CodeGen peephole: fold redundant phys reg copies

[oota-llvm.git] / test / CodeGen / X86 / avx1-logical-load-folding.ll

diff --git a/test/CodeGen/X86/avx1-logical-load-folding.ll b/test/CodeGen/X86/avx1-logical-load-folding.ll
index 56ef55309b9e8abab10af209bb8156fbc62ec399..90e00c965391e146399c1733ed0450b18a9d153a 100644 (file)
--- a/test/CodeGen/X86/avx1-logical-load-folding.ll
+++ b/test/CodeGen/X86/avx1-logical-load-folding.ll
@@ -1,4 +1,4 @@
-; RUN: llc -O3 -disable-peephole -mattr=-avx2 < %s | FileCheck %s
+; RUN: llc -O3 -disable-peephole -mcpu=corei7-avx -mattr=+avx < %s | FileCheck %s
 
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.9.0"
@@ -6,7 +6,7 @@ target triple = "x86_64-apple-macosx10.9.0"
 ; Function Attrs: nounwind ssp uwtable
 define void @test1(float* %A, float* %C) #0 {
   %tmp1 = bitcast float* %A to <8 x float>*
-  %tmp2 = load <8 x float>* %tmp1, align 32
+  %tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
   %tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
   %tmp4 = and <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
   %tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
@@ -20,7 +20,7 @@ define void @test1(float* %A, float* %C) #0 {
 ; Function Attrs: nounwind ssp uwtable
 define void @test2(float* %A, float* %C) #0 {
   %tmp1 = bitcast float* %A to <8 x float>*
-  %tmp2 = load <8 x float>* %tmp1, align 32
+  %tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
   %tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
   %tmp4 = or <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
   %tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
@@ -34,7 +34,7 @@ define void @test2(float* %A, float* %C) #0 {
 ; Function Attrs: nounwind ssp uwtable
 define void @test3(float* %A, float* %C) #0 {
   %tmp1 = bitcast float* %A to <8 x float>*
-  %tmp2 = load <8 x float>* %tmp1, align 32
+  %tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
   %tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
   %tmp4 = xor <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
   %tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
@@ -47,7 +47,7 @@ define void @test3(float* %A, float* %C) #0 {
 
 define void @test4(float* %A, float* %C) #0 {
   %tmp1 = bitcast float* %A to <8 x float>*
-  %tmp2 = load <8 x float>* %tmp1, align 32
+  %tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
   %tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
   %tmp4 = xor <8 x i32> %tmp3, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
   %tmp5 = and <8 x i32> %tmp4, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>