diff options
author | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2017-04-12 12:41:37 +0000 |
---|---|---|
committer | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2017-04-12 12:41:37 +0000 |
commit | da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04 (patch) | |
tree | 5ead03687c900acdb6bf62c7c34fa34f62b03480 /llvm/lib | |
parent | 12194e9bec6f5c4dc887659983764e6cfb708205 (diff) | |
download | bcm5719-llvm-da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04.tar.gz bcm5719-llvm-da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04.zip |
[LoopVectorizer, TTI] New method supportsEfficientVectorElementLoadStore()
Since SystemZ supports vector element load/store instructions, there is no
need for extracts/inserts if a vector load/store gets scalarized.
This patch lets Target specify that it supports such instructions by means of
a new TTI hook that defaults to false.
The use for this is in the LoopVectorizer getScalarizationOverhead() method,
which will with this patch produce a smaller sum for a vector load/store on
SystemZ.
New test: test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll
Review: Adam Nemet
https://reviews.llvm.org/D30680
llvm-svn: 300056
Diffstat (limited to 'llvm/lib')
-rw-r--r-- | llvm/lib/Analysis/TargetTransformInfo.cpp | 4 | ||||
-rw-r--r-- | llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h | 1 | ||||
-rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 8 |
3 files changed, 11 insertions, 2 deletions
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp index c8b8740bd85..d73b1a12803 100644 --- a/llvm/lib/Analysis/TargetTransformInfo.cpp +++ b/llvm/lib/Analysis/TargetTransformInfo.cpp @@ -197,6 +197,10 @@ getOperandsScalarizationOverhead(ArrayRef<const Value *> Args, return TTIImpl->getOperandsScalarizationOverhead(Args, VF); } +bool TargetTransformInfo::supportsEfficientVectorElementLoadStore() const { + return TTIImpl->supportsEfficientVectorElementLoadStore(); +} + bool TargetTransformInfo::enableAggressiveInterleaving(bool LoopHasReductions) const { return TTIImpl->enableAggressiveInterleaving(LoopHasReductions); } diff --git a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h index d2639cb271d..3766ed45b8c 100644 --- a/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h +++ b/llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h @@ -55,6 +55,7 @@ public: unsigned getNumberOfRegisters(bool Vector); unsigned getRegisterBitWidth(bool Vector); + bool supportsEfficientVectorElementLoadStore() { return true; } bool enableInterleavedAccessVectorization() { return true; } int getArithmeticInstrCost( diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index f891cd9d62c..26bcbcb5f18 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -3663,13 +3663,17 @@ static unsigned getScalarizationOverhead(Instruction *I, unsigned VF, unsigned Cost = 0; Type *RetTy = ToVectorTy(I->getType(), VF); - if (!RetTy->isVoidTy()) + if (!RetTy->isVoidTy() && + (!isa<LoadInst>(I) || + !TTI.supportsEfficientVectorElementLoadStore())) Cost += TTI.getScalarizationOverhead(RetTy, true, false); if (CallInst *CI = dyn_cast<CallInst>(I)) { SmallVector<const Value *, 4> Operands(CI->arg_operands()); Cost += TTI.getOperandsScalarizationOverhead(Operands, VF); - } else { + } + else if (!isa<StoreInst>(I) || + !TTI.supportsEfficientVectorElementLoadStore()) { SmallVector<const Value *, 4> Operands(I->operand_values()); Cost += TTI.getOperandsScalarizationOverhead(Operands, VF); } |