vendor/llvm/llvm-release_350-r216957

15 files changed, 834 insertions, 18 deletions

diff --git a/test/Transforms/LoopVectorize/X86/already-vectorized.ll b/test/Transforms/LoopVectorize/X86/already-vectorized.ll
index 885418c0fdd9..9c69ba87f392 100644
--- a/test/Transforms/LoopVectorize/X86/already-vectorized.ll
+++ b/test/Transforms/LoopVectorize/X86/already-vectorized.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -debug-only=loop-vectorize -O3 -S 2>&1 | FileCheck %s
+; RUN: opt < %s -disable-loop-unrolling -debug-only=loop-vectorize -O3 -S 2>&1 | FileCheck %s
 ; REQUIRES: asserts
 ; We want to make sure that we don't even try to vectorize loops again
 ; The vectorizer used to mark the un-vectorized loop only as already vectorized
@@ -40,7 +40,7 @@ for.end:                                          ; preds = %for.body
 
 ; Now, we check for the Hint metadata
 ; CHECK: [[vect]] = metadata !{metadata [[vect]], metadata [[width:![0-9]+]], metadata [[unroll:![0-9]+]]}
-; CHECK: [[width]] = metadata !{metadata !"llvm.vectorizer.width", i32 1}
-; CHECK: [[unroll]] = metadata !{metadata !"llvm.vectorizer.unroll", i32 1}
+; CHECK: [[width]] = metadata !{metadata !"llvm.loop.vectorize.width", i32 1}
+; CHECK: [[unroll]] = metadata !{metadata !"llvm.loop.interleave.count", i32 1}
 ; CHECK: [[scalar]] = metadata !{metadata [[scalar]], metadata [[width]], metadata [[unroll]]}
 
diff --git a/test/Transforms/LoopVectorize/X86/avx512.ll b/test/Transforms/LoopVectorize/X86/avx512.ll
new file mode 100644
index 000000000000..a2208668177d
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/avx512.ll
@@ -0,0 +1,35 @@
+; RUN: opt -mattr=+avx512f --loop-vectorize -S < %s | llc -mattr=+avx512f | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.9.0"
+
+; Verify that we generate 512-bit wide vectors for a basic integer memset
+; loop.
+
+; CHECK-LABEL: f:
+; CHECK: vmovdqu32 %zmm{{.}}, (
+; CHECK-NOT: %ymm
+
+define void @f(i32* %a, i32 %n) {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, 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 ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  store i32 %n, i32* %arrayidx, align 4
+  %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
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll b/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll
new file mode 100644
index 000000000000..529ed883c3b4
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/fp32_to_uint32-cost-model.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -mcpu=core-avx2 -loop-vectorize -S | llc -mcpu=core-avx2 | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx"
+
+@float_array = common global [10000 x float] zeroinitializer, align 16
+@unsigned_array = common global [10000 x i32] zeroinitializer, align 16
+
+; If we need to scalarize the fptoui and then use inserts to build up the
+; vector again, then there is certainly no value in going 256-bit wide.
+; CHECK-NOT: vinserti128
+
+define void @convert(i32 %N) {
+entry:
+  %0 = icmp eq i32 %N, 0
+  br i1 %0, label %for.end, label %for.body.preheader
+
+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 ]
+  %arrayidx = getelementptr inbounds [10000 x float]* @float_array, i64 0, i64 %indvars.iv
+  %1 = load float* %arrayidx, align 4
+  %conv = fptoui float %1 to i32
+  %arrayidx2 = getelementptr inbounds [10000 x i32]* @unsigned_array, i64 0, i64 %indvars.iv
+  store i32 %conv, i32* %arrayidx2, align 4
+  %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
+  ret void
+}
+
diff --git a/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll b/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll
new file mode 100644
index 000000000000..ef3e3bec793a
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -mcpu=core-avx2 -loop-vectorize -S | llc -mcpu=core-avx2 | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx"
+
+@n = global i32 10000, align 4
+@double_array = common global [10000 x double] zeroinitializer, align 16
+@unsigned_array = common global [10000 x i32] zeroinitializer, align 16
+
+; If we need to scalarize the fptoui and then use inserts to build up the
+; vector again, then there is certainly no value in going 256-bit wide.
