[CodeGen][ExpandMemcmp] Allow memcmp to expand to vector loads (2).

 - Targets that want to support memcmp expansions now return the list of
   supported load sizes.
 - Expansion codegen does not assume that all power-of-two load sizes
   smaller than the max load size are valid. For examples, this is not the
   case for x86(32bit)+sse2.

Fixes PR34887.

llvm-svn: 316905

2 files changed, 13 insertions, 4 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index 52c5b688d35..43b9892fc5a 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -226,9 +226,17 @@ bool PPCTTIImpl::enableAggressiveInterleaving(bool LoopHasReductions) {
   return LoopHasReductions;
 }
 
-bool PPCTTIImpl::enableMemCmpExpansion(unsigned &MaxLoadSize) {
-  MaxLoadSize = 8;
-  return true;
+const PPCTTIImpl::TTI::MemCmpExpansionOptions *
+PPCTTIImpl::enableMemCmpExpansion(bool IsZeroCmp) const {
+  static const auto Options = []() {
+    TTI::MemCmpExpansionOptions Options;
+    Options.LoadSizes.push_back(8);
+    Options.LoadSizes.push_back(4);
+    Options.LoadSizes.push_back(2);
+    Options.LoadSizes.push_back(1);
+    return Options;
+  }();
+  return &Options;
 }
 
 bool PPCTTIImpl::enableInterleavedAccessVectorization() {
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 60dea0b0226..acf5066bc6d 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -63,7 +63,8 @@ public:
   /// @{
 
   bool enableAggressiveInterleaving(bool LoopHasReductions);
-  bool enableMemCmpExpansion(unsigned &MaxLoadSize);
+  const TTI::MemCmpExpansionOptions *enableMemCmpExpansion(
+      bool IsZeroCmp) const;
   bool enableInterleavedAccessVectorization();
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector) const;