diff options
Diffstat (limited to 'llvm')
-rw-r--r-- | llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp | 10 | ||||
-rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll | 15 |
2 files changed, 22 insertions, 3 deletions
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index 360652f3dce..8e3ec815e82 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -1101,11 +1101,15 @@ bool BoUpSLP::isFullyVectorizableTinyTree() { if (VectorizableTree.size() != 2) return false; + // Handle splat stores. + if (!VectorizableTree[0].NeedToGather && isSplat(VectorizableTree[1].Scalars)) + return true; + // Gathering cost would be too much for tiny trees. - if (VectorizableTree[0].NeedToGather || VectorizableTree[1].NeedToGather) - return false; + if (VectorizableTree[0].NeedToGather || VectorizableTree[1].NeedToGather) + return false; - return true; + return true; } int BoUpSLP::getTreeCost() { diff --git a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll index 2747a1f4899..10c3130b424 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll @@ -138,3 +138,18 @@ for.body: ; preds = %entry, %for.body for.end: ; preds = %for.body, %entry ret void } + + +; CHECK-LABEL: store_splat +; CHECK: store <4 x float> +define void @store_splat(float*, float) { + %3 = getelementptr inbounds float* %0, i64 0 + store float %1, float* %3, align 4 + %4 = getelementptr inbounds float* %0, i64 1 + store float %1, float* %4, align 4 + %5 = getelementptr inbounds float* %0, i64 2 + store float %1, float* %5, align 4 + %6 = getelementptr inbounds float* %0, i64 3 + store float %1, float* %6, align 4 + ret void +} |