+; CHECK-NOT: vpinsrd
+
+define void @convert() {
+entry:
+  %0 = load i32* @n, align 4
+  %cmp4 = icmp eq i32 %0, 0
+  br i1 %cmp4, label %for.end, label %for.body.preheader
+
+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 ]
+  %arrayidx = getelementptr inbounds [10000 x double]* @double_array, i64 0, i64 %indvars.iv
+  %1 = load double* %arrayidx, align 8
+  %conv = fptoui double %1 to i32
+  %arrayidx2 = getelementptr inbounds [10000 x i32]* @unsigned_array, i64 0, i64 %indvars.iv
+  store i32 %conv, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %2 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp ult i32 %2, %0
+  br i1 %cmp, label %for.body, label %for.end.loopexit
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll b/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
new file mode 100644
index 000000000000..23e62275ce04
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+
+; CHECK: cost of 7 for VF 8 For instruction:   %conv = fptosi float %tmp to i8
+define void @float_to_sint8_cost(i8* noalias nocapture %a, float* noalias nocapture readonly %b) nounwind {
+entry:
+  br label %for.body
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
+  %tmp = load float* %arrayidx, align 4
+  %conv = fptosi float %tmp to i8
+  %arrayidx2 = getelementptr inbounds i8* %a, i64 %indvars.iv
+  store i8 %conv, i8* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/lit.local.cfg b/test/Transforms/LoopVectorize/X86/lit.local.cfg
index ba763cf03ffc..e71f3cc4c41e 100644
--- a/test/Transforms/LoopVectorize/X86/lit.local.cfg
+++ b/test/Transforms/LoopVectorize/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/LoopVectorize/X86/metadata-enable.ll b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
new file mode 100644
index 000000000000..8e0ca417b404
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
@@ -0,0 +1,176 @@
+; RUN: opt < %s -mcpu=corei7 -O1 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1
+; RUN: opt < %s -mcpu=corei7 -O2 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O2
+; RUN: opt < %s -mcpu=corei7 -O3 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O3
+; RUN: opt < %s -mcpu=corei7 -Os -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=Os
+; RUN: opt < %s -mcpu=corei7 -Oz -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=Oz
+; RUN: opt < %s -mcpu=corei7 -O1 -vectorize-loops -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1VEC
+; RUN: opt < %s -mcpu=corei7 -Oz -vectorize-loops -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=OzVEC
+; RUN: opt < %s -mcpu=corei7 -O1 -loop-vectorize -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1VEC2
+; RUN: opt < %s -mcpu=corei7 -Oz -loop-vectorize -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=OzVEC2
+; RUN: opt < %s -mcpu=corei7 -O3 -disable-loop-vectorization -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O3DIS
+
+; This file tests the llvm.loop.vectorize.enable metadata forcing
+; vectorization even when optimization levels are too low, or when
+; vectorization is disabled.
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; O1-LABEL: @enabled(
+; O1: store <4 x i32>
+; O1: ret i32
+; O2-LABEL: @enabled(
+; O2: store <4 x i32>
+; O2: ret i32
+; O3-LABEL: @enabled(
+; O3: store <4 x i32>
+; O3: ret i32
+; Pragma always wins!
+; O3DIS-LABEL: @enabled(
+; O3DIS: store <4 x i32>
+; O3DIS: ret i32
+; Os-LABEL: @enabled(
+; Os: store <4 x i32>
+; Os: ret i32
+; Oz-LABEL: @enabled(
+; Oz: store <4 x i32>
+; Oz: ret i32
+; O1VEC-LABEL: @enabled(
+; O1VEC: store <4 x i32>
+; O1VEC: ret i32
+; OzVEC-LABEL: @enabled(
+; OzVEC: store <4 x i32>
+; OzVEC: ret i32
+; O1VEC2-LABEL: @enabled(
+; O1VEC2: store <4 x i32>
+; O1VEC2: ret i32
+; OzVEC2-LABEL: @enabled(
+; OzVEC2: store <4 x i32>
+; OzVEC2: ret i32
+
+define i32 @enabled(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %N) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %N
+  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  store i32 %add, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                          ; preds = %for.body
+  %1 = load i32* %a, align 4
+  ret i32 %1
+}
+
+; O1-LABEL: @nopragma(
+; O1-NOT: store <4 x i32>
+; O1: ret i32
+; O2-LABEL: @nopragma(
+; O2: store <4 x i32>
+; O2: ret i32
+; O3-LABEL: @nopragma(
+; O3: store <4 x i32>
+; O3: ret i32
+; O3DIS-LABEL: @nopragma(
+; O3DIS-NOT: store <4 x i32>
+; O3DIS: ret i32
+; Os-LABEL: @nopragma(
+; Os: store <4 x i32>
+; Os: ret i32
+; Oz-LABEL: @nopragma(
+; Oz-NOT: store <4 x i32>
+; Oz: ret i32
+; O1VEC-LABEL: @nopragma(
+; O1VEC: store <4 x i32>
+; O1VEC: ret i32
+; OzVEC-LABEL: @nopragma(
+; OzVEC: store <4 x i32>
+; OzVEC: ret i32
+; O1VEC2-LABEL: @nopragma(
+; O1VEC2: store <4 x i32>
+; O1VEC2: ret i32
+; OzVEC2-LABEL: @nopragma(
+; OzVEC2: store <4 x i32>
+; OzVEC2: ret i32
+
+define i32 @nopragma(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %N) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %N
+  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  store i32 %add, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  %1 = load i32* %a, align 4
+  ret i32 %1
+}
+
+; O1-LABEL: @disabled(
+; O1-NOT: store <4 x i32>
+; O1: ret i32
+; O2-LABEL: @disabled(
+; O2-NOT: store <4 x i32>
+; O2: ret i32
+; O3-LABEL: @disabled(
+; O3-NOT: store <4 x i32>
+; O3: ret i32
+; O3DIS-LABEL: @disabled(
+; O3DIS-NOT: store <4 x i32>
+; O3DIS: ret i32
+; Os-LABEL: @disabled(
+; Os-NOT: store <4 x i32>
+; Os: ret i32
+; Oz-LABEL: @disabled(
+; Oz-NOT: store <4 x i32>
+; Oz: ret i32
+; O1VEC-LABEL: @disabled(
+; O1VEC-NOT: store <4 x i32>
+; O1VEC: ret i32
+; OzVEC-LABEL: @disabled(
+; OzVEC-NOT: store <4 x i32>
+; OzVEC: ret i32
+; O1VEC2-LABEL: @disabled(
+; O1VEC2-NOT: store <4 x i32>
+; O1VEC2: ret i32
+; OzVEC2-LABEL: @disabled(
+; OzVEC2-NOT: store <4 x i32>
+; OzVEC2: ret i32
+
+define i32 @disabled(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %N) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %N
+  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  store i32 %add, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
+
+for.end:                                          ; preds = %for.body
+  %1 = load i32* %a, align 4
+  ret i32 %1
+}
+
+!0 = metadata !{metadata !0, metadata !1}
+!1 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 1}
+!2 = metadata !{metadata !2, metadata !3}
+!3 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 0}
diff --git a/test/Transforms/LoopVectorize/X86/small-size.ll b/test/Transforms/LoopVectorize/X86/small-size.ll
index 14ac417bb573..bcf16aa5db13 100644
--- a/test/Transforms/LoopVectorize/X86/small-size.ll
+++ b/test/Transforms/LoopVectorize/X86/small-size.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s -basicaa -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -loop-vectorize-with-block-frequency -dce -instcombine -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
@@ -115,6 +115,31 @@ define void @example3(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture
   ret void
 }
 
+; N is unknown, we need a tail. Can't vectorize because the loop is cold.
+;CHECK-LABEL: @example4(
+;CHECK-NOT: <4 x i32>
+;CHECK: ret void
+define void @example4(i32 %n, i32* noalias nocapture %p, i32* noalias nocapture %q) {
+  %1 = icmp eq i32 %n, 0
+  br i1 %1, label %._crit_edge, label %.lr.ph, !prof !0
+
+.lr.ph:                                           ; preds = %0, %.lr.ph
+  %.05 = phi i32 [ %2, %.lr.ph ], [ %n, %0 ]
+  %.014 = phi i32* [ %5, %.lr.ph ], [ %p, %0 ]
+  %.023 = phi i32* [ %3, %.lr.ph ], [ %q, %0 ]
+  %2 = add nsw i32 %.05, -1
+  %3 = getelementptr inbounds i32* %.023, i64 1
+  %4 = load i32* %.023, align 16
+  %5 = getelementptr inbounds i32* %.014, i64 1
+  store i32 %4, i32* %.014, align 16
+  %6 = icmp eq i32 %2, 0
+  br i1 %6, label %._crit_edge, label %.lr.ph
+
+._crit_edge:                                      ; preds = %.lr.ph, %0
+  ret void
+}
+
+!0 = metadata !{metadata !"branch_weights", i32 64, i32 4}
 
 ; We can't vectorize this one because we need a runtime ptr check.
 ;CHECK-LABEL: @example23(
diff --git a/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll b/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
new file mode 100644
index 000000000000..86c32b2d2ee4
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
@@ -0,0 +1,26 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+
+; CHECK: cost of 20 for VF 2 For instruction:   %conv = uitofp i64 %tmp to double
+; CHECK: cost of 40 for VF 4 For instruction:   %conv = uitofp i64 %tmp to double
+define void @uint64_to_double_cost(i64* noalias nocapture %a, double* noalias nocapture readonly %b) nounwind {
+entry:
+  br label %for.body
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i64* %a, i64 %indvars.iv
+  %tmp = load i64* %arrayidx, align 4
+  %conv = uitofp i64 %tmp to double
+  %arrayidx2 = getelementptr inbounds double* %b, i64 %indvars.iv
+  store double %conv, double* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll b/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
index ea107dc4dc51..d5024bb13210 100644
--- a/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
+++ b/test/Transforms/LoopVectorize/X86/unroll-small-loops.ll
@@ -1,13 +1,26 @@
-; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-unroll=0 -dce -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -force-vector-unroll=0 -dce -S \
+; RUN:   | FileCheck %s --check-prefix=CHECK-VECTOR
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=1 -force-vector-unroll=0 -dce -S \
+; RUN:   | FileCheck %s --check-prefix=CHECK-SCALAR
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
-;CHECK-LABEL: @foo(
-;CHECK: load <4 x i32>
-;CHECK-NOT: load <4 x i32>
-;CHECK: store <4 x i32>
-;CHECK-NOT: store <4 x i32>
-;CHECK: ret
+
+; We don't unroll this loop because it has a small constant trip count.
+;
+; CHECK-VECTOR-LABEL: @foo(
+; CHECK-VECTOR: load <4 x i32>
+; CHECK-VECTOR-NOT: load <4 x i32>
+; CHECK-VECTOR: store <4 x i32>
+; CHECK-VECTOR-NOT: store <4 x i32>
+; CHECK-VECTOR: ret
+;
+; CHECK-SCALAR-LABEL: @foo(
+; CHECK-SCALAR: load i32*
+; CHECK-SCALAR-NOT: load i32*
+; CHECK-SCALAR: store i32
+; CHECK-SCALAR-NOT: store i32
+; CHECK-SCALAR: ret
 define i32 @foo(i32* nocapture %A) nounwind uwtable ssp {
   br label %1
 
@@ -26,10 +39,18 @@ define i32 @foo(i32* nocapture %A) nounwind uwtable ssp {
   ret i32 undef
 }
 
-;CHECK-LABEL: @bar(
-;CHECK: store <4 x i32>
-;CHECK: store <4 x i32>
-;CHECK: ret
+; But this is a good small loop to unroll as we don't know of a bound on its
+; trip count.
+;
+; CHECK-VECTOR-LABEL: @bar(
+; CHECK-VECTOR: store <4 x i32>
+; CHECK-VECTOR: store <4 x i32>
+; CHECK-VECTOR: ret
+;
+; CHECK-SCALAR-LABEL: @bar(
+; CHECK-SCALAR: store i32
+; CHECK-SCALAR: store i32
+; CHECK-SCALAR: ret
 define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp {
   %1 = icmp sgt i32 %n, 0
   br i1 %1, label %.lr.ph, label %._crit_edge
@@ -48,3 +69,32 @@ define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp {
 ._crit_edge:                                      ; preds = %.lr.ph, %0
   ret i32 undef
 }
+
+; Also unroll if we need a runtime check but it was going to be added for
+; vectorization anyways.
+; CHECK-VECTOR-LABEL: @runtime_chk(
+; CHECK-VECTOR: store <4 x float>
+; CHECK-VECTOR: store <4 x float>
+;
+; But not if the unrolling would introduce the runtime check.
+; CHECK-SCALAR-LABEL: @runtime_chk(
+; CHECK-SCALAR: store float
+; CHECK-SCALAR-NOT: store float
+define void @runtime_chk(float* %A, float* %B, float %N) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4
+  %mul = fmul float %0, %N
+  %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+  store float %mul, float* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/vect.omp.force.ll b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
new file mode 100644
index 000000000000..074313bde6f5
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
@@ -0,0 +1,93 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+; CHECK: LV: Loop hints: force=enabled
+; CHECK: LV: Loop hints: force=?
+; No more loops in the module
+; CHECK-NOT: LV: Loop hints: force=
+; CHECK: 2 loop-vectorize               - Number of loops analyzed for vectorization
+; CHECK: 1 loop-vectorize               - Number of loops vectorized
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+;
+; The source code for the test:
+;
+; #include <math.h>
+; void foo(float* restrict A, float * restrict B, int size)
+; {
+;   for (int i = 0; i < size; ++i) A[i] = sinf(B[i]);
+; }
+;
+
+;
+; This loop will be vectorized, although the scalar cost is lower than any of vector costs, but vectorization is explicitly forced in metadata.
+;
+
+define void @vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
+entry:
+  %cmp6 = icmp sgt i32 %size, 0
+  br i1 %cmp6, label %for.body.preheader, label %for.end
+
+for.body.preheader:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
+  %call = tail call float @llvm.sin.f32(float %0)
+  %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+  store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
+  %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, %size
+  br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !1
+
+for.end.loopexit:
+  br label %for.end
+
+for.end:
+  ret void
+}
+
+!1 = metadata !{metadata !1, metadata !2}
+!2 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true}
+
+;
+; This method will not be vectorized, as scalar cost is lower than any of vector costs.
+;
+
+define void @not_vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
+entry:
+  %cmp6 = icmp sgt i32 %size, 0
+  br i1 %cmp6, label %for.body.preheader, label %for.end
+
+for.body.preheader:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %call = tail call float @llvm.sin.f32(float %0)
+  %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+  store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %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, %size
+  br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !3
+
+for.end.loopexit:
+  br label %for.end
+
+for.end:
+  ret void
+}
+
+declare float @llvm.sin.f32(float) nounwind readnone
+
+; Dummy metadata
+!3 = metadata !{metadata !3}
+
diff --git a/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll b/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
new file mode 100644
index 000000000000..97c31a148e3a
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vect.omp.force.small-tc.ll
@@ -0,0 +1,73 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -debug-only=loop-vectorize -stats -S -vectorizer-min-trip-count=21 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+; CHECK: LV: Loop hints: force=enabled
+; CHECK: LV: Loop hints: force=?
+; No more loops in the module
+; CHECK-NOT: LV: Loop hints: force=
+; CHECK: 2 loop-vectorize               - Number of loops analyzed for vectorization
+; CHECK: 1 loop-vectorize               - Number of loops vectorized
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+;
+; The source code for the test:
+;
+; void foo(float* restrict A, float* restrict B)
+; {
+;     for (int i = 0; i < 20; ++i) A[i] += B[i];
+; }
+;
+
+;
+; This loop will be vectorized, although the trip count is below the threshold, but vectorization is explicitly forced in metadata.
+;
+define void @vectorized(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
+  %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+  %1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
+  %add = fadd fast float %0, %1
+  store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 20
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
+
+for.end:
+  ret void
+}
+
+!1 = metadata !{metadata !1, metadata !2}
+!2 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true}
+
+;
+; This loop will not be vectorized as the trip count is below the threshold.
