diff options
Diffstat (limited to 'llvm/lib/Target/X86')
| -rw-r--r-- | llvm/lib/Target/X86/X86TargetTransformInfo.cpp | 23 | ||||
| -rw-r--r-- | llvm/lib/Target/X86/X86TargetTransformInfo.h | 9 |
2 files changed, 23 insertions, 9 deletions
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp index d3a75123935..82e4dfe25b7 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -2723,7 +2723,12 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, unsigned Alignment, - unsigned AddressSpace) { + unsigned AddressSpace, + bool IsMasked) { + + if (IsMasked) + return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices, + Alignment, AddressSpace, IsMasked); // We currently Support only fully-interleaved groups, with no gaps. // TODO: Support also strided loads (interleaved-groups with gaps). @@ -2832,7 +2837,12 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX512(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, unsigned Alignment, - unsigned AddressSpace) { + unsigned AddressSpace, + bool IsMasked) { + + if (IsMasked) + return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices, + Alignment, AddressSpace, IsMasked); // VecTy for interleave memop is <VF*Factor x Elt>. // So, for VF=4, Interleave Factor = 3, Element type = i32 we have @@ -2950,7 +2960,8 @@ int X86TTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, unsigned Alignment, - unsigned AddressSpace) { + unsigned AddressSpace, + bool IsMasked) { auto isSupportedOnAVX512 = [](Type *VecTy, bool HasBW) { Type *EltTy = VecTy->getVectorElementType(); if (EltTy->isFloatTy() || EltTy->isDoubleTy() || EltTy->isIntegerTy(64) || @@ -2962,11 +2973,11 @@ int X86TTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, }; if (ST->hasAVX512() && isSupportedOnAVX512(VecTy, ST->hasBWI())) return getInterleavedMemoryOpCostAVX512(Opcode, VecTy, Factor, Indices, - Alignment, AddressSpace); + Alignment, AddressSpace, IsMasked); if (ST->hasAVX2()) return getInterleavedMemoryOpCostAVX2(Opcode, VecTy, Factor, Indices, - Alignment, AddressSpace); + Alignment, AddressSpace, IsMasked); return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices, - Alignment, AddressSpace); + Alignment, AddressSpace, IsMasked); } diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.h b/llvm/lib/Target/X86/X86TargetTransformInfo.h index 3df89903882..2bd778a4211 100644 --- a/llvm/lib/Target/X86/X86TargetTransformInfo.h +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.h @@ -101,13 +101,16 @@ public: int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, - unsigned Alignment, unsigned AddressSpace); + unsigned Alignment, unsigned AddressSpace, + bool IsMasked = false); int getInterleavedMemoryOpCostAVX512(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, - unsigned Alignment, unsigned AddressSpace); + unsigned Alignment, unsigned AddressSpace, + bool IsMasked = false); int getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices, - unsigned Alignment, unsigned AddressSpace); + unsigned Alignment, unsigned AddressSpace, + bool IsMasked = false); int getIntImmCost(int64_t); |
