[LoopVectorize] Propagate 'nontemporal' attribute into vectorized instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245632 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index e131cc02e3781929e89c394409dbbcffccfc0690..9166d9e233e04778bf3f3853d30982a2e2d63c0e 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/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 &&
     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);
       continue;
 
     To->setMetadata(Kind, M.second);

diff --git a/test/Transforms/LoopVectorize/nontemporal.ll b/test/Transforms/LoopVectorize/nontemporal.ll
new file mode 100644 (file)
index 0000000..106b190
--- /dev/null
+++ b/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}