Fix PR19657 (scalar loads not combined into vector load)

If we have common uses on separate paths in the tree; process the one with greater common depth first.
This makes sure that we do not assume we need to extract a load when it is actually going to be part of a vectorized tree.

Review: http://reviews.llvm.org/D3800

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210310 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index ce0a009e1cb147cda9bd8072ebeaa9c0bb8dd614..d862167095945860174e134590077fa603d9cefd 100644 (file)
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -914,8 +914,20 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
       if (isa<BinaryOperator>(VL0) && VL0->isCommutative()) {
         ValueList Left, Right;
         reorderInputsAccordingToOpcode(VL, Left, Right);
-        buildTree_rec(Left, Depth + 1);
-        buildTree_rec(Right, Depth + 1);
+        BasicBlock *LeftBB = getSameBlock(Left);
+        BasicBlock *RightBB = getSameBlock(Right);
+        // If we have common uses on separate paths in the tree make sure we
+        // process the one with greater common depth first.
+        // We can use block numbering to determine the subtree traversal as
+        // earler user has to come in between the common use and the later user.
+        if (LeftBB && RightBB && LeftBB == RightBB &&
+            getLastIndex(Right) > getLastIndex(Left)) {
+          buildTree_rec(Right, Depth + 1);
+          buildTree_rec(Left, Depth + 1);
+        } else {
+          buildTree_rec(Left, Depth + 1);
+          buildTree_rec(Right, Depth + 1);
+        }
         return;
       }
 

diff --git a/test/Transforms/SLPVectorizer/X86/pr19657.ll b/test/Transforms/SLPVectorizer/X86/pr19657.ll
new file mode 100644 (file)
index 0000000..9352308
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/pr19657.ll
@@ -0,0 +1,73 @@
+; RUN: opt < %s -O1 -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7-avx | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+;CHECK: load <2 x double>*
+;CHECK: fadd <2 x double>
+;CHECK: store <2 x double>
+
+; Function Attrs: nounwind uwtable
+define void @foo(double* %x) #0 {
+  %1 = alloca double*, align 8
+  store double* %x, double** %1, align 8
+  %2 = load double** %1, align 8
+  %3 = getelementptr inbounds double* %2, i64 0
+  %4 = load double* %3, align 8
+  %5 = load double** %1, align 8
+  %6 = getelementptr inbounds double* %5, i64 0
+  %7 = load double* %6, align 8
+  %8 = fadd double %4, %7
+  %9 = load double** %1, align 8
+  %10 = getelementptr inbounds double* %9, i64 0
+  %11 = load double* %10, align 8
+  %12 = fadd double %8, %11
+  %13 = load double** %1, align 8
+  %14 = getelementptr inbounds double* %13, i64 0
+  store double %12, double* %14, align 8
+  %15 = load double** %1, align 8
+  %16 = getelementptr inbounds double* %15, i64 1
+  %17 = load double* %16, align 8
+  %18 = load double** %1, align 8
+  %19 = getelementptr inbounds double* %18, i64 1
+  %20 = load double* %19, align 8
+  %21 = fadd double %17, %20
+  %22 = load double** %1, align 8
+  %23 = getelementptr inbounds double* %22, i64 1
+  %24 = load double* %23, align 8
+  %25 = fadd double %21, %24
+  %26 = load double** %1, align 8
+  %27 = getelementptr inbounds double* %26, i64 1
+  store double %25, double* %27, align 8
+  %28 = load double** %1, align 8
+  %29 = getelementptr inbounds double* %28, i64 2
+  %30 = load double* %29, align 8
+  %31 = load double** %1, align 8
+  %32 = getelementptr inbounds double* %31, i64 2
+  %33 = load double* %32, align 8
+  %34 = fadd double %30, %33
+  %35 = load double** %1, align 8
+  %36 = getelementptr inbounds double* %35, i64 2
+  %37 = load double* %36, align 8
+  %38 = fadd double %34, %37
+  %39 = load double** %1, align 8
+  %40 = getelementptr inbounds double* %39, i64 2
+  store double %38, double* %40, align 8
+  %41 = load double** %1, align 8
+  %42 = getelementptr inbounds double* %41, i64 3
+  %43 = load double* %42, align 8
+  %44 = load double** %1, align 8
+  %45 = getelementptr inbounds double* %44, i64 3
+  %46 = load double* %45, align 8
+  %47 = fadd double %43, %46
+  %48 = load double** %1, align 8
+  %49 = getelementptr inbounds double* %48, i64 3
+  %50 = load double* %49, align 8
+  %51 = fadd double %47, %50
+  %52 = load double** %1, align 8
+  %53 = getelementptr inbounds double* %52, i64 3
+  store double %51, double* %53, align 8
+  ret void
+}
+
+attributes #0 = { nounwind }