From 4d8ffa082c19eeb6c07ec3f82b06604d66c18949 Mon Sep 17 00:00:00 2001
From: Michael Zolotukhin <mzolotukhin@apple.com>
Date: Fri, 19 Jun 2015 17:40:15 +0000
Subject: [PATCH] [SLP] Vectorize for all-constant entries.

Differential Revision: http://reviews.llvm.org/D10531

llvm-svn: 240144
---
 llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp  |  6 ++++--
 .../Transforms/SLPVectorizer/X86/tiny-tree.ll    | 16 ++++++++++++++++
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 149936b11b30..370e2956ac4f 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1637,8 +1637,10 @@ bool BoUpSLP::isFullyVectorizableTinyTree() {
   if (VectorizableTree.size() != 2)
     return false;
 
-  // Handle splat stores.
-  if (!VectorizableTree[0].NeedToGather && isSplat(VectorizableTree[1].Scalars))
+  // Handle splat and all-constants stores.
+  if (!VectorizableTree[0].NeedToGather &&
+      (allConstant(VectorizableTree[1].Scalars) ||
+       isSplat(VectorizableTree[1].Scalars)))
     return true;
 
   // Gathering cost would be too much for tiny trees.
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
index 6c93222ef93a..26af8165bc37 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
@@ -153,3 +153,19 @@ define void @store_splat(float*, float) {
   store float %1, float* %6, align 4
   ret void
 }
+
+
+; CHECK-LABEL: store_const
+; CHECK: store <4 x i32>
+define void @store_const(i32* %a) {
+entry:
+  %ptr0 = getelementptr inbounds i32, i32* %a, i64 0
+  store i32 10, i32* %ptr0, align 4
+  %ptr1 = getelementptr inbounds i32, i32* %a, i64 1
+  store i32 30, i32* %ptr1, align 4
+  %ptr2 = getelementptr inbounds i32, i32* %a, i64 2
+  store i32 20, i32* %ptr2, align 4
+  %ptr3 = getelementptr inbounds i32, i32* %a, i64 3
+  store i32 40, i32* %ptr3, align 4
+  ret void
+}