[llvm] r245632 - [LoopVectorize] Propagate 'nontemporal' attribute into vectorized instructions.

[Philip Reames via llvm-commits]

Michael,

Can you add a test case that shows two adjacent loads one with 
!nontemporal, one without?  I want to make sure we get that correct 
(i.e. not marking the result non-temporary if vectorized).  Doing this 
as a test case would make it obvious to future readers as well.

(Same for the SLP patch btw.)

Philip

On 08/20/2015 03:27 PM, Michael Zolotukhin via llvm-commits wrote:
> 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}
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits