[llvm] r245632 - [LoopVectorize] Propagate 'nontemporal' attribute into vectorized instructions.
Michael Zolotukhin via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 20 15:27:38 PDT 2015
Author: mzolotukhin
Date: Thu Aug 20 17:27:38 2015
New Revision: 245632
URL: http://llvm.org/viewvc/llvm-project?rev=245632&view=rev
Log:
[LoopVectorize] Propagate 'nontemporal' attribute into vectorized instructions.
Added:
llvm/trunk/test/Transforms/LoopVectorize/nontemporal.ll
Modified:
llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
Modified: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp?rev=245632&r1=245631&r2=245632&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp Thu Aug 20 17:27:38 2015
@@ -552,7 +552,8 @@ static void propagateMetadata(Instructio
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);
Added: llvm/trunk/test/Transforms/LoopVectorize/nontemporal.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/nontemporal.ll?rev=245632&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/nontemporal.ll (added)
+++ llvm/trunk/test/Transforms/LoopVectorize/nontemporal.ll Thu Aug 20 17:27:38 2015
@@ -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}
More information about the llvm-commits
mailing list