diff options
| author | Michael Zolotukhin <mzolotukhin@apple.com> | 2015-08-20 22:27:38 +0000 |
|---|---|---|
| committer | Michael Zolotukhin <mzolotukhin@apple.com> | 2015-08-20 22:27:38 +0000 |
| commit | 2a3d99fedfa9ed911ed35753cfe490b885340877 (patch) | |
| tree | 113dc21a843cf8fa027011d531ac3fd961a3b52d /llvm | |
| parent | 075c6ee843d3f68dc1f91b5e14a1eda5ad2ccad1 (diff) | |
| download | bcm5719-llvm-2a3d99fedfa9ed911ed35753cfe490b885340877.tar.gz bcm5719-llvm-2a3d99fedfa9ed911ed35753cfe490b885340877.zip | |
[LoopVectorize] Propagate 'nontemporal' attribute into vectorized instructions.
llvm-svn: 245632
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 3 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/nontemporal.ll | 47 |
2 files changed, 49 insertions, 1 deletions
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index e131cc02e37..9166d9e233e 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -552,7 +552,8 @@ static void propagateMetadata(Instruction *To, const Instruction *From) { if (Kind != LLVMContext::MD_tbaa && Kind != LLVMContext::MD_alias_scope && Kind != LLVMContext::MD_noalias && - Kind != LLVMContext::MD_fpmath) + Kind != LLVMContext::MD_fpmath && + Kind != LLVMContext::MD_nontemporal) continue; To->setMetadata(Kind, M.second); diff --git a/llvm/test/Transforms/LoopVectorize/nontemporal.ll b/llvm/test/Transforms/LoopVectorize/nontemporal.ll new file mode 100644 index 00000000000..106b1903122 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/nontemporal.ll @@ -0,0 +1,47 @@ +; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -instcombine -S | FileCheck %s + +target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128" +target triple = "arm64-apple-ios5.0.0" + +; CHECK-LABEL: @foo( +define void @foo(float* noalias %a, float* noalias %b, float* noalias %c, i32 %N) { +entry: + %cmp.4 = icmp sgt i32 %N, 0 + br i1 %cmp.4, label %for.body.preheader, label %for.end + +for.body.preheader: ; preds = %entry + br label %for.body + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + +; Check that we don't lose !nontemporal hint when vectorizing loads. +; CHECK: %wide.load{{[0-9]*}} = load <4 x float>, <4 x float>* %{{[0-9]+}}, align 4, !nontemporal !0 + %arrayidx = getelementptr inbounds float, float* %b, i64 %indvars.iv + %0 = load float, float* %arrayidx, align 4, !nontemporal !0 + +; Check that we don't introduce !nontemporal hint when the original scalar loads didn't have it. +; CHECK: %wide.load{{[0-9]+}} = load <4 x float>, <4 x float>* %{{[0-9]+}}, align 4{{$}} + %arrayidx2 = getelementptr inbounds float, float* %c, i64 %indvars.iv + %1 = load float, float* %arrayidx2, align 4 + %add = fadd float %0, %1 + +; Check that we don't lose !nontemporal hint when vectorizing stores. +; CHECK: store <4 x float> %{{[0-9]+}}, <4 x float>* %{{[0-9]+}}, align 4, !nontemporal !0 + %arrayidx4 = getelementptr inbounds float, float* %a, i64 %indvars.iv + store float %add, float* %arrayidx4, align 4, !nontemporal !0 + + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %N + br i1 %exitcond, label %for.end.loopexit, label %for.body + +for.end.loopexit: ; preds = %for.body + br label %for.end + +for.end: ; preds = %for.end.loopexit, %entry +; CHECK: ret void + ret void +} + +!0 = !{i32 1} |

