5 files changed, 563 insertions, 2 deletions
diff --git a/test/Transforms/SLPVectorizer/X86/addsub.ll b/test/Transforms/SLPVectorizer/X86/addsub.ll
new file mode 100644
index 0000000..8303bc8
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/addsub.ll
@@ -0,0 +1,181 @@
+; RUN: opt < %s -basicaa -slp-vectorizer -S | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@b = common global [4 x i32] zeroinitializer, align 16
+@c = common global [4 x i32] zeroinitializer, align 16
+@d = common global [4 x i32] zeroinitializer, align 16
+@e = common global [4 x i32] zeroinitializer, align 16
+@a = common global [4 x i32] zeroinitializer, align 16
+@fb = common global [4 x float] zeroinitializer, align 16
+@fc = common global [4 x float] zeroinitializer, align 16
+@fa = common global [4 x float] zeroinitializer, align 16
+
+; CHECK-LABEL: @addsub
+; CHECK: %5 = add <4 x i32> %3, %4
+; CHECK: %6 = add <4 x i32> %2, %5
+; CHECK: %7 = sub <4 x i32> %2, %5
+; CHECK: %8 = shufflevector <4 x i32> %6, <4 x i32> %7, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+
+; Function Attrs: nounwind uwtable
+define void @addsub() #0 {
+entry:
+  %0 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 0), align 4
+  %1 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 0), align 4
+  %add = add nsw i32 %0, %1
+  %2 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 0), align 4
+  %3 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 0), align 4
+  %add1 = add nsw i32 %2, %3
+  %add2 = add nsw i32 %add, %add1
+  store i32 %add2, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 0), align 4
+  %4 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 1), align 4
+  %5 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 1), align 4
+  %add3 = add nsw i32 %4, %5
+  %6 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 1), align 4
+  %7 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 1), align 4
+  %add4 = add nsw i32 %6, %7
+  %sub = sub nsw i32 %add3, %add4
+  store i32 %sub, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 1), align 4
+  %8 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 2), align 4
+  %9 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 2), align 4
+  %add5 = add nsw i32 %8, %9
+  %10 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 2), align 4
+  %11 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 2), align 4
+  %add6 = add nsw i32 %10, %11
+  %add7 = add nsw i32 %add5, %add6
+  store i32 %add7, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 2), align 4
+  %12 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 3), align 4
+  %13 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 3), align 4
+  %add8 = add nsw i32 %12, %13
+  %14 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 3), align 4
+  %15 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 3), align 4
+  %add9 = add nsw i32 %14, %15
+  %sub10 = sub nsw i32 %add8, %add9
+  store i32 %sub10, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 3), align 4
+  ret void
+}
+
+; CHECK-LABEL: @subadd
+; CHECK:  %5 = add <4 x i32> %3, %4
+; CHECK:  %6 = sub <4 x i32> %2, %5
+; CHECK:  %7 = add <4 x i32> %2, %5
+; CHECK:  %8 = shufflevector <4 x i32> %6, <4 x i32> %7, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+
+; Function Attrs: nounwind uwtable
+define void @subadd() #0 {
+entry:
+  %0 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 0), align 4
+  %1 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 0), align 4
+  %add = add nsw i32 %0, %1
+  %2 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 0), align 4
+  %3 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 0), align 4
+  %add1 = add nsw i32 %2, %3
+  %sub = sub nsw i32 %add, %add1
+  store i32 %sub, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 0), align 4
+  %4 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 1), align 4
+  %5 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 1), align 4
+  %add2 = add nsw i32 %4, %5
+  %6 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 1), align 4
+  %7 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 1), align 4
+  %add3 = add nsw i32 %6, %7
+  %add4 = add nsw i32 %add2, %add3
+  store i32 %add4, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 1), align 4
+  %8 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 2), align 4
+  %9 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 2), align 4
+  %add5 = add nsw i32 %8, %9
+  %10 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 2), align 4
+  %11 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 2), align 4
+  %add6 = add nsw i32 %10, %11
+  %sub7 = sub nsw i32 %add5, %add6
+  store i32 %sub7, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 2), align 4
+  %12 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 3), align 4
+  %13 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 3), align 4
+  %add8 = add nsw i32 %12, %13
+  %14 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 3), align 4
+  %15 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 3), align 4
+  %add9 = add nsw i32 %14, %15
+  %add10 = add nsw i32 %add8, %add9
+  store i32 %add10, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 3), align 4
+  ret void
+}
+
+; CHECK-LABEL: @faddfsub
+; CHECK: %2 = fadd <4 x float> %0, %1
+; CHECK: %3 = fsub <4 x float> %0, %1
+; CHECK: %4 = shufflevector <4 x float> %2, <4 x float> %3, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; Function Attrs: nounwind uwtable
+define void @faddfsub() #0 {
+entry:
+  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
+  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
+  %add = fadd float %0, %1
+  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
+  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
+  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
+  %sub = fsub float %2, %3
+  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
+  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
+  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
+  %add1 = fadd float %4, %5
+  store float %add1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
+  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
+  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
+  %sub2 = fsub float %6, %7
+  store float %sub2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
+  ret void
+}
+
+; CHECK-LABEL: @fsubfadd
+; CHECK: %2 = fsub <4 x float> %0, %1
+; CHECK: %3 = fadd <4 x float> %0, %1
+; CHECK: %4 = shufflevector <4 x float> %2, <4 x float> %3, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; Function Attrs: nounwind uwtable
+define void @fsubfadd() #0 {
+entry:
+  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
+  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
+  %sub = fsub float %0, %1
+  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
+  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
+  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
+  %add = fadd float %2, %3
+  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
+  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
+  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
+  %sub1 = fsub float %4, %5
+  store float %sub1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
+  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
+  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
+  %add2 = fadd float %6, %7
+  store float %add2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
+  ret void
+}
+
+; CHECK-LABEL: @No_faddfsub
+; CHECK-NOT: fadd <4 x float>
+; CHECK-NOT: fsub <4 x float>
+; CHECK-NOT: shufflevector
+; Function Attrs: nounwind uwtable
+define void @No_faddfsub() #0 {
+entry:
+  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
+  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
+  %add = fadd float %0, %1
+  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
+  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
+  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
+  %add1 = fadd float %2, %3
+  store float %add1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
+  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
+  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
+  %add2 = fadd float %4, %5
+  store float %add2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
+  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
+  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
+  %sub = fsub float %6, %7
+  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
+  ret void
+}
+
+attributes #0 = { nounwind }
+
diff --git a/test/Transforms/SLPVectorizer/X86/gep.ll b/test/Transforms/SLPVectorizer/X86/gep.ll
new file mode 100644
index 0000000..9e105ec
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/gep.ll
@@ -0,0 +1,41 @@
+; RUN: opt < %s -basicaa -slp-vectorizer -S |FileCheck %s
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; Test if SLP can handle GEP expressions.
+; The test perform the following action:
+;   x->first  = y->first  + 16
+;   x->second = y->second + 16
+
+; CHECK-LABEL: foo1
+; CHECK: <2 x i32*>
+define void @foo1 ({ i32*, i32* }* noalias %x, { i32*, i32* }* noalias %y) {
+  %1 = getelementptr inbounds { i32*, i32* }* %y, i64 0, i32 0
+  %2 = load i32** %1, align 8
+  %3 = getelementptr inbounds i32* %2, i64 16
+  %4 = getelementptr inbounds { i32*, i32* }* %x, i64 0, i32 0
+  store i32* %3, i32** %4, align 8
+  %5 = getelementptr inbounds { i32*, i32* }* %y, i64 0, i32 1
+  %6 = load i32** %5, align 8
+  %7 = getelementptr inbounds i32* %6, i64 16
+  %8 = getelementptr inbounds { i32*, i32* }* %x, i64 0, i32 1
+  store i32* %7, i32** %8, align 8
+  ret void
+}
+
+; Test that we don't vectorize GEP expressions if indexes are not constants.
+; We can't produce an efficient code in that case.
+; CHECK-LABEL: foo2
+; CHECK-NOT: <2 x i32*>
+define void @foo2 ({ i32*, i32* }* noalias %x, { i32*, i32* }* noalias %y, i32 %i) {
+  %1 = getelementptr inbounds { i32*, i32* }* %y, i64 0, i32 0
+  %2 = load i32** %1, align 8
+  %3 = getelementptr inbounds i32* %2, i32 %i
+  %4 = getelementptr inbounds { i32*, i32* }* %x, i64 0, i32 0
+  store i32* %3, i32** %4, align 8
+  %5 = getelementptr inbounds { i32*, i32* }* %y, i64 0, i32 1
+  %6 = load i32** %5, align 8
+  %7 = getelementptr inbounds i32* %6, i32 %i
+  %8 = getelementptr inbounds { i32*, i32* }* %x, i64 0, i32 1
+  store i32* %7, i32** %8, align 8
+  ret void
+}
diff --git a/test/Transforms/SLPVectorizer/X86/intrinsic.ll b/test/Transforms/SLPVectorizer/X86/intrinsic.ll
index 30c5093..937252f 100644
--- a/test/Transforms/SLPVectorizer/X86/intrinsic.ll
+++ b/test/Transforms/SLPVectorizer/X86/intrinsic.ll
@@ -117,3 +117,270 @@ entry:
 ; CHECK: store <4 x i32>
 ; CHECK: ret
 }
+
+declare i32 @llvm.ctlz.i32(i32,i1) nounwind readnone
+
+define void @vec_ctlz_i32(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 true) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 true) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_ctlz_i32(
+; CHECK: load <4 x i32>
+; CHECK: load <4 x i32>
+; CHECK: call <4 x i32> @llvm.ctlz.v4i32
+; CHECK: store <4 x i32>
+; CHECK: ret
+}
+
+define void @vec_ctlz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.ctlz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.ctlz.i32(i32 %add2,i1 false) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.ctlz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.ctlz.i32(i32 %add4,i1 false) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_ctlz_i32_neg(
+; CHECK-NOT: call <4 x i32> @llvm.ctlz.v4i32
+
+}
+
+
+declare i32 @llvm.cttz.i32(i32,i1) nounwind readnone
+
+define void @vec_cttz_i32(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 true) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 true) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_cttz_i32(
+; CHECK: load <4 x i32>
+; CHECK: load <4 x i32>
+; CHECK: call <4 x i32> @llvm.cttz.v4i32
+; CHECK: store <4 x i32>
+; CHECK: ret
+}
+
+define void @vec_cttz_i32_neg(i32* %a, i32* %b, i32* %c, i1) {
+entry:
+  %i0 = load i32* %a, align 4
+  %i1 = load i32* %b, align 4
+  %add1 = add i32 %i0, %i1
+  %call1 = tail call i32 @llvm.cttz.i32(i32 %add1,i1 true) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds i32* %a, i32 1
+  %i2 = load i32* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i32 1
+  %i3 = load i32* %arrayidx3, align 4
+  %add2 = add i32 %i2, %i3
+  %call2 = tail call i32 @llvm.cttz.i32(i32 %add2,i1 false) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds i32* %a, i32 2
+  %i4 = load i32* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds i32* %b, i32 2
+  %i5 = load i32* %arrayidx5, align 4
+  %add3 = add i32 %i4, %i5
+  %call3 = tail call i32 @llvm.cttz.i32(i32 %add3,i1 true) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds i32* %a, i32 3
+  %i6 = load i32* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds i32* %b, i32 3
+  %i7 = load i32* %arrayidx7, align 4
+  %add4 = add i32 %i6, %i7
+  %call4 = tail call i32 @llvm.cttz.i32(i32 %add4,i1 false) nounwind readnone
+
+  store i32 %call1, i32* %c, align 4
+  %arrayidx8 = getelementptr inbounds i32* %c, i32 1
+  store i32 %call2, i32* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds i32* %c, i32 2
+  store i32 %call3, i32* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds i32* %c, i32 3
+  store i32 %call4, i32* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_cttz_i32_neg(
+; CHECK-NOT: call <4 x i32> @llvm.cttz.v4i32
+}
+
+
+declare float @llvm.powi.f32(float, i32)
+define void @vec_powi_f32(float* %a, float* %b, float* %c, i32 %P) {
+entry:
+  %i0 = load float* %a, align 4
+  %i1 = load float* %b, align 4
+  %add1 = fadd float %i0, %i1
+  %call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds float* %a, i32 1
+  %i2 = load float* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds float* %b, i32 1
+  %i3 = load float* %arrayidx3, align 4
+  %add2 = fadd float %i2, %i3
+  %call2 = tail call float @llvm.powi.f32(float %add2,i32 %P) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds float* %a, i32 2
+  %i4 = load float* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds float* %b, i32 2
+  %i5 = load float* %arrayidx5, align 4
+  %add3 = fadd float %i4, %i5
+  %call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds float* %a, i32 3
+  %i6 = load float* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds float* %b, i32 3
+  %i7 = load float* %arrayidx7, align 4
+  %add4 = fadd float %i6, %i7
+  %call4 = tail call float @llvm.powi.f32(float %add4,i32 %P) nounwind readnone
+
+  store float %call1, float* %c, align 4
+  %arrayidx8 = getelementptr inbounds float* %c, i32 1
+  store float %call2, float* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds float* %c, i32 2
+  store float %call3, float* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds float* %c, i32 3
+  store float %call4, float* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_powi_f32(
+; CHECK: load <4 x float>
+; CHECK: load <4 x float>
+; CHECK: call <4 x float> @llvm.powi.v4f32
+; CHECK: store <4 x float>
+; CHECK: ret
+}
+
+
+define void @vec_powi_f32_neg(float* %a, float* %b, float* %c, i32 %P, i32 %Q) {
+entry:
+  %i0 = load float* %a, align 4
+  %i1 = load float* %b, align 4
+  %add1 = fadd float %i0, %i1
+  %call1 = tail call float @llvm.powi.f32(float %add1,i32 %P) nounwind readnone
+
+  %arrayidx2 = getelementptr inbounds float* %a, i32 1
+  %i2 = load float* %arrayidx2, align 4
+  %arrayidx3 = getelementptr inbounds float* %b, i32 1
+  %i3 = load float* %arrayidx3, align 4
+  %add2 = fadd float %i2, %i3
+  %call2 = tail call float @llvm.powi.f32(float %add2,i32 %Q) nounwind readnone
+
+  %arrayidx4 = getelementptr inbounds float* %a, i32 2
+  %i4 = load float* %arrayidx4, align 4
+  %arrayidx5 = getelementptr inbounds float* %b, i32 2
+  %i5 = load float* %arrayidx5, align 4
+  %add3 = fadd float %i4, %i5
+  %call3 = tail call float @llvm.powi.f32(float %add3,i32 %P) nounwind readnone
+
+  %arrayidx6 = getelementptr inbounds float* %a, i32 3
+  %i6 = load float* %arrayidx6, align 4
+  %arrayidx7 = getelementptr inbounds float* %b, i32 3
+  %i7 = load float* %arrayidx7, align 4
+  %add4 = fadd float %i6, %i7
+  %call4 = tail call float @llvm.powi.f32(float %add4,i32 %Q) nounwind readnone
+
+  store float %call1, float* %c, align 4
+  %arrayidx8 = getelementptr inbounds float* %c, i32 1
+  store float %call2, float* %arrayidx8, align 4
+  %arrayidx9 = getelementptr inbounds float* %c, i32 2
+  store float %call3, float* %arrayidx9, align 4
+  %arrayidx10 = getelementptr inbounds float* %c, i32 3
+  store float %call4, float* %arrayidx10, align 4
+  ret void
+
+; CHECK-LABEL: @vec_powi_f32_neg(
+; CHECK-NOT: call <4 x float> @llvm.powi.v4f32
+}
diff --git a/test/Transforms/SLPVectorizer/X86/lit.local.cfg b/test/Transforms/SLPVectorizer/X86/lit.local.cfg
index ba763cf..e71f3cc 100644
--- a/test/Transforms/SLPVectorizer/X86/lit.local.cfg
+++ b/test/Transforms/SLPVectorizer/X86/lit.local.cfg
@@ -1,4 +1,3 @@
-targets = set(config.root.targets_to_build.split())
-if not 'X86' in targets:
+if not 'X86' in config.root.targets:
     config.unsupported = True
 
diff --git a/test/Transforms/SLPVectorizer/X86/pr19657.ll b/test/Transforms/SLPVectorizer/X86/pr19657.ll
new file mode 100644
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 }