+;
+define void @not_vectorized(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+  %1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %add = fadd fast float %0, %1
+  store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 20
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3
+
+for.end:
+  ret void
+}
+
+!3 = metadata !{metadata !3}
+
diff --git a/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll b/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
index 59bb8d0054c5..e57cfefec07c 100644
--- a/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
+++ b/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
@@ -1,4 +1,4 @@
-; RUN: opt -loop-vectorize -mcpu=corei7-avx -debug -S < %s 2>&1 | FileCheck %s
+; RUN: opt -basicaa -loop-vectorize -mcpu=corei7-avx -debug -S < %s 2>&1 | FileCheck %s
 ; REQUIRES: asserts
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
diff --git a/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll b/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll
new file mode 100644
index 000000000000..93f24cbf4909
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vectorization-remarks-missed.ll
@@ -0,0 +1,161 @@
+; RUN: opt < %s -loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
+
+; C/C++ code for tests
+; void test(int *A, int Length) {
+; #pragma clang loop vectorize(enable) interleave(enable)
+;   for (int i = 0; i < Length; i++) {
+;     A[i] = i;
+;     if (A[i] > Length)
+;       break;
+;   }
+; }
+
+; void test_disabled(int *A, int Length) {
+; #pragma clang loop vectorize(disable) interleave(disable)
+;   for (int i = 0; i < Length; i++)
+;     A[i] = i;
+; }
+
+; void test_array_bounds(int *A, int *B, int Length) {
+; #pragma clang loop vectorize(enable)
+;   for (int i = 0; i < Length; i++)
+;     A[i] = A[B[i]];
+; }
+
+; File, line, and column should match those specified in the metadata
+; CHECK: remark: source.cpp:4:5: loop not vectorized: could not determine number of loop iterations
+; CHECK: remark: source.cpp:4:5: loop not vectorized: vectorization was not specified
+; CHECK: remark: source.cpp:13:5: loop not vectorized: vector width and interleave count are explicitly set to 1
+; CHECK: remark: source.cpp:19:5: loop not vectorized: cannot identify array bounds
+; CHECK: remark: source.cpp:19:5: loop not vectorized: vectorization is explicitly enabled
+; CHECK: warning: source.cpp:19:5: loop not vectorized: failed explicitly specified loop vectorization
+
+; CHECK: _Z4testPii
+; CHECK-NOT: x i32>
+; CHECK: ret
+
+; CHECK: _Z13test_disabledPii
+; CHECK-NOT: x i32>
+; CHECK: ret
+
+; CHECK: _Z17test_array_boundsPiS_i
+; CHECK-NOT: x i32>
+; CHECK: ret
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; Function Attrs: nounwind optsize ssp uwtable
+define void @_Z4testPii(i32* nocapture %A, i32 %Length) #0 {
+entry:
+  %cmp10 = icmp sgt i32 %Length, 0, !dbg !12
+  br i1 %cmp10, label %for.body, label %for.end, !dbg !12, !llvm.loop !14
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv, !dbg !16
+  %0 = trunc i64 %indvars.iv to i32, !dbg !16
+  store i32 %0, i32* %arrayidx, align 4, !dbg !16, !tbaa !18
+  %cmp3 = icmp sle i32 %0, %Length, !dbg !22
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !12
+  %1 = trunc i64 %indvars.iv.next to i32
+  %cmp = icmp slt i32 %1, %Length, !dbg !12
+  %or.cond = and i1 %cmp3, %cmp, !dbg !22
+  br i1 %or.cond, label %for.body, label %for.end, !dbg !22
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void, !dbg !24
+}
+
+; Function Attrs: nounwind optsize ssp uwtable
+define void @_Z13test_disabledPii(i32* nocapture %A, i32 %Length) #0 {
+entry:
+  %cmp4 = icmp sgt i32 %Length, 0, !dbg !25
+  br i1 %cmp4, label %for.body, label %for.end, !dbg !25, !llvm.loop !27
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv, !dbg !30
+  %0 = trunc i64 %indvars.iv to i32, !dbg !30
+  store i32 %0, i32* %arrayidx, align 4, !dbg !30, !tbaa !18
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !25
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !25
+  %exitcond = icmp eq i32 %lftr.wideiv, %Length, !dbg !25
+  br i1 %exitcond, label %for.end, label %for.body, !dbg !25, !llvm.loop !27
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void, !dbg !31
+}
+
+; Function Attrs: nounwind optsize ssp uwtable
+define void @_Z17test_array_boundsPiS_i(i32* nocapture %A, i32* nocapture readonly %B, i32 %Length) #0 {
+entry:
+  %cmp9 = icmp sgt i32 %Length, 0, !dbg !32
+  br i1 %cmp9, label %for.body.preheader, label %for.end, !dbg !32, !llvm.loop !34
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body, !dbg !35
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds i32* %B, i64 %indvars.iv, !dbg !35
+  %0 = load i32* %arrayidx, align 4, !dbg !35, !tbaa !18
+  %idxprom1 = sext i32 %0 to i64, !dbg !35
+  %arrayidx2 = getelementptr inbounds i32* %A, i64 %idxprom1, !dbg !35
+  %1 = load i32* %arrayidx2, align 4, !dbg !35, !tbaa !18
+  %arrayidx4 = getelementptr inbounds i32* %A, i64 %indvars.iv, !dbg !35
+  store i32 %1, i32* %arrayidx4, align 4, !dbg !35, !tbaa !18
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !32
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !32
+  %exitcond = icmp eq i32 %lftr.wideiv, %Length, !dbg !32
+  br i1 %exitcond, label %for.end.loopexit, label %for.body, !dbg !32, !llvm.loop !34
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret void, !dbg !36
+}
+
+attributes #0 = { nounwind }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!9, !10}
+!llvm.ident = !{!11}
+
+!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5.0", i1 true, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !"", i32 2}
+!1 = metadata !{metadata !"source.cpp", metadata !"."}
+!2 = metadata !{}
+!3 = metadata !{metadata !4, metadata !7, metadata !8}
+!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test", metadata !"test", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32)* @_Z4testPii, null, null, metadata !2, i32 1}
+!5 = metadata !{i32 786473, metadata !1}
+!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null}
+!7 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test_disabled", metadata !"test_disabled", metadata !"", i32 10, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32)* @_Z13test_disabledPii, null, null, metadata !2, i32 10}
+!8 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"test_array_bounds", metadata !"test_array_bounds", metadata !"", i32 16, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, void (i32*, i32*, i32)* @_Z17test_array_boundsPiS_i, null, null, metadata !2, i32 16}
+!9 = metadata !{i32 2, metadata !"Dwarf Version", i32 2}
+!10 = metadata !{i32 2, metadata !"Debug Info Version", i32 1}
+!11 = metadata !{metadata !"clang version 3.5.0"}
+!12 = metadata !{i32 3, i32 8, metadata !13, null}
+!13 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 3, i32 0, i32 0}
+!14 = metadata !{metadata !14, metadata !15, metadata !15}
+!15 = metadata !{metadata !"llvm.loop.vectorize.enable", i1 true}
+!16 = metadata !{i32 4, i32 5, metadata !17, null}
+!17 = metadata !{i32 786443, metadata !1, metadata !13, i32 3, i32 36, i32 0, i32 1}
+!18 = metadata !{metadata !19, metadata !19, i64 0}
+!19 = metadata !{metadata !"int", metadata !20, i64 0}
+!20 = metadata !{metadata !"omnipotent char", metadata !21, i64 0}
+!21 = metadata !{metadata !"Simple C/C++ TBAA"}
+!22 = metadata !{i32 5, i32 9, metadata !23, null}
+!23 = metadata !{i32 786443, metadata !1, metadata !17, i32 5, i32 9, i32 0, i32 2}
+!24 = metadata !{i32 8, i32 1, metadata !4, null}
+!25 = metadata !{i32 12, i32 8, metadata !26, null}
+!26 = metadata !{i32 786443, metadata !1, metadata !7, i32 12, i32 3, i32 0, i32 3}
+!27 = metadata !{metadata !27, metadata !28, metadata !29}
+!28 = metadata !{metadata !"llvm.loop.interleave.count", i32 1}
+!29 = metadata !{metadata !"llvm.loop.vectorize.width", i32 1}
+!30 = metadata !{i32 13, i32 5, metadata !26, null}
+!31 = metadata !{i32 14, i32 1, metadata !7, null}
+!32 = metadata !{i32 18, i32 8, metadata !33, null}
+!33 = metadata !{i32 786443, metadata !1, metadata !8, i32 18, i32 3, i32 0, i32 4}
+!34 = metadata !{metadata !34, metadata !15}
+!35 = metadata !{i32 19, i32 5, metadata !33, null}
+!36 = metadata !{i32 20, i32 1, metadata !8, null}
diff --git a/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll b/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll
new file mode 100644
index 000000000000..f6834477ff51
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vectorization-remarks.ll
@@ -0,0 +1,74 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' 2>&1 | FileCheck -check-prefix=VECTORIZED %s
+; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-unroll=4 -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' 2>&1 | FileCheck -check-prefix=UNROLLED %s
+; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-unroll=1 -mtriple=x86_64-unknown-linux -S -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck -check-prefix=NONE %s
+
+; This code has all the !dbg annotations needed to track source line information,
+; but is missing the llvm.dbg.cu annotation. This prevents code generation from
+; emitting debug info in the final output.
+; RUN: llc -mtriple x86_64-pc-linux-gnu %s -o - | FileCheck -check-prefix=DEBUG-OUTPUT %s
+; DEBUG-OUTPUT-NOT: .loc
+; DEBUG-OUTPUT-NOT: {{.*}}.debug_info
+
+; VECTORIZED: remark: vectorization-remarks.c:17:8: vectorized loop (vectorization factor: 4, unrolling interleave factor: 1)
+; UNROLLED: remark: vectorization-remarks.c:17:8: unrolled with interleaving factor 4 (vectorization not beneficial)
+; NONE: remark: vectorization-remarks.c:17:8: loop not vectorized: vector width and interleave count are explicitly set to 1
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+define i32 @foo(i32 %n) #0 {
+entry:
+  %diff = alloca i32, align 4
+  %cb = alloca [16 x i8], align 16
+  %cc = alloca [16 x i8], align 16
+  store i32 0, i32* %diff, align 4, !dbg !10, !tbaa !11
+  br label %for.body, !dbg !15
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %add8 = phi i32 [ 0, %entry ], [ %add, %for.body ], !dbg !19
+  %arrayidx = getelementptr inbounds [16 x i8]* %cb, i64 0, i64 %indvars.iv, !dbg !19
+  %0 = load i8* %arrayidx, align 1, !dbg !19, !tbaa !21
+  %conv = sext i8 %0 to i32, !dbg !19
+  %arrayidx2 = getelementptr inbounds [16 x i8]* %cc, i64 0, i64 %indvars.iv, !dbg !19
+  %1 = load i8* %arrayidx2, align 1, !dbg !19, !tbaa !21
+  %conv3 = sext i8 %1 to i32, !dbg !19
+  %sub = sub i32 %conv, %conv3, !dbg !19
+  %add = add nsw i32 %sub, %add8, !dbg !19
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !15
+  %exitcond = icmp eq i64 %indvars.iv.next, 16, !dbg !15
+  br i1 %exitcond, label %for.end, label %for.body, !dbg !15
+
+for.end:                                          ; preds = %for.body
+  store i32 %add, i32* %diff, align 4, !dbg !19, !tbaa !11
+  call void @ibar(i32* %diff) #2, !dbg !22
+  ret i32 0, !dbg !23
+}
+
+declare void @ibar(i32*) #1
+
+!llvm.module.flags = !{!7, !8}
+!llvm.ident = !{!9}
+
+!1 = metadata !{metadata !"vectorization-remarks.c", metadata !"."}
+!2 = metadata !{}
+!3 = metadata !{metadata !4}
+!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"foo", metadata !"foo", metadata !"", i32 5, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 true, i32 (i32)* @foo, null, null, metadata !2, i32 6} ; [ DW_TAG_subprogram ] [line 5] [def] [scope 6] [foo]
+!5 = metadata !{i32 786473, metadata !1}          ; [ DW_TAG_file_type ] [./vectorization-remarks.c]
+!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ]
+!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 4}
+!8 = metadata !{i32 1, metadata !"Debug Info Version", i32 1}
+!9 = metadata !{metadata !"clang version 3.5.0 "}
+!10 = metadata !{i32 8, i32 3, metadata !4, null} ; [ DW_TAG_imported_declaration ]
+!11 = metadata !{metadata !12, metadata !12, i64 0}
+!12 = metadata !{metadata !"int", metadata !13, i64 0}
+!13 = metadata !{metadata !"omnipotent char", metadata !14, i64 0}
+!14 = metadata !{metadata !"Simple C/C++ TBAA"}
+!15 = metadata !{i32 17, i32 8, metadata !16, null}
+!16 = metadata !{i32 786443, metadata !1, metadata !17, i32 17, i32 8, i32 2, i32 3} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c]
+!17 = metadata !{i32 786443, metadata !1, metadata !18, i32 17, i32 8, i32 1, i32 2} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c]
+!18 = metadata !{i32 786443, metadata !1, metadata !4, i32 17, i32 3, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c]
+!19 = metadata !{i32 18, i32 5, metadata !20, null}
+!20 = metadata !{i32 786443, metadata !1, metadata !18, i32 17, i32 27, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [./vectorization-remarks.c]
+!21 = metadata !{metadata !13, metadata !13, i64 0}
+!22 = metadata !{i32 20, i32 3, metadata !4, null}
+!23 = metadata !{i32 21, i32 3, metadata !4, null}