5 files changed, 26 insertions, 45 deletions
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index c312e53b354..5d791a76610 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -582,17 +582,12 @@ bool PPCTTIImpl::enableAggressiveInterleaving(bool LoopHasReductions) {
   return LoopHasReductions;
 }
 
-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;
+PPCTTIImpl::TTI::MemCmpExpansionOptions
+PPCTTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
+  TTI::MemCmpExpansionOptions Options;
+  Options.LoadSizes = {8, 4, 2, 1};
+  Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
+  return Options;
 }
 
 bool PPCTTIImpl::enableInterleavedAccessVectorization() {
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 04063404e2a..047f2e34e85 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -66,8 +66,8 @@ public:
   /// @{
   bool useColdCCForColdCall(Function &F);
   bool enableAggressiveInterleaving(bool LoopHasReductions);
-  const TTI::MemCmpExpansionOptions *enableMemCmpExpansion(
-      bool IsZeroCmp) const;
+  TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
+                                                    bool IsZeroCmp) const;
   bool enableInterleavedAccessVectorization();
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector) const;
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index 6f03ba7adc9..5ce077bdce7 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -879,11 +879,6 @@ namespace llvm {
     /// Vector-sized comparisons are fast using PCMPEQ + PMOVMSK or PTEST.
     MVT hasFastEqualityCompare(unsigned NumBits) const override;
 
-    /// Allow multiple load pairs per block for smaller and faster code.
-    unsigned getMemcmpEqZeroLoadsPerBlock() const override {
-      return 2;
-    }
-
     /// Return the value type to use for ISD::SETCC.
     EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
                            EVT VT) const override;
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 08e46ed2ce3..843d6cf839d 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -3291,38 +3291,29 @@ bool X86TTIImpl::areFunctionArgsABICompatible(
          TM.getSubtarget<X86Subtarget>(*Callee).useAVX512Regs();
 }
 
-const X86TTIImpl::TTI::MemCmpExpansionOptions *
-X86TTIImpl::enableMemCmpExpansion(bool IsZeroCmp) const {
-  // Only enable vector loads for equality comparison.
-  // Right now the vector version is not as fast, see #33329.
-  static const auto ThreeWayOptions = [this]() {
-    TTI::MemCmpExpansionOptions Options;
-    if (ST->is64Bit()) {
-      Options.LoadSizes.push_back(8);
-    }
-    Options.LoadSizes.push_back(4);
-    Options.LoadSizes.push_back(2);
-    Options.LoadSizes.push_back(1);
-    return Options;
-  }();
-  static const auto EqZeroOptions = [this]() {
-    TTI::MemCmpExpansionOptions Options;
+X86TTIImpl::TTI::MemCmpExpansionOptions
+X86TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
+  TTI::MemCmpExpansionOptions Options;
+  Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
+  Options.NumLoadsPerBlock = 2;
+  if (IsZeroCmp) {
+    // Only enable vector loads for equality comparison. Right now the vector
+    // version is not as fast for three way compare (see #33329).
     // TODO: enable AVX512 when the DAG is ready.
     // if (ST->hasAVX512()) Options.LoadSizes.push_back(64);
     if (ST->hasAVX2()) Options.LoadSizes.push_back(32);
     if (ST->hasSSE2()) Options.LoadSizes.push_back(16);
-    if (ST->is64Bit()) {
-      Options.LoadSizes.push_back(8);
-    }
-    Options.LoadSizes.push_back(4);
-    Options.LoadSizes.push_back(2);
-    Options.LoadSizes.push_back(1);
     // All GPR and vector loads can be unaligned. SIMD compare requires integer
     // vectors (SSE2/AVX2).
     Options.AllowOverlappingLoads = true;
-    return Options;
-  }();
-  return IsZeroCmp ? &EqZeroOptions : &ThreeWayOptions;
+  }
+  if (ST->is64Bit()) {
+    Options.LoadSizes.push_back(8);
+  }
+  Options.LoadSizes.push_back(4);
+  Options.LoadSizes.push_back(2);
+  Options.LoadSizes.push_back(1);
+  return Options;
 }
 
 bool X86TTIImpl::enableInterleavedAccessVectorization() {
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.h b/llvm/lib/Target/X86/X86TargetTransformInfo.h
index f43155e3838..25d9c33eb16 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.h
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.h
@@ -199,8 +199,8 @@ public:
   bool areFunctionArgsABICompatible(const Function *Caller,
                                     const Function *Callee,
                                     SmallPtrSetImpl<Argument *> &Args) const;
-  const TTI::MemCmpExpansionOptions *enableMemCmpExpansion(
-      bool IsZeroCmp) const;
+  TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
+                                                    bool IsZeroCmp) const;
   bool enableInterleavedAccessVectorization();
 private:
   int getGSScalarCost(unsigned Opcode, Type *DataTy, bool VariableMask,