[CGP] avoid zext/trunc of a memcmp expansion compare

This could be viewed as another shortcoming of the DAGCombiner:
when both operands of a compare are zexted from the same source
type, we should be able to compare the original types.

The effect on PowerPC perf is likely unnoticeable, but there's a
visible regression for x86 if we feed the suboptimal IR for memcmp
expansion to the DAG:

_cmp_eq4_zexted_to_i64:
  movl  (%rdi), %ecx
  movl  (%rsi), %edx
  xorl  %eax, %eax
  cmpq  %rdx, %rcx
  sete  %al

_cmp_eq4_better:
  movl  (%rdi), %ecx
  xorl  %eax, %eax
  cmpl  (%rsi), %ecx
  sete  %al

llvm-svn: 304923

1 files changed, 4 insertions, 4 deletions

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index 84719f20485..e797f1af70c 100644
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -1841,11 +1841,11 @@ Value *MemCmpExpansion::getCompareLoadPairs(unsigned Index, unsigned Size,
     // Load LoadSizeType from the base address.
     Value *LoadSrc1 = Builder.CreateLoad(LoadSizeType, Source1);
     Value *LoadSrc2 = Builder.CreateLoad(LoadSizeType, Source2);
-    if (LoadSizeType != MaxLoadType) {
-      LoadSrc1 = Builder.CreateZExtOrTrunc(LoadSrc1, MaxLoadType);
-      LoadSrc2 = Builder.CreateZExtOrTrunc(LoadSrc2, MaxLoadType);
-    }
     if (NumLoads != 1) {
+      if (LoadSizeType != MaxLoadType) {
+        LoadSrc1 = Builder.CreateZExtOrTrunc(LoadSrc1, MaxLoadType);
+        LoadSrc2 = Builder.CreateZExtOrTrunc(LoadSrc2, MaxLoadType);
+      }
       // If we have multiple loads per block, we need to generate a composite
       // comparison using xor+or.
       Diff = Builder.CreateXor(LoadSrc1, LoadSrc2);