Fix line endings

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291663 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/Analysis/CostModel/X86/strided-load-i16.ll b/test/Analysis/CostModel/X86/strided-load-i16.ll
index 2c2cf3938bcb3910d5517ae635d4dc502697001e..ef786e7509503d1c3ee57b2bc64c8e1df837846e 100755 (executable)
--- a/test/Analysis/CostModel/X86/strided-load-i16.ll
+++ b/test/Analysis/CostModel/X86/strided-load-i16.ll
@@ -1,113 +1,113 @@
-; REQUIRES: asserts\r
-; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s\r
-\r
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"\r
-target triple = "x86_64-unknown-linux-gnu"\r
-\r
-@A = global [10240 x i16] zeroinitializer, align 16\r
-@B = global [10240 x i16] zeroinitializer, align 16\r
-\r
-; Function Attrs: nounwind uwtable\r
-define void @load_i16_stride2() {\r
-;CHECK-LABEL: load_i16_stride2\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 32 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 1\r
-  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0\r
-  %1 = load i16, i16* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv\r
-  store i16 %1, i16* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i16_stride3() {\r
-;CHECK-LABEL: load_i16_stride3\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 32 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 3\r
-  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0\r
-  %1 = load i16, i16* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv\r
-  store i16 %1, i16* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i16_stride4() {\r
-;CHECK-LABEL: load_i16_stride4\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 5 for VF 32 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 2\r
-  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0\r
-  %1 = load i16, i16* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv\r
-  store i16 %1, i16* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i16_stride5() {\r
-;CHECK-LABEL: load_i16_stride5\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 6 for VF 32 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 5\r
-  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0\r
-  %1 = load i16, i16* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv\r
-  store i16 %1, i16* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
+; REQUIRES: asserts
+; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@A = global [10240 x i16] zeroinitializer, align 16
+@B = global [10240 x i16] zeroinitializer, align 16
+
+; Function Attrs: nounwind uwtable
+define void @load_i16_stride2() {
+;CHECK-LABEL: load_i16_stride2
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 32 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 1
+  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
+  %1 = load i16, i16* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
+  store i16 %1, i16* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i16_stride3() {
+;CHECK-LABEL: load_i16_stride3
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 32 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 3
+  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
+  %1 = load i16, i16* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
+  store i16 %1, i16* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i16_stride4() {
+;CHECK-LABEL: load_i16_stride4
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 5 for VF 32 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 2
+  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
+  %1 = load i16, i16* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
+  store i16 %1, i16* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i16_stride5() {
+;CHECK-LABEL: load_i16_stride5
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 6 for VF 32 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 5
+  %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
+  %1 = load i16, i16* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
+  store i16 %1, i16* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

diff --git a/test/Analysis/CostModel/X86/strided-load-i32.ll b/test/Analysis/CostModel/X86/strided-load-i32.ll
index 0dcd3929da7f2eec900fc1e936f99d59cf594129..fad9def2bf7849fa02009cd7cfaa419658725209 100755 (executable)
--- a/test/Analysis/CostModel/X86/strided-load-i32.ll
+++ b/test/Analysis/CostModel/X86/strided-load-i32.ll
@@ -1,110 +1,110 @@
-; REQUIRES: asserts\r
-; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s\r
-\r
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"\r
-target triple = "x86_64-unknown-linux-gnu"\r
-\r
-@A = global [10240 x i32] zeroinitializer, align 16\r
-@B = global [10240 x i32] zeroinitializer, align 16\r
-\r
-; Function Attrs: nounwind uwtable\r
-define void @load_int_stride2() {\r
-;CHECK-LABEL: load_int_stride2\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 16 For instruction:  %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 1\r
-  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0\r
-  %1 = load i32, i32* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv\r
-  store i32 %1, i32* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_int_stride3() {\r
-;CHECK-LABEL: load_int_stride3\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 16 For instruction:  %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 3\r
-  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0\r
-  %1 = load i32, i32* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv\r
-  store i32 %1, i32* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_int_stride4() {\r
-;CHECK-LABEL: load_int_stride4\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 5 for VF 16 For instruction:  %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 2\r
-  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0\r
