[X86] Add custom isel to select ADD/SUB/OR/XOR/AND to their non-immediate forms under...

Summary:
We attempt to prevent folding immediates with multiple users under optsize. But we only do this from store nodes and X86ISD::ADD/SUB/XOR/OR/AND patterns. We don't do it for ISD::ADD/SUB/XOR/OR/AND even though we count them as users when deciding whether to fold into other nodes. This leads to situations where we block folding to a compare for example, but still fold into an AND or OR as seen in PR27202.

Unfortunately touching the isel patterns in tablegen for the ISD::ADD/SUB/XOR/OR/AND opcodes will cause the patterns to be unusable for fast isel. And we don't have a way to make a fast isel only pattern.

To workaround this, this patch adds custom isel in front of the isel table that will select the non-immediate forms if the immediate has additional users. This may create some issues for ANDN and NOT matching. And there's room for improvement with unsigned 32 immediates on 64-bit AND.

This patch needs more thorough test cases, but I wanted to get feedback on the direction. Please send me any other test cases you've seen in the wild.

I think we probably have the same issue with the immediate matching when we fold RMW from X86ISD::ADD/SUB/XOR/OR/AND. And our TEST immedaite shrinking logic. Our cost modeling for immediates that can fit in a sign extended 8-bit immediate on a 16/32/64 bit operation is completely wrong.

I also wonder if we should update the ConstantHoisting cost model and block folding for "opaque" constants. But of course constants can still be created by DAG combine and lowering optimizations.

Fixes PR27202

Reviewers: spatel, RKSimon, andreadb

Reviewed By: RKSimon

Subscribers: jsji, hiraditya, jdoerfert, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59909

