[X86] Correct the size check in foldMemoryOperandCustom.

The Size either needs to be 0 meaning we aren't folding
a stack reload. Or the stack slot needs to be at least
16 bytes. I've also added a paranoia check ensure the
RCSize is at leat 16 bytes as well. This avoids any
FR32/FR64 surprises, but I think we already filtered
those earlier.

All of our test case have Size as either 0 or 16 and
RCSize == 16. So the Size <= 16 check worked for those
cases.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365234 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp
index f1f020f78c4340061235cc80fe21f02cfdcee305..2e868a60ce46067d4ec6709ef5fdebe52fa00e83 100644 (file)
--- a/lib/Target/X86/X86InstrInfo.cpp
+++ b/lib/Target/X86/X86InstrInfo.cpp
@@ -4568,7 +4568,7 @@ MachineInstr *X86InstrInfo::foldMemoryOperandCustom(
       const TargetRegisterInfo &TRI = *MF.getSubtarget().getRegisterInfo();
       const TargetRegisterClass *RC = getRegClass(MI.getDesc(), OpNum, &RI, MF);
       unsigned RCSize = TRI.getRegSizeInBits(*RC) / 8;
-      if (Size <= RCSize && 4 <= Align) {
+      if ((Size == 0 || Size >= 16) && RCSize >= 16 && 4 <= Align) {
         int PtrOffset = SrcIdx * 4;
         unsigned NewImm = (DstIdx << 4) | ZMask;
         unsigned NewOpCode =
@@ -4592,7 +4592,7 @@ MachineInstr *X86InstrInfo::foldMemoryOperandCustom(
       const TargetRegisterInfo &TRI = *MF.getSubtarget().getRegisterInfo();
       const TargetRegisterClass *RC = getRegClass(MI.getDesc(), OpNum, &RI, MF);
       unsigned RCSize = TRI.getRegSizeInBits(*RC) / 8;
-      if (Size <= RCSize && 8 <= Align) {
+      if ((Size == 0 || Size >= 16) && RCSize >= 16 && 8 <= Align) {
         unsigned NewOpCode =
             (MI.getOpcode() == X86::VMOVHLPSZrr) ? X86::VMOVLPSZ128rm :
             (MI.getOpcode() == X86::VMOVHLPSrr)  ? X86::VMOVLPSrm     :