-  %1 = load i32, i32* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv\r
-  store i32 %1, i32* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_int_stride5() {\r
-;CHECK-LABEL: load_int_stride5\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 6 for VF 16 For instruction:  %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 5\r
-  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0\r
-  %1 = load i32, i32* %arrayidx, align 4\r
-  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv\r
-  store i32 %1, i32* %arrayidx2, align 2\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
+; REQUIRES: asserts
+; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@A = global [10240 x i32] zeroinitializer, align 16
+@B = global [10240 x i32] zeroinitializer, align 16
+
+; Function Attrs: nounwind uwtable
+define void @load_int_stride2() {
+;CHECK-LABEL: load_int_stride2
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 16 For instruction:  %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 1
+  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0
+  %1 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv
+  store i32 %1, i32* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_int_stride3() {
+;CHECK-LABEL: load_int_stride3
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 16 For instruction:  %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 3
+  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0
+  %1 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv
+  store i32 %1, i32* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_int_stride4() {
+;CHECK-LABEL: load_int_stride4
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 5 for VF 16 For instruction:  %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 2
+  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0
+  %1 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv
+  store i32 %1, i32* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_int_stride5() {
+;CHECK-LABEL: load_int_stride5
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 6 for VF 16 For instruction:  %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 5
+  %arrayidx = getelementptr inbounds [10240 x i32], [10240 x i32]* @A, i64 0, i64 %0
+  %1 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [10240 x i32], [10240 x i32]* @B, i64 0, i64 %indvars.iv
+  store i32 %1, i32* %arrayidx2, align 2
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+

diff --git a/test/Analysis/CostModel/X86/strided-load-i64.ll b/test/Analysis/CostModel/X86/strided-load-i64.ll
index 0370b6f80efdb911dfcca1fbca62dafd21e9c851..a7f593017d6035c5d226e8eae884a73e04d60304 100755 (executable)
--- a/test/Analysis/CostModel/X86/strided-load-i64.ll
+++ b/test/Analysis/CostModel/X86/strided-load-i64.ll
@@ -1,81 +1,81 @@
-; REQUIRES: asserts\r
-; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s\r
-\r
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"\r
-target triple = "x86_64-unknown-linux-gnu"\r
-\r
-@A = global [10240 x i64] zeroinitializer, align 16\r
-@B = global [10240 x i64] zeroinitializer, align 16\r
-\r
-; Function Attrs: nounwind uwtable\r
-define void @load_i64_stride2() {\r
-;CHECK-LABEL: load_i64_stride2\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 1\r
-  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0\r
-  %1 = load i64, i64* %arrayidx, align 16\r
-  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv\r
-  store i64 %1, i64* %arrayidx2, align 8\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i64_stride3() {\r
-;CHECK-LABEL: load_i64_stride3\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 3\r
-  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0\r
-  %1 = load i64, i64* %arrayidx, align 16\r
-  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv\r
-  store i64 %1, i64* %arrayidx2, align 8\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i64_stride4() {\r
-;CHECK-LABEL: load_i64_stride4\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 5 for VF 8 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 4\r
-  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0\r
-  %1 = load i64, i64* %arrayidx, align 16\r
-  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv\r
-  store i64 %1, i64* %arrayidx2, align 8\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
+; REQUIRES: asserts
+; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@A = global [10240 x i64] zeroinitializer, align 16
+@B = global [10240 x i64] zeroinitializer, align 16
+
+; Function Attrs: nounwind uwtable
+define void @load_i64_stride2() {
+;CHECK-LABEL: load_i64_stride2
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 1
+  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0
+  %1 = load i64, i64* %arrayidx, align 16
+  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv
+  store i64 %1, i64* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i64_stride3() {
+;CHECK-LABEL: load_i64_stride3
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 3
+  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0
+  %1 = load i64, i64* %arrayidx, align 16
+  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv
+  store i64 %1, i64* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i64_stride4() {
+;CHECK-LABEL: load_i64_stride4
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 5 for VF 8 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 4
+  %arrayidx = getelementptr inbounds [10240 x i64], [10240 x i64]* @A, i64 0, i64 %0
+  %1 = load i64, i64* %arrayidx, align 16
+  %arrayidx2 = getelementptr inbounds [10240 x i64], [10240 x i64]* @B, i64 0, i64 %indvars.iv
+  store i64 %1, i64* %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

diff --git a/test/Analysis/CostModel/X86/strided-load-i8.ll b/test/Analysis/CostModel/X86/strided-load-i8.ll
index 2a3a838641519f06e1bb746b23a9318d6f538a33..a97a32c5c940796cf134b0ae4a429fe1818f8509 100755 (executable)
--- a/test/Analysis/CostModel/X86/strided-load-i8.ll
+++ b/test/Analysis/CostModel/X86/strided-load-i8.ll
@@ -1,117 +1,117 @@
-; REQUIRES: asserts\r
-; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s\r
-\r
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"\r
-target triple = "x86_64-unknown-linux-gnu"\r
-\r
-@A = global [10240 x i8] zeroinitializer, align 16\r
-@B = global [10240 x i8] zeroinitializer, align 16\r
-\r
-; Function Attrs: nounwind uwtable\r
-define void @load_i8_stride2() {\r
-;CHECK-LABEL: load_i8_stride2\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 8 for VF 32 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 20 for VF 64 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 1\r
-  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0\r
-  %1 = load i8, i8* %arrayidx, align 2\r
-  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv\r
-  store i8 %1, i8* %arrayidx2, align 1\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i8_stride3() {\r
-;CHECK-LABEL: load_i8_stride3\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 8 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 20 for VF 32 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 39 for VF 64 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 3\r
-  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0\r
-  %1 = load i8, i8* %arrayidx, align 2\r
-  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv\r
-  store i8 %1, i8* %arrayidx2, align 1\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i8_stride4() {\r
-;CHECK-LABEL: load_i8_stride4\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 8 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 20 for VF 32 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 59 for VF 64 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = shl nsw i64 %indvars.iv, 2\r
-  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0\r
-  %1 = load i8, i8* %arrayidx, align 2\r
-  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv\r
-  store i8 %1, i8* %arrayidx2, align 1\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
-\r
-define void @load_i8_stride5() {\r
-;CHECK-LABEL: load_i8_stride5\r
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 3 for VF 4 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 8 for VF 8 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 20 for VF 16 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 39 for VF 32 For instruction:   %1 = load\r
-;CHECK: Found an estimated cost of 78 for VF 64 For instruction:   %1 = load\r
-entry:\r
-  br label %for.body\r
-\r
-for.body:                                         ; preds = %for.body, %entry\r
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]\r
-  %0 = mul nsw i64 %indvars.iv, 5\r
-  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0\r
-  %1 = load i8, i8* %arrayidx, align 2\r
-  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv\r
-  store i8 %1, i8* %arrayidx2, align 1\r
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1\r
-  %exitcond = icmp eq i64 %indvars.iv.next, 1024\r
-  br i1 %exitcond, label %for.end, label %for.body\r
-\r
-for.end:                                          ; preds = %for.body\r
-  ret void\r
-}\r
+; REQUIRES: asserts
+; RUN: opt -loop-vectorize -S -mcpu=skx --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@A = global [10240 x i8] zeroinitializer, align 16
+@B = global [10240 x i8] zeroinitializer, align 16
+
+; Function Attrs: nounwind uwtable
+define void @load_i8_stride2() {
+;CHECK-LABEL: load_i8_stride2
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 8 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 20 for VF 64 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 1
+  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0
+  %1 = load i8, i8* %arrayidx, align 2
+  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv
+  store i8 %1, i8* %arrayidx2, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i8_stride3() {
+;CHECK-LABEL: load_i8_stride3
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 8 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 20 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 39 for VF 64 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 3
+  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0
+  %1 = load i8, i8* %arrayidx, align 2
+  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv
+  store i8 %1, i8* %arrayidx2, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i8_stride4() {
+;CHECK-LABEL: load_i8_stride4
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 8 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 20 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 59 for VF 64 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = shl nsw i64 %indvars.iv, 2
+  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0
+  %1 = load i8, i8* %arrayidx, align 2
+  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv
+  store i8 %1, i8* %arrayidx2, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+define void @load_i8_stride5() {
+;CHECK-LABEL: load_i8_stride5
+;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 8 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 20 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 39 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 78 for VF 64 For instruction:   %1 = load
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %0 = mul nsw i64 %indvars.iv, 5
+  %arrayidx = getelementptr inbounds [10240 x i8], [10240 x i8]* @A, i64 0, i64 %0
+  %1 = load i8, i8* %arrayidx, align 2
+  %arrayidx2 = getelementptr inbounds [10240 x i8], [10240 x i8]* @B, i64 0, i64 %indvars.iv
+  store i8 %1, i8* %arrayidx2, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}