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365163 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelDAGToDAG.cpp b/lib/Target/X86/X86ISelDAGToDAG.cpp
index ccda8babf5141de6b167484745315ae2c3a0af2b..95d31e62cafc8671a1007733db12dda0cdc8d29b 100644 (file)
--- a/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -4302,7 +4302,109 @@ void X86DAGToDAGISel::Select(SDNode *Node) {
   case ISD::XOR:
     if (tryShrinkShlLogicImm(Node))
       return;
-    break;
+
+    LLVM_FALLTHROUGH;
+  case ISD::ADD:
+  case ISD::SUB: {
+    // Try to avoid folding immediates with multiple uses for optsize.
+    // This code tries to select to register form directly to avoid going
+    // through the isel table which might fold the immediate. We can't change
+    // the patterns on the add/sub/and/or/xor with immediate paterns in the
+    // tablegen files to check immediate use count without making the patterns
+    // unavailable to the fast-isel table.
+    if (!OptForSize)
+      break;
+
+    // Only handle i8/i16/i32/i64.
+    if (NVT != MVT::i8 && NVT != MVT::i16 && NVT != MVT::i32 && NVT != MVT::i64)
+      break;
+
+    SDValue N0 = Node->getOperand(0);
+    SDValue N1 = Node->getOperand(1);
+
+    ConstantSDNode *Cst = dyn_cast<ConstantSDNode>(N1);
+    if (!Cst)
+      break;
+
+    int64_t Val = Cst->getSExtValue();
+
+    // Make sure its an immediate that is considered foldable.
+    // FIXME: Handle unsigned 32 bit immediates for 64-bit AND.
+    if (!isInt<8>(Val) && !isInt<32>(Val))
+      break;
+
+    // Check if we should avoid folding this immediate.
+    if (!shouldAvoidImmediateInstFormsForSize(N1.getNode()))
+      break;
+
+    // We should not fold the immediate. So we need a register form instead.
+    unsigned ROpc, MOpc;
+    switch (NVT.SimpleTy) {
+    default: llvm_unreachable("Unexpected VT!");
+    case MVT::i8:
+      switch (Opcode) {
+      default: llvm_unreachable("Unexpected opcode!");
+      case ISD::ADD: ROpc = X86::ADD8rr; MOpc = X86::ADD8rm; break;
+      case ISD::SUB: ROpc = X86::SUB8rr; MOpc = X86::SUB8rm; break;
+      case ISD::AND: ROpc = X86::AND8rr; MOpc = X86::AND8rm; break;
+      case ISD::OR:  ROpc = X86::OR8rr;  MOpc = X86::OR8rm;  break;
+      case ISD::XOR: ROpc = X86::XOR8rr; MOpc = X86::XOR8rm; break;
+      }
+      break;
+    case MVT::i16:
+      switch (Opcode) {
+      default: llvm_unreachable("Unexpected opcode!");
+      case ISD::ADD: ROpc = X86::ADD16rr; MOpc = X86::ADD16rm; break;
+      case ISD::SUB: ROpc = X86::SUB16rr; MOpc = X86::SUB16rm; break;
+      case ISD::AND: ROpc = X86::AND16rr; MOpc = X86::AND16rm; break;
+      case ISD::OR:  ROpc = X86::OR16rr;  MOpc = X86::OR16rm;  break;
+      case ISD::XOR: ROpc = X86::XOR16rr; MOpc = X86::XOR16rm; break;
+      }
+      break;
+    case MVT::i32:
+      switch (Opcode) {
+      default: llvm_unreachable("Unexpected opcode!");
+      case ISD::ADD: ROpc = X86::ADD32rr; MOpc = X86::ADD32rm; break;
+      case ISD::SUB: ROpc = X86::SUB32rr; MOpc = X86::SUB32rm; break;
+      case ISD::AND: ROpc = X86::AND32rr; MOpc = X86::AND32rm; break;
+      case ISD::OR:  ROpc = X86::OR32rr;  MOpc = X86::OR32rm;  break;
+      case ISD::XOR: ROpc = X86::XOR32rr; MOpc = X86::XOR32rm; break;
+      }
+      break;
+    case MVT::i64:
+      switch (Opcode) {
+      default: llvm_unreachable("Unexpected opcode!");
+      case ISD::ADD: ROpc = X86::ADD64rr; MOpc = X86::ADD64rm; break;
+      case ISD::SUB: ROpc = X86::SUB64rr; MOpc = X86::SUB64rm; break;
+      case ISD::AND: ROpc = X86::AND64rr; MOpc = X86::AND64rm; break;
+      case ISD::OR:  ROpc = X86::OR64rr;  MOpc = X86::OR64rm;  break;
+      case ISD::XOR: ROpc = X86::XOR64rr; MOpc = X86::XOR64rm; break;
+      }
+      break;
+    }
+
+    // Ok this is a AND/OR/XOR/ADD/SUB with constant.
+
+    // If this is a not a subtract, we can still try to fold a load.
+    if (Opcode != ISD::SUB) {
+      SDValue Tmp0, Tmp1, Tmp2, Tmp3, Tmp4;
+      if (tryFoldLoad(Node, N0, Tmp0, Tmp1, Tmp2, Tmp3, Tmp4)) {
+        SDValue Ops[] = { N1, Tmp0, Tmp1, Tmp2, Tmp3, Tmp4, N0.getOperand(0) };
+        SDVTList VTs = CurDAG->getVTList(NVT, MVT::i32, MVT::Other);
+        MachineSDNode *CNode = CurDAG->getMachineNode(MOpc, dl, VTs, Ops);
+        // Update the chain.
+        ReplaceUses(N0.getValue(1), SDValue(CNode, 2));
+        // Record the mem-refs
+        CurDAG->setNodeMemRefs(CNode, {cast<LoadSDNode>(N0)->getMemOperand()});
+        ReplaceUses(SDValue(Node, 0), SDValue(CNode, 0));
+        CurDAG->RemoveDeadNode(Node);
+        return;
+      }
+    }
+
+    CurDAG->SelectNodeTo(Node, ROpc, NVT, MVT::i32, N0, N1);
+    return;
+  }
 
   case X86ISD::SMUL:
     // i16/i32/i64 are handled with isel patterns.

diff --git a/test/CodeGen/X86/popcnt.ll b/test/CodeGen/X86/popcnt.ll
index 7405c23502aead48c6928db5a03dde2cf92292ad..c68a3a5fe3246463d2944da414591e2dc5c8eb06 100644 (file)
--- a/test/CodeGen/X86/popcnt.ll
+++ b/test/CodeGen/X86/popcnt.ll
@@ -613,11 +613,12 @@ define i32 @cnt32_optsize(i32 %x) nounwind readnone optsize {
 ; X32-NEXT:    shrl %ecx
 ; X32-NEXT:    andl $1431655765, %ecx # imm = 0x55555555
 ; X32-NEXT:    subl %ecx, %eax
-; X32-NEXT:    movl %eax, %ecx
-; X32-NEXT:    andl $858993459, %ecx # imm = 0x33333333
+; X32-NEXT:    movl $858993459, %ecx # imm = 0x33333333
+; X32-NEXT:    movl %eax, %edx
+; X32-NEXT:    andl %ecx, %edx
 ; X32-NEXT:    shrl $2, %eax
-; X32-NEXT:    andl $858993459, %eax # imm = 0x33333333
-; X32-NEXT:    addl %ecx, %eax
+; X32-NEXT:    andl %ecx, %eax
+; X32-NEXT:    addl %edx, %eax
 ; X32-NEXT:    movl %eax, %ecx
 ; X32-NEXT:    shrl $4, %ecx
 ; X32-NEXT:    addl %eax, %ecx
@@ -632,11 +633,12 @@ define i32 @cnt32_optsize(i32 %x) nounwind readnone optsize {
 ; X64-NEXT:    shrl %eax
 ; X64-NEXT:    andl $1431655765, %eax # imm = 0x55555555
 ; X64-NEXT:    subl %eax, %edi
-; X64-NEXT:    movl %edi, %eax
-; X64-NEXT:    andl $858993459, %eax # imm = 0x33333333
+; X64-NEXT:    movl $858993459, %eax # imm = 0x33333333
+; X64-NEXT:    movl %edi, %ecx
+; X64-NEXT:    andl %eax, %ecx
 ; X64-NEXT:    shrl $2, %edi
-; X64-NEXT:    andl $858993459, %edi # imm = 0x33333333
-; X64-NEXT:    addl %eax, %edi
+; X64-NEXT:    andl %eax, %edi
+; X64-NEXT:    addl %ecx, %edi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shrl $4, %eax
 ; X64-NEXT:    addl %edi, %eax
@@ -661,40 +663,49 @@ define i32 @cnt32_optsize(i32 %x) nounwind readnone optsize {
 define i64 @cnt64_optsize(i64 %x) nounwind readnone optsize {
 ; X32-NOSSE-LABEL: cnt64_optsize:
 ; X32-NOSSE:       # %bb.0:
+; X32-NOSSE-NEXT:    pushl %ebx
+; X32-NOSSE-NEXT:    pushl %edi
+; X32-NOSSE-NEXT:    pushl %esi
 ; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NOSSE-NEXT:    movl %ecx, %edx
 ; X32-NOSSE-NEXT:    shrl %edx
-; X32-NOSSE-NEXT:    andl $1431655765, %edx # imm = 0x55555555
+; X32-NOSSE-NEXT:    movl $1431655765, %esi # imm = 0x55555555
+; X32-NOSSE-NEXT:    andl %esi, %edx
 ; X32-NOSSE-NEXT:    subl %edx, %ecx
-; X32-NOSSE-NEXT:    movl %ecx, %edx
-; X32-NOSSE-NEXT:    andl $858993459, %edx # imm = 0x33333333
+; X32-NOSSE-NEXT:    movl $858993459, %edx # imm = 0x33333333
+; X32-NOSSE-NEXT:    movl %ecx, %edi
+; X32-NOSSE-NEXT:    andl %edx, %edi
 ; X32-NOSSE-NEXT:    shrl $2, %ecx
-; X32-NOSSE-NEXT:    andl $858993459, %ecx # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %edx, %ecx
-; X32-NOSSE-NEXT:    movl %ecx, %edx
-; X32-NOSSE-NEXT:    shrl $4, %edx
-; X32-NOSSE-NEXT:    addl %ecx, %edx
-; X32-NOSSE-NEXT:    andl $252645135, %edx # imm = 0xF0F0F0F
-; X32-NOSSE-NEXT:    imull $16843009, %edx, %ecx # imm = 0x1010101
-; X32-NOSSE-NEXT:    shrl $24, %ecx
-; X32-NOSSE-NEXT:    movl %eax, %edx
-; X32-NOSSE-NEXT:    shrl %edx
-; X32-NOSSE-NEXT:    andl $1431655765, %edx # imm = 0x55555555
-; X32-NOSSE-NEXT:    subl %edx, %eax
-; X32-NOSSE-NEXT:    movl %eax, %edx
-; X32-NOSSE-NEXT:    andl $858993459, %edx # imm = 0x33333333
+; X32-NOSSE-NEXT:    andl %edx, %ecx
+; X32-NOSSE-NEXT:    addl %edi, %ecx
+; X32-NOSSE-NEXT:    movl %ecx, %edi
+; X32-NOSSE-NEXT:    shrl $4, %edi
+; X32-NOSSE-NEXT:    addl %ecx, %edi
+; X32-NOSSE-NEXT:    movl $252645135, %ecx # imm = 0xF0F0F0F
+; X32-NOSSE-NEXT:    andl %ecx, %edi
+; X32-NOSSE-NEXT:    imull $16843009, %edi, %edi # imm = 0x1010101
+; X32-NOSSE-NEXT:    shrl $24, %edi
+; X32-NOSSE-NEXT:    movl %eax, %ebx
+; X32-NOSSE-NEXT:    shrl %ebx
+; X32-NOSSE-NEXT:    andl %esi, %ebx
+; X32-NOSSE-NEXT:    subl %ebx, %eax
+; X32-NOSSE-NEXT:    movl %eax, %esi
+; X32-NOSSE-NEXT:    andl %edx, %esi
 ; X32-NOSSE-NEXT:    shrl $2, %eax
-; X32-NOSSE-NEXT:    andl $858993459, %eax # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %edx, %eax
+; X32-NOSSE-NEXT:    andl %edx, %eax
+; X32-NOSSE-NEXT:    addl %esi, %eax
 ; X32-NOSSE-NEXT:    movl %eax, %edx
 ; X32-NOSSE-NEXT:    shrl $4, %edx
 ; X32-NOSSE-NEXT:    addl %eax, %edx
-; X32-NOSSE-NEXT:    andl $252645135, %edx # imm = 0xF0F0F0F
+; X32-NOSSE-NEXT:    andl %ecx, %edx
 ; X32-NOSSE-NEXT:    imull $16843009, %edx, %eax # imm = 0x1010101
 ; X32-NOSSE-NEXT:    shrl $24, %eax
-; X32-NOSSE-NEXT:    addl %ecx, %eax
+; X32-NOSSE-NEXT:    addl %edi, %eax
 ; X32-NOSSE-NEXT:    xorl %edx, %edx
+; X32-NOSSE-NEXT:    popl %esi
+; X32-NOSSE-NEXT:    popl %edi
+; X32-NOSSE-NEXT:    popl %ebx
 ; X32-NOSSE-NEXT:    retl
 ;
 ; X64-LABEL: cnt64_optsize:
@@ -781,77 +792,83 @@ define i64 @cnt64_optsize(i64 %x) nounwind readnone optsize {
 define i128 @cnt128_optsize(i128 %x) nounwind readnone optsize {
 ; X32-NOSSE-LABEL: cnt128_optsize:
 ; X32-NOSSE:       # %bb.0:
+; X32-NOSSE-NEXT:    pushl %ebp
 ; X32-NOSSE-NEXT:    pushl %ebx
 ; X32-NOSSE-NEXT:    pushl %edi
 ; X32-NOSSE-NEXT:    pushl %esi
-; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %esi
-; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X32-NOSSE-NEXT:    movl %edi, %ebx
+; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ebx
+; X32-NOSSE-NEXT:    movl %ebx, %ecx
+; X32-NOSSE-NEXT:    shrl %ecx
+; X32-NOSSE-NEXT:    movl $1431655765, %edi # imm = 0x55555555
+; X32-NOSSE-NEXT:    andl %edi, %ecx
+; X32-NOSSE-NEXT:    movl $1431655765, %edi # imm = 0x55555555
+; X32-NOSSE-NEXT:    subl %ecx, %ebx
+; X32-NOSSE-NEXT:    movl $858993459, %ecx # imm = 0x33333333
+; X32-NOSSE-NEXT:    movl %ebx, %ebp
+; X32-NOSSE-NEXT:    andl %ecx, %ebp
+; X32-NOSSE-NEXT:    shrl $2, %ebx
+; X32-NOSSE-NEXT:    andl %ecx, %ebx
+; X32-NOSSE-NEXT:    addl %ebp, %ebx
+; X32-NOSSE-NEXT:    movl %ebx, %ebp
+; X32-NOSSE-NEXT:    shrl $4, %ebp
+; X32-NOSSE-NEXT:    addl %ebx, %ebp
+; X32-NOSSE-NEXT:    movl %eax, %ebx
 ; X32-NOSSE-NEXT:    shrl %ebx
-; X32-NOSSE-NEXT:    andl $1431655765, %ebx # imm = 0x55555555
-; X32-NOSSE-NEXT:    subl %ebx, %edi
-; X32-NOSSE-NEXT:    movl %edi, %ebx
-; X32-NOSSE-NEXT:    andl $858993459, %ebx # imm = 0x33333333
-; X32-NOSSE-NEXT:    shrl $2, %edi
-; X32-NOSSE-NEXT:    andl $858993459, %edi # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %ebx, %edi
-; X32-NOSSE-NEXT:    movl %edi, %ebx
-; X32-NOSSE-NEXT:    shrl $4, %ebx
-; X32-NOSSE-NEXT:    addl %edi, %ebx
-; X32-NOSSE-NEXT:    andl $252645135, %ebx # imm = 0xF0F0F0F
-; X32-NOSSE-NEXT:    imull $16843009, %ebx, %edi # imm = 0x1010101
+; X32-NOSSE-NEXT:    andl %edi, %ebx
+; X32-NOSSE-NEXT:    subl %ebx, %eax
+; X32-NOSSE-NEXT:    movl %eax, %ebx
+; X32-NOSSE-NEXT:    andl %ecx, %ebx
+; X32-NOSSE-NEXT:    shrl $2, %eax
+; X32-NOSSE-NEXT:    andl %ecx, %eax
+; X32-NOSSE-NEXT:    addl %ebx, %eax
+; X32-NOSSE-NEXT:    movl %eax, %edi
+; X32-NOSSE-NEXT:    shrl $4, %edi
+; X32-NOSSE-NEXT:    addl %eax, %edi
+; X32-NOSSE-NEXT:    movl $252645135, %ebx # imm = 0xF0F0F0F
+; X32-NOSSE-NEXT:    andl %ebx, %ebp
+; X32-NOSSE-NEXT:    imull $16843009, %ebp, %eax # imm = 0x1010101
+; X32-NOSSE-NEXT:    shrl $24, %eax
+; X32-NOSSE-NEXT:    andl %ebx, %edi
+; X32-NOSSE-NEXT:    imull $16843009, %edi, %edi # imm = 0x1010101
 ; X32-NOSSE-NEXT:    shrl $24, %edi
-; X32-NOSSE-NEXT:    movl %esi, %ebx
-; X32-NOSSE-NEXT:    shrl %ebx
-; X32-NOSSE-NEXT:    andl $1431655765, %ebx # imm = 0x55555555
-; X32-NOSSE-NEXT:    subl %ebx, %esi
-; X32-NOSSE-NEXT:    movl %esi, %ebx
-; X32-NOSSE-NEXT:    andl $858993459, %ebx # imm = 0x33333333
+; X32-NOSSE-NEXT:    addl %eax, %edi
+; X32-NOSSE-NEXT:    movl %esi, %eax
+; X32-NOSSE-NEXT:    shrl %eax
+; X32-NOSSE-NEXT:    movl $1431655765, %ebp # imm = 0x55555555
+; X32-NOSSE-NEXT:    andl %ebp, %eax
+; X32-NOSSE-NEXT:    subl %eax, %esi
+; X32-NOSSE-NEXT:    movl %esi, %eax
+; X32-NOSSE-NEXT:    andl %ecx, %eax
 ; X32-NOSSE-NEXT:    shrl $2, %esi
-; X32-NOSSE-NEXT:    andl $858993459, %esi # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %ebx, %esi
-; X32-NOSSE-NEXT:    movl %esi, %ebx
-; X32-NOSSE-NEXT:    shrl $4, %ebx
-; X32-NOSSE-NEXT:    addl %esi, %ebx
-; X32-NOSSE-NEXT:    andl $252645135, %ebx # imm = 0xF0F0F0F
-; X32-NOSSE-NEXT:    imull $16843009, %ebx, %esi # imm = 0x1010101
-; X32-NOSSE-NEXT:    shrl $24, %esi
-; X32-NOSSE-NEXT:    addl %edi, %esi
-; X32-NOSSE-NEXT:    movl %edx, %edi
-; X32-NOSSE-NEXT:    shrl %edi
-; X32-NOSSE-NEXT:    andl $1431655765, %edi # imm = 0x55555555
-; X32-NOSSE-NEXT:    subl %edi, %edx
-; X32-NOSSE-NEXT:    movl %edx, %edi
-; X32-NOSSE-NEXT:    andl $858993459, %edi # imm = 0x33333333
+; X32-NOSSE-NEXT:    andl %ecx, %esi
+; X32-NOSSE-NEXT:    addl %eax, %esi
+; X32-NOSSE-NEXT:    movl %esi, %eax
+; X32-NOSSE-NEXT:    shrl $4, %eax
+; X32-NOSSE-NEXT:    addl %esi, %eax
+; X32-NOSSE-NEXT:    movl %edx, %esi
+; X32-NOSSE-NEXT:    shrl %esi
+; X32-NOSSE-NEXT:    andl %ebp, %esi
+; X32-NOSSE-NEXT:    subl %esi, %edx
+; X32-NOSSE-NEXT:    movl %edx, %esi
+; X32-NOSSE-NEXT:    andl %ecx, %esi
 ; X32-NOSSE-NEXT:    shrl $2, %edx
-; X32-NOSSE-NEXT:    andl $858993459, %edx # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %edi, %edx
-; X32-NOSSE-NEXT:    movl %edx, %edi
-; X32-NOSSE-NEXT:    shrl $4, %edi
-; X32-NOSSE-NEXT:    addl %edx, %edi
-; X32-NOSSE-NEXT:    andl $252645135, %edi # imm = 0xF0F0F0F
-; X32-NOSSE-NEXT:    imull $16843009, %edi, %edx # imm = 0x1010101
-; X32-NOSSE-NEXT:    shrl $24, %edx
-; X32-NOSSE-NEXT:    movl %ecx, %edi
-; X32-NOSSE-NEXT:    shrl %edi
-; X32-NOSSE-NEXT:    andl $1431655765, %edi # imm = 0x55555555
-; X32-NOSSE-NEXT:    subl %edi, %ecx
-; X32-NOSSE-NEXT:    movl %ecx, %edi
-; X32-NOSSE-NEXT:    andl $858993459, %edi # imm = 0x33333333
-; X32-NOSSE-NEXT:    shrl $2, %ecx
-; X32-NOSSE-NEXT:    andl $858993459, %ecx # imm = 0x33333333
-; X32-NOSSE-NEXT:    addl %edi, %ecx
-; X32-NOSSE-NEXT:    movl %ecx, %edi
-; X32-NOSSE-NEXT:    shrl $4, %edi
-; X32-NOSSE-NEXT:    addl %ecx, %edi
-; X32-NOSSE-NEXT:    andl $252645135, %edi # imm = 0xF0F0F0F
-; X32-NOSSE-NEXT:    imull $16843009, %edi, %ecx # imm = 0x1010101
-; X32-NOSSE-NEXT:    shrl $24, %ecx
+; X32-NOSSE-NEXT:    andl %ecx, %edx
+; X32-NOSSE-NEXT:    addl %esi, %edx
+; X32-NOSSE-NEXT:    movl %edx, %ecx
+; X32-NOSSE-NEXT:    shrl $4, %ecx
 ; X32-NOSSE-NEXT:    addl %edx, %ecx
-; X32-NOSSE-NEXT:    addl %esi, %ecx
+; X32-NOSSE-NEXT:    andl %ebx, %eax
+; X32-NOSSE-NEXT:    andl %ebx, %ecx
+; X32-NOSSE-NEXT:    imull $16843009, %eax, %eax # imm = 0x1010101
+; X32-NOSSE-NEXT:    shrl $24, %eax
+; X32-NOSSE-NEXT:    imull $16843009, %ecx, %ecx # imm = 0x1010101
+; X32-NOSSE-NEXT:    shrl $24, %ecx
+; X32-NOSSE-NEXT:    addl %eax, %ecx
+; X32-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-NOSSE-NEXT:    addl %edi, %ecx
 ; X32-NOSSE-NEXT:    xorl %edx, %edx
 ; X32-NOSSE-NEXT:    movl %edx, 12(%eax)
 ; X32-NOSSE-NEXT:    movl %edx, 8(%eax)
@@ -860,6 +877,7 @@ define i128 @cnt128_optsize(i128 %x) nounwind readnone optsize {
 ; X32-NOSSE-NEXT:    popl %esi
 ; X32-NOSSE-NEXT:    popl %edi
 ; X32-NOSSE-NEXT:    popl %ebx
+; X32-NOSSE-NEXT:    popl %ebp
 ; X32-NOSSE-NEXT:    retl $4
 ;
 ; X64-LABEL: cnt128_optsize:

diff --git a/test/CodeGen/X86/pr27202.ll b/test/CodeGen/X86/pr27202.ll
index e0483e9c0b63d71424c38fce154af93472fdc1fc..f8bf22bca8e9f64b46c5c67bc1809a776feda052 100644 (file)
--- a/test/CodeGen/X86/pr27202.ll
+++ b/test/CodeGen/X86/pr27202.ll
@@ -4,8 +4,8 @@
 define i1 @foo(i32 %i) optsize {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    andl $305419896, %edi # imm = 0x12345678
 ; CHECK-NEXT:    movl $305419896, %eax # imm = 0x12345678
+; CHECK-NEXT:    andl %eax, %edi
 ; CHECK-NEXT:    cmpl %eax, %edi
 ; CHECK-NEXT:    sete %al
 ; CHECK-NEXT:    retq
@@ -17,8 +17,8 @@ define i1 @foo(i32 %i) optsize {
 define zeroext i1 @g(i32 %x) optsize {
 ; CHECK-LABEL: g:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    orl $1, %edi
 ; CHECK-NEXT:    movl $1, %eax
+; CHECK-NEXT:    orl %eax, %edi
 ; CHECK-NEXT:    cmpl %eax, %edi
 ; CHECK-NEXT:    sete %al
 ; CHECK-NEXT:    retq