diff options
| author | Guillaume Chatelet <gchatelet@google.com> | 2019-10-22 17:16:52 +0200 |
|---|---|---|
| committer | Guillaume Chatelet <gchatelet@google.com> | 2019-10-25 21:26:59 +0200 |
| commit | a4783ef58d3dd52b2079e885e9b4467c6b0b3a16 (patch) | |
| tree | 933af222146c40ba67e58f05093900f4b6882af8 /llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp | |
| parent | 3c7c3717932aba864c23edd2e48f1b28a6d532d5 (diff) | |
| download | bcm5719-llvm-a4783ef58d3dd52b2079e885e9b4467c6b0b3a16.tar.gz bcm5719-llvm-a4783ef58d3dd52b2079e885e9b4467c6b0b3a16.zip | |
[Alignment][NFC] getMemoryOpCost uses MaybeAlign
Summary:
This is patch is part of a series to introduce an Alignment type.
See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html
See this patch for the introduction of the type: https://reviews.llvm.org/D64790
Reviewers: courbet
Subscribers: nemanjai, hiraditya, kbarton, MaskRay, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69307
Diffstat (limited to 'llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp index 86c8684d14d..ed1d6e5ca36 100644 --- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp +++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp @@ -735,11 +735,13 @@ int ARMTTIImpl::getArithmeticInstrCost( return BaseCost; } -int ARMTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment, - unsigned AddressSpace, const Instruction *I) { +int ARMTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src, + MaybeAlign Alignment, unsigned AddressSpace, + const Instruction *I) { std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src); - if (ST->hasNEON() && Src->isVectorTy() && Alignment != 16 && + if (ST->hasNEON() && Src->isVectorTy() && + (Alignment && *Alignment != Align(16)) && Src->getVectorElementType()->isDoubleTy()) { // Unaligned loads/stores are extremely inefficient. // We need 4 uops for vst.1/vld.1 vs 1uop for vldr/vstr. |
