CodeGen peephole: fold redundant phys reg copies

[oota-llvm.git] / test / CodeGen / X86 / loop-strength-reduce-2.ll

diff --git a/test/CodeGen/X86/loop-strength-reduce-2.ll b/test/CodeGen/X86/loop-strength-reduce-2.ll
index b094fed2f67b95eb5e95d07e75290539ea34db2e..06281902141537769f61c202830fd82fe36d1544 100644 (file)
--- a/test/CodeGen/X86/loop-strength-reduce-2.ll
+++ b/test/CodeGen/X86/loop-strength-reduce-2.ll
@@ -1,18 +1,20 @@
-; RUN: llc < %s -march=x86 -mcpu=corei7 -relocation-model=pic | FileCheck %s -check-prefix=PIC
-; RUN: llc < %s -march=x86 -mcpu=corei7 -relocation-model=static | FileCheck %s -check-prefix=STATIC
+; RUN: llc < %s -march=x86 -relocation-model=pic | FileCheck %s -check-prefix=PIC
+; RUN: llc < %s -march=x86 -relocation-model=static | FileCheck %s -check-prefix=STATIC
 ;
 ; Make sure the common loop invariant A is hoisted up to preheader,
 ; since too many registers are needed to subsume it into the addressing modes.
 ; It's safe to sink A in when it's not pic.
 
 ; PIC:  align
-; PIC:  movlpd %xmm0, -4([[REG:%e[a-z]+]])
+; PIC:  movl  $4, -4([[REG:%e[a-z]+]])
+; PIC:  movl  $5, ([[REG]])
 ; PIC:  addl  $4, [[REG]]
 ; PIC:  decl  {{%e[[a-z]+}}
 ; PIC:  jne
 
 ; STATIC: align
-; STATIC: movlpd %xmm0, -4(%ecx)
+; STATIC: movl  $4, -4(%ecx)
+; STATIC: movl  $5, (%ecx)
 ; STATIC: addl  $4, %ecx
 ; STATIC: decl  %eax
 ; STATIC: jne
@@ -29,10 +31,10 @@ cond_true:          ; preds = %cond_true, %entry
        %indvar = phi i32 [ 0, %entry ], [ %indvar.next, %cond_true ]           ; <i32> [#uses=2]
        %i.0.0 = bitcast i32 %indvar to i32             ; <i32> [#uses=2]
        %tmp2 = add i32 %i.0.0, 1               ; <i32> [#uses=1]
-       %tmp = getelementptr [16 x [16 x i32]]* @A, i32 0, i32 %row, i32 %tmp2          ; <i32*> [#uses=1]
+       %tmp = getelementptr [16 x [16 x i32]], [16 x [16 x i32]]* @A, i32 0, i32 %row, i32 %tmp2               ; <i32*> [#uses=1]
        store i32 4, i32* %tmp
        %tmp5.upgrd.1 = add i32 %i.0.0, 2               ; <i32> [#uses=1]
-       %tmp7 = getelementptr [16 x [16 x i32]]* @A, i32 0, i32 %row, i32 %tmp5.upgrd.1         ; <i32*> [#uses=1]
+       %tmp7 = getelementptr [16 x [16 x i32]], [16 x [16 x i32]]* @A, i32 0, i32 %row, i32 %tmp5.upgrd.1              ; <i32*> [#uses=1]
        store i32 5, i32* %tmp7
        %indvar.next = add i32 %indvar, 1               ; <i32> [#uses=2]
        %exitcond = icmp eq i32 %indvar.next, %N                ; <i1> [#uses=1]