diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86TargetTransformInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/X86/X86TargetTransformInfo.cpp | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index 62f95277d016..3d8d0a236a3c 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -213,7 +213,7 @@ X86TTIImpl::getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const { case TargetTransformInfo::RGK_Scalar: return TypeSize::getFixed(ST->is64Bit() ? 64 : 32); case TargetTransformInfo::RGK_FixedWidthVector: - if (ST->hasAVX512() && ST->hasEVEX512() && PreferVectorWidth >= 512) + if (ST->hasAVX512() && PreferVectorWidth >= 512) return TypeSize::getFixed(512); if (ST->hasAVX() && PreferVectorWidth >= 256) return TypeSize::getFixed(256); @@ -1206,6 +1206,8 @@ InstructionCost X86TTIImpl::getArithmeticInstrCost( { ISD::MUL, MVT::v4i32, { 2, 5, 1, 3 } }, // pmulld { ISD::MUL, MVT::v4i64, { 12, 15, 19, 20 } }, + { X86ISD::PMULUDQ, MVT::v4i64, { 3, 5, 5, 6 } }, // pmuludq + split + { ISD::AND, MVT::v32i8, { 1, 1, 1, 2 } }, // vandps { ISD::AND, MVT::v16i16, { 1, 1, 1, 2 } }, // vandps { ISD::AND, MVT::v8i32, { 1, 1, 1, 2 } }, // vandps @@ -6591,7 +6593,7 @@ X86TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const { // Only enable vector loads for equality comparison. Right now the vector // version is not as fast for three way compare (see #33329). const unsigned PreferredWidth = ST->getPreferVectorWidth(); - if (PreferredWidth >= 512 && ST->hasAVX512() && ST->hasEVEX512()) + if (PreferredWidth >= 512 && ST->hasAVX512()) Options.LoadSizes.push_back(64); if (PreferredWidth >= 256 && ST->hasAVX()) Options.LoadSizes.push_back(32); if (PreferredWidth >= 128 && ST->hasSSE2()) Options.LoadSizes.push_back(16); |