %ebp
+; X32-NEXT:    movl %ebp, %esi
+; X32-NEXT:    movl %edx, %ebp
 ; X32-NEXT:    addl %ebx, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl %esi, %edi
-; X32-NEXT:    setb %bl
+; X32-NEXT:    adcl %edi, %ebp
+; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    mull %ecx
-; X32-NEXT:    addl %edi, %eax
-; X32-NEXT:    movzbl %bl, %ecx
+; X32-NEXT:    mull %esi
+; X32-NEXT:    addl %ebp, %eax
+; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %edx
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -6477,146 +6446,139 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    imull %eax, %edi
-; X32-NEXT:    movl %eax, %esi
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    mull %ecx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ebp
 ; X32-NEXT:    addl %edi, %edx
-; X32-NEXT:    imull {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    imull %ebx, %ecx
 ; X32-NEXT:    addl %edx, %ecx
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    movl %eax, %ecx
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    imull %esi, %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    imull %edi, %ecx
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    mull %ebx
+; X32-NEXT:    mull %edi
 ; X32-NEXT:    addl %ecx, %edx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    imull %ebx, %ecx
+; X32-NEXT:    imull %edi, %ecx
 ; X32-NEXT:    addl %edx, %ecx
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl %ebp, %eax
 ; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %ebx, %eax
-; X32-NEXT:    mull %esi
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl %edi, %eax
-; X32-NEXT:    mull %esi
+; X32-NEXT:    movl %edi, %ebp
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    mull %ecx
+; X32-NEXT:    movl %edx, %edi
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %esi, %eax
+; X32-NEXT:    mull %ecx
 ; X32-NEXT:    movl %edx, %esi
 ; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    addl %ebx, %ecx
+; X32-NEXT:    addl %edi, %ecx
 ; X32-NEXT:    adcl $0, %esi
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    movl %ebp, %eax
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %edi
-; X32-NEXT:    addl %ecx, %eax
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl %eax, %ebp
+; X32-NEXT:    addl %ecx, %ebp
 ; X32-NEXT:    adcl %esi, %edi
 ; X32-NEXT:    setb %cl
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    mull %ebx
 ; X32-NEXT:    movl %edx, %esi
-; X32-NEXT:    addl %edi, %eax
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    addl %edi, %edx
 ; X32-NEXT:    movzbl %cl, %ecx
 ; X32-NEXT:    adcl %ecx, %esi
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, %ebx
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, %ebp
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
-; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
@@ -6626,18 +6588,18 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
-; X32-NEXT:    movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -6650,13 +6612,10 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
 ; X32-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
 ; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    adcl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
-; X32-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
-; X32-NEXT:    movl 16(%ebp), %ecx
+; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, (%ecx)
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
@@ -6689,36 +6648,34 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X32-NEXT:    movl %esi, 56(%ecx)
 ; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
 ; X32-NEXT:    movl %esi, 60(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 64(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 68(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 72(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 76(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 80(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 84(%ecx)
-; X32-NEXT:    movl %ebx, 88(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 92(%ecx)
-; X32-NEXT:    movl %edi, 96(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 100(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 104(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 108(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 112(%ecx)
-; X32-NEXT:    movl %edx, 116(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
-; X32-NEXT:    movl %eax, 120(%ecx)
-; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 64(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 68(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 72(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 76(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 80(%ecx)
+; X32-NEXT:    movl %ebp, 84(%ecx)
+; X32-NEXT:    movl %edi, 88(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 92(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 96(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 100(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 104(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 108(%ecx)
+; X32-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X32-NEXT:    movl %esi, 112(%ecx)
+; X32-NEXT:    movl %ebx, 116(%ecx)
+; X32-NEXT:    movl %edx, 120(%ecx)
 ; X32-NEXT:    movl %eax, 124(%ecx)
-; X32-NEXT:    addl $996, %esp # imm = 0x3E4
+; X32-NEXT:    addl $1000, %esp # imm = 0x3E8
 ; X32-NEXT:    popl %esi
 ; X32-NEXT:    popl %edi
 ; X32-NEXT:    popl %ebx
@@ -6798,8 +6755,8 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    adcq %rdx, %rbx
 ; X64-NEXT:    movq 16(%rsi), %rax
 ; X64-NEXT:    movq %rsi, %r13
-; X64-NEXT:    movq %r13, {{[0-9]+}}(%rsp) # 8-byte Spill
-; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r13, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
+; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    mulq %r11
 ; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
@@ -6811,7 +6768,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    adcq %rbx, %r11
 ; X64-NEXT:    movq %r8, %rax
 ; X64-NEXT:    movq %r8, %rbp
-; X64-NEXT:    movq %rbp, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbp, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    movq %r9, %rax
 ; X64-NEXT:    adcq %rcx, %rax
@@ -6841,9 +6798,9 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    movq %rbp, %rax
 ; X64-NEXT:    addq %r9, %rax
-; X64-NEXT:    movq %rax, -{{[0-9]+}}(%rsp) # 8-byte Spill
-; X64-NEXT:    movq %r9, {{[0-9]+}}(%rsp) # 8-byte Spill
-; X64-NEXT:    movq -{{[0-9]+}}(%rsp), %rax # 8-byte Reload
+; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
+; X64-NEXT:    movq %r9, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
+; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
 ; X64-NEXT:    adcq %r15, %rax
 ; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    adcq %r14, %r12
@@ -6881,7 +6838,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    adcq %rbx, %r10
 ; X64-NEXT:    movq %rcx, %rdx
 ; X64-NEXT:    movq %rcx, %r12
-; X64-NEXT:    movq %r12, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r12, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    addq %r9, %rdx
 ; X64-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    movq %r11, %r8
@@ -7031,7 +6988,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    movq %rbx, %rax
 ; X64-NEXT:    mulq %rcx
 ; X64-NEXT:    movq %rcx, %rbx
-; X64-NEXT:    movq %rbx, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rbx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    movq %rdx, %rcx
 ; X64-NEXT:    movq %rax, %r8
 ; X64-NEXT:    addq %rbp, %r8
@@ -7395,7 +7352,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    adcq $0, %r15
 ; X64-NEXT:    movq %rbp, %rax
 ; X64-NEXT:    movq %r8, %rdi
-; X64-NEXT:    movq %rdi, {{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    mulq %rdi
 ; X64-NEXT:    movq %rdx, %r9
 ; X64-NEXT:    movq %rax, %r8
@@ -7643,7 +7600,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    movq %r9, %rax
 ; X64-NEXT:    mulq %rcx
 ; X64-NEXT:    movq %rcx, %r10
-; X64-NEXT:    movq %r10, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    movq %rdx, %rcx
 ; X64-NEXT:    movq %rax, %rdi
 ; X64-NEXT:    addq %rsi, %rdi
@@ -7663,7 +7620,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload
 ; X64-NEXT:    movq %rcx, %rax
 ; X64-NEXT:    movq %r11, %rsi
-; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    mulq %rsi
 ; X64-NEXT:    movq %rdx, %r11
 ; X64-NEXT:    movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
@@ -7906,7 +7863,7 @@ define void @test_1024(i1024* %a, i1024* %b, i1024* %out) nounwind {
 ; X64-NEXT:    movq 88(%rsi), %rax
 ; X64-NEXT:    movq %rsi, %r9
 ; X64-NEXT:    movq %rax, %rsi
-; X64-NEXT:    movq %rsi, -{{[0-9]+}}(%rsp) # 8-byte Spill
+; X64-NEXT:    movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; X64-NEXT:    mulq %rcx
 ; X64-NEXT:    movq %rcx, %r11
 ; X64-NEXT:    movq %rdx, %rbp

diff --git a/test/CodeGen/X86/peephole-na-phys-copy-folding.ll b/test/CodeGen/X86/peephole-na-phys-copy-folding.ll
index 66047e3677f64b30a5c0ee6cc1970179f979be57..d011916f0935d593ff07a7851d070381df8648f7 100644 (file)
--- a/test/CodeGen/X86/peephole-na-phys-copy-folding.ll
+++ b/test/CodeGen/X86/peephole-na-phys-copy-folding.ll
@@ -1,13 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=i386-linux-gnu %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK32
-; RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sahf %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK64
-
-; TODO: Reenable verify-machineinstrs once the if (!AXDead) // FIXME in
-; X86InstrInfo::copyPhysReg() is resolved.
+; RUN: llc -mtriple=i386-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK32
+; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK64
 
 ; The peephole optimizer can elide some physical register copies such as
 ; EFLAGS. Make sure the flags are used directly, instead of needlessly using
-; lahf, when possible.
+; saving and restoring specific conditions.
 
 @L = external global i32
 @M = external global i8
@@ -209,29 +206,22 @@ exit2:
 define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
 ; CHECK32-LABEL: test_intervening_call:
 ; CHECK32:       # %bb.0: # %entry
-; CHECK32-NEXT:    pushl %ebp
-; CHECK32-NEXT:    movl %esp, %ebp
 ; CHECK32-NEXT:    pushl %ebx
 ; CHECK32-NEXT:    pushl %esi
-; CHECK32-NEXT:    movl 12(%ebp), %eax
-; CHECK32-NEXT:    movl 16(%ebp), %edx
-; CHECK32-NEXT:    movl 20(%ebp), %ebx
-; CHECK32-NEXT:    movl 24(%ebp), %ecx
-; CHECK32-NEXT:    movl 8(%ebp), %esi
-; CHECK32-NEXT:    lock cmpxchg8b (%esi)
 ; CHECK32-NEXT:    pushl %eax
-; CHECK32-NEXT:    seto %al
-; CHECK32-NEXT:    lahf
-; CHECK32-NEXT:    movl %eax, %esi
-; CHECK32-NEXT:    popl %eax
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; CHECK32-NEXT:    lock cmpxchg8b (%esi)
+; CHECK32-NEXT:    setne %bl
 ; CHECK32-NEXT:    subl $8, %esp
 ; CHECK32-NEXT:    pushl %edx
 ; CHECK32-NEXT:    pushl %eax
 ; CHECK32-NEXT:    calll bar
 ; CHECK32-NEXT:    addl $16, %esp
-; CHECK32-NEXT:    movl %esi, %eax
-; CHECK32-NEXT:    addb $127, %al
-; CHECK32-NEXT:    sahf
+; CHECK32-NEXT:    testb $-1, %bl
 ; CHECK32-NEXT:    jne .LBB4_3
 ; CHECK32-NEXT:  # %bb.1: # %t
 ; CHECK32-NEXT:    movl $42, %eax
@@ -240,39 +230,28 @@ define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
 ; CHECK32-NEXT:    xorl %eax, %eax
 ; CHECK32-NEXT:  .LBB4_2: # %t
 ; CHECK32-NEXT:    xorl %edx, %edx
+; CHECK32-NEXT:    addl $4, %esp
 ; CHECK32-NEXT:    popl %esi
 ; CHECK32-NEXT:    popl %ebx
-; CHECK32-NEXT:    popl %ebp
 ; CHECK32-NEXT:    retl
 ;
 ; CHECK64-LABEL: test_intervening_call:
 ; CHECK64:       # %bb.0: # %entry
-; CHECK64-NEXT:    pushq %rbp
-; CHECK64-NEXT:    movq %rsp, %rbp
 ; CHECK64-NEXT:    pushq %rbx
-; CHECK64-NEXT:    pushq %rax
 ; CHECK64-NEXT:    movq %rsi, %rax
 ; CHECK64-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; CHECK64-NEXT:    pushq %rax
-; CHECK64-NEXT:    seto %al
-; CHECK64-NEXT:    lahf
-; CHECK64-NEXT:    movq %rax, %rbx
-; CHECK64-NEXT:    popq %rax
+; CHECK64-NEXT:    setne %bl
 ; CHECK64-NEXT:    movq %rax, %rdi
 ; CHECK64-NEXT:    callq bar
-; CHECK64-NEXT:    movq %rbx, %rax
-; CHECK64-NEXT:    addb $127, %al
-; CHECK64-NEXT:    sahf
-; CHECK64-NEXT:    jne .LBB4_3
+; CHECK64-NEXT:    testb $-1, %bl
+; CHECK64-NEXT:    jne .LBB4_2
 ; CHECK64-NEXT:  # %bb.1: # %t
 ; CHECK64-NEXT:    movl $42, %eax
-; CHECK64-NEXT:    jmp .LBB4_2
-; CHECK64-NEXT:  .LBB4_3: # %f
+; CHECK64-NEXT:    popq %rbx
+; CHECK64-NEXT:    retq
+; CHECK64-NEXT:  .LBB4_2: # %f
 ; CHECK64-NEXT:    xorl %eax, %eax
-; CHECK64-NEXT:  .LBB4_2: # %t
-; CHECK64-NEXT:    addq $8, %rsp
 ; CHECK64-NEXT:    popq %rbx
-; CHECK64-NEXT:    popq %rbp
 ; CHECK64-NEXT:    retq
 entry:
   ; cmpxchg sets EFLAGS, call clobbers it, then br uses EFLAGS.
@@ -293,32 +272,27 @@ define i64 @test_two_live_flags(i64* %foo0, i64 %bar0, i64 %baz0, i64* %foo1, i6
 ; CHECK32-LABEL: test_two_live_flags:
 ; CHECK32:       # %bb.0: # %entry
 ; CHECK32-NEXT:    pushl %ebp
-; CHECK32-NEXT:    movl %esp, %ebp
 ; CHECK32-NEXT:    pushl %ebx
 ; CHECK32-NEXT:    pushl %edi
 ; CHECK32-NEXT:    pushl %esi
-; CHECK32-NEXT:    movl 44(%ebp), %edi
-; CHECK32-NEXT:    movl 12(%ebp), %eax
-; CHECK32-NEXT:    movl 16(%ebp), %edx
-; CHECK32-NEXT:    movl 20(%ebp), %ebx
-; CHECK32-NEXT:    movl 24(%ebp), %ecx
-; CHECK32-NEXT:    movl 8(%ebp), %esi
+; CHECK32-NEXT:    pushl %eax
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ebp
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; CHECK32-NEXT:    lock cmpxchg8b (%esi)
+; CHECK32-NEXT:    setne {{[0-9]+}}(%esp) # 1-byte Folded Spill
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT:    movl %edi, %edx
+; CHECK32-NEXT:    movl %ebp, %ecx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; CHECK32-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; CHECK32-NEXT:    lock cmpxchg8b (%esi)
-; CHECK32-NEXT:    seto %al
-; CHECK32-NEXT:    lahf
-; CHECK32-NEXT:    movl %eax, %esi
-; CHECK32-NEXT:    movl 32(%ebp), %eax
-; CHECK32-NEXT:    movl 36(%ebp), %edx
-; CHECK32-NEXT:    movl %edi, %ecx
-; CHECK32-NEXT:    movl 40(%ebp), %ebx
-; CHECK32-NEXT:    movl 28(%ebp), %edi
-; CHECK32-NEXT:    lock cmpxchg8b (%edi)
 ; CHECK32-NEXT:    sete %al
-; CHECK32-NEXT:    pushl %eax
-; CHECK32-NEXT:    movl %esi, %eax
-; CHECK32-NEXT:    addb $127, %al
-; CHECK32-NEXT:    sahf
-; CHECK32-NEXT:    popl %eax
+; CHECK32-NEXT:    testb $-1, {{[0-9]+}}(%esp) # 1-byte Folded Reload
 ; CHECK32-NEXT:    jne .LBB5_4
 ; CHECK32-NEXT:  # %bb.1: # %entry
 ; CHECK32-NEXT:    testb %al, %al
@@ -330,6 +304,7 @@ define i64 @test_two_live_flags(i64* %foo0, i64 %bar0, i64 %baz0, i64* %foo1, i6
 ; CHECK32-NEXT:    xorl %eax, %eax
 ; CHECK32-NEXT:  .LBB5_3: # %t
 ; CHECK32-NEXT:    xorl %edx, %edx
+; CHECK32-NEXT:    addl $4, %esp
 ; CHECK32-NEXT:    popl %esi
 ; CHECK32-NEXT:    popl %edi
 ; CHECK32-NEXT:    popl %ebx
@@ -338,32 +313,22 @@ define i64 @test_two_live_flags(i64* %foo0, i64 %bar0, i64 %baz0, i64* %foo1, i6
 ;
 ; CHECK64-LABEL: test_two_live_flags:
 ; CHECK64:       # %bb.0: # %entry
-; CHECK64-NEXT:    pushq %rbp
-; CHECK64-NEXT:    movq %rsp, %rbp
 ; CHECK64-NEXT:    movq %rsi, %rax
 ; CHECK64-NEXT:    lock cmpxchgq %rdx, (%rdi)
-; CHECK64-NEXT:    seto %al
-; CHECK64-NEXT:    lahf
-; CHECK64-NEXT:    movq %rax, %rdx
+; CHECK64-NEXT:    setne %dl
 ; CHECK64-NEXT:    movq %r8, %rax
 ; CHECK64-NEXT:    lock cmpxchgq %r9, (%rcx)
 ; CHECK64-NEXT:    sete %al
-; CHECK64-NEXT:    pushq %rax
-; CHECK64-NEXT:    movq %rdx, %rax
-; CHECK64-NEXT:    addb $127, %al
-; CHECK64-NEXT:    sahf
-; CHECK64-NEXT:    popq %rax
+; CHECK64-NEXT:    testb $-1, %dl
 ; CHECK64-NEXT:    jne .LBB5_3
 ; CHECK64-NEXT:  # %bb.1: # %entry
 ; CHECK64-NEXT:    testb %al, %al
 ; CHECK64-NEXT:    je .LBB5_3
 ; CHECK64-NEXT:  # %bb.2: # %t
 ; CHECK64-NEXT:    movl $42, %eax
-; CHECK64-NEXT:    popq %rbp
 ; CHECK64-NEXT:    retq
 ; CHECK64-NEXT:  .LBB5_3: # %f
 ; CHECK64-NEXT:    xorl %eax, %eax
-; CHECK64-NEXT:    popq %rbp
 ; CHECK64-NEXT:    retq
 entry:
   %cx0 = cmpxchg i64* %foo0, i64 %bar0, i64 %baz0 seq_cst seq_cst

diff --git a/test/CodeGen/X86/win64_frame.ll b/test/CodeGen/X86/win64_frame.ll
index 28f712b30f6db57a4418bf618336e321aabadf95..516bff33ee8d56a71383339dae0be039dff6e5e6 100644 (file)
--- a/test/CodeGen/X86/win64_frame.ll
+++ b/test/CodeGen/X86/win64_frame.ll
@@ -225,71 +225,29 @@ entry:
 declare i64 @dummy()
 
 define i64 @f10(i64* %foo, i64 %bar, i64 %baz) {
-; PUSHF-LABEL: f10:
-; PUSHF:       # %bb.0:
-; PUSHF-NEXT:    pushq %rbp
-; PUSHF-NEXT:    .seh_pushreg 5
-; PUSHF-NEXT:    pushq %rsi
-; PUSHF-NEXT:    .seh_pushreg 6
-; PUSHF-NEXT:    pushq %rdi
-; PUSHF-NEXT:    .seh_pushreg 7
-; PUSHF-NEXT:    subq $32, %rsp
-; PUSHF-NEXT:    .seh_stackalloc 32
-; PUSHF-NEXT:    leaq {{[0-9]+}}(%rsp), %rbp
-; PUSHF-NEXT:    .seh_setframe 5, 32
-; PUSHF-NEXT:    .seh_endprologue
-; PUSHF-NEXT:    movq %rdx, %rsi
-; PUSHF-NEXT:    movq %rsi, %rax
-; PUSHF-NEXT:    lock cmpxchgq %r8, (%rcx)
-; PUSHF-NEXT:    pushfq
-; PUSHF-NEXT:    popq %rdi
-; PUSHF-NEXT:    callq dummy
-; PUSHF-NEXT:    pushq %rdi
-; PUSHF-NEXT:    popfq
-; PUSHF-NEXT:    cmovneq %rsi, %rax
-; PUSHF-NEXT:    addq $32, %rsp
-; PUSHF-NEXT:    popq %rdi
-; PUSHF-NEXT:    popq %rsi
-; PUSHF-NEXT:    popq %rbp
-; PUSHF-NEXT:    retq
-; PUSHF-NEXT:    .seh_handlerdata
-; PUSHF-NEXT:    .text
-; PUSHF-NEXT:    .seh_endproc
-;
-; SAHF-LABEL: f10:
-; SAHF:       # %bb.0:
-; SAHF-NEXT:    pushq %rbp
-; SAHF-NEXT:    .seh_pushreg 5
-; SAHF-NEXT:    pushq %rsi
-; SAHF-NEXT:    .seh_pushreg 6
-; SAHF-NEXT:    pushq %rdi
-; SAHF-NEXT:    .seh_pushreg 7
-; SAHF-NEXT:    subq $32, %rsp
-; SAHF-NEXT:    .seh_stackalloc 32
-; SAHF-NEXT:    leaq {{[0-9]+}}(%rsp), %rbp
-; SAHF-NEXT:    .seh_setframe 5, 32
-; SAHF-NEXT:    .seh_endprologue
-; SAHF-NEXT:    movq %rdx, %rsi
-; SAHF-NEXT:    movq %rsi, %rax
-; SAHF-NEXT:    lock cmpxchgq %r8, (%rcx)
-; SAHF-NEXT:    seto %al
-; SAHF-NEXT:    lahf
-; SAHF-NEXT:    movq %rax, %rdi
-; SAHF-NEXT:    callq dummy
-; SAHF-NEXT:    pushq %rax
-; SAHF-NEXT:    movq %rdi, %rax
-; SAHF-NEXT:    addb $127, %al
-; SAHF-NEXT:    sahf
-; SAHF-NEXT:    popq %rax
-; SAHF-NEXT:    cmovneq %rsi, %rax
-; SAHF-NEXT:    addq $32, %rsp
-; SAHF-NEXT:    popq %rdi
-; SAHF-NEXT:    popq %rsi
-; SAHF-NEXT:    popq %rbp
-; SAHF-NEXT:    retq
-; SAHF-NEXT:    .seh_handlerdata
-; SAHF-NEXT:    .text
-; SAHF-NEXT:    .seh_endproc
+; ALL-LABEL: f10:
+; ALL:       # %bb.0:
+; ALL-NEXT:    pushq %rsi
+; ALL-NEXT:    .seh_pushreg 6
+; ALL-NEXT:    pushq %rbx
+; ALL-NEXT:    .seh_pushreg 3
+; ALL-NEXT:    subq $40, %rsp
+; ALL-NEXT:    .seh_stackalloc 40
+; ALL-NEXT:    .seh_endprologue
+; ALL-NEXT:    movq %rdx, %rsi
+; ALL-NEXT:    movq %rsi, %rax
+; ALL-NEXT:    lock cmpxchgq %r8, (%rcx)
+; ALL-NEXT:    sete %bl
+; ALL-NEXT:    callq dummy
+; ALL-NEXT:    testb $-1, %bl
+; ALL-NEXT:    cmoveq %rsi, %rax
+; ALL-NEXT:    addq $40, %rsp
+; ALL-NEXT:    popq %rbx
+; ALL-NEXT:    popq %rsi
+; ALL-NEXT:    retq
+; ALL-NEXT:    .seh_handlerdata
+; ALL-NEXT:    .text
+; ALL-NEXT:    .seh_endproc
   %cx = cmpxchg i64* %foo, i64 %bar, i64 %baz seq_cst seq_cst
   %v = extractvalue { i64, i1 } %cx, 0
   %p = extractvalue { i64, i1 } %cx, 1

diff --git a/test/CodeGen/X86/x86-repmov-copy-eflags.ll b/test/CodeGen/X86/x86-repmov-copy-eflags.ll
index ad3988857284950edc62904661727d3a663003f3..a51f09ef23c4353c68cbfaab82a3ba2bf6718467 100644 (file)
--- a/test/CodeGen/X86/x86-repmov-copy-eflags.ll
+++ b/test/CodeGen/X86/x86-repmov-copy-eflags.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s | FileCheck %s
+; RUN: llc -verify-machineinstrs < %s | FileCheck %s
 target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
 target triple = "i686-pc-windows-msvc18.0.0"
 
@@ -39,15 +39,12 @@ declare void @g(%struct.T*)
 ; CHECK:     leal 8(%esp), %esi
 
 ; CHECK:     decl     (%esp)
-; CHECK:     seto     %al
-; CHECK:     lahf
-; CHECK:     movl     %eax, %edi
+; CHECK:     setne    %[[NE_REG:.*]]
 ; CHECK:     pushl     %esi
 ; CHECK:     calll     _g
 ; CHECK:     addl     $4, %esp
-; CHECK:     movl     %edi, %eax
-; CHECK:     addb     $127, %al
-; CHECK:     sahf
+; CHECK:     testb    $-1, %[[NE_REG]]
+; CHECK:     jne
 
 attributes #0 = { nounwind optsize }
 attributes #1 = { argmemonly nounwind }