[ARM] Enable shrink-wrapping by default.

[oota-llvm.git] / test / CodeGen / X86 / fold-pcmpeqd-2.ll

diff --git a/test/CodeGen/X86/fold-pcmpeqd-2.ll b/test/CodeGen/X86/fold-pcmpeqd-2.ll
index 2bde76efd2ae7868b5a331c60c84d21070e66145..d95c6323de4ee01a2017eefef658e4ac413cb198 100644 (file)
--- a/test/CodeGen/X86/fold-pcmpeqd-2.ll
+++ b/test/CodeGen/X86/fold-pcmpeqd-2.ll
@@ -11,7 +11,7 @@
 ; CHECK: .space 16,255
 
 ; No pcmpeqd instructions, everybody uses the constant pool.
-; CHECK: program_1:
+; CHECK-LABEL: program_1:
 ; CHECK-NOT: pcmpeqd
 
        %struct.__ImageExecInfo = type <{ <4 x i32>, <4 x float>, <2 x i64>, i8*, i8*, i8*, i32, i32, i32, i32, i32 }>
@@ -20,7 +20,7 @@
 
 define void @program_1(%struct._image2d_t* %dest, %struct._image2d_t* %t0, <4 x float> %p0, <4 x float> %p1, <4 x float> %p4, <4 x float> %p5, <4 x float> %p6) nounwind {
 entry:
-       %tmp3.i = load i32* null                ; <i32> [#uses=1]
+       %tmp3.i = load i32, i32* null           ; <i32> [#uses=1]
        %cmp = icmp slt i32 0, %tmp3.i          ; <i1> [#uses=1]
        br i1 %cmp, label %forcond, label %ifthen
 
@@ -28,7 +28,7 @@ ifthen:               ; preds = %entry
        ret void
 
 forcond:               ; preds = %entry
-       %tmp3.i536 = load i32* null             ; <i32> [#uses=1]
+       %tmp3.i536 = load i32, i32* null                ; <i32> [#uses=1]
        %cmp12 = icmp slt i32 0, %tmp3.i536             ; <i1> [#uses=1]
        br i1 %cmp12, label %forbody, label %afterfor
 
@@ -54,22 +54,27 @@ forbody:            ; preds = %forcond
        %mul310 = fmul <4 x float> %bitcast204.i104, zeroinitializer            ; <<4 x float>> [#uses=2]
        %mul313 = fmul <4 x float> %bitcast204.i, zeroinitializer               ; <<4 x float>> [#uses=1]
        %cmpunord.i11 = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i8 3) nounwind          ; <<4 x float>> [#uses=1]
+       %tmp83 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul310, <4 x float> zeroinitializer) nounwind               ; <<4 x float>> [#uses=1]
+       %bitcast.i3 = bitcast <4 x float> %mul310 to <4 x i32>          ; <<4 x i32>> [#uses=1]
+       %andps.i5 = and <4 x i32> %bitcast.i3, zeroinitializer          ; <<4 x i32>> [#uses=1]
+
+       call void null(<4 x float> %mul313, <4 x float> %cmpunord.i11, <4 x float> %tmp83, <4 x float> zeroinitializer, %struct.__ImageExecInfo* null, <4 x i32> zeroinitializer) nounwind
+
+       %tmp84 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul313, <4 x float> zeroinitializer) nounwind               ; <<4 x float>> [#uses=1]
+
        %bitcast6.i13 = bitcast <4 x float> %cmpunord.i11 to <4 x i32>          ; <<4 x i32>> [#uses=2]
        %andps.i14 = add <4 x i32> <i32 1, i32 1, i32 1, i32 1>, %bitcast6.i13          ; <<4 x i32>> [#uses=1]
        %not.i16 = xor <4 x i32> %bitcast6.i13, < i32 -1, i32 -1, i32 -1, i32 -1 >              ; <<4 x i32>> [#uses=1]
        %andnps.i17 = add <4 x i32> <i32 1, i32 1, i32 1, i32 1>, %not.i16              ; <<4 x i32>> [#uses=1]
        %orps.i18 = or <4 x i32> %andnps.i17, %andps.i14                ; <<4 x i32>> [#uses=1]
        %bitcast17.i19 = bitcast <4 x i32> %orps.i18 to <4 x float>             ; <<4 x float>> [#uses=1]
-       %tmp83 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul310, <4 x float> zeroinitializer) nounwind               ; <<4 x float>> [#uses=1]
-       %bitcast.i3 = bitcast <4 x float> %mul310 to <4 x i32>          ; <<4 x i32>> [#uses=1]
-       %andps.i5 = and <4 x i32> %bitcast.i3, zeroinitializer          ; <<4 x i32>> [#uses=1]
+
        %bitcast11.i6 = bitcast <4 x float> %tmp83 to <4 x i32>         ; <<4 x i32>> [#uses=1]
        %not.i7 = xor <4 x i32> zeroinitializer, < i32 -1, i32 -1, i32 -1, i32 -1 >             ; <<4 x i32>> [#uses=1]
        %andnps.i8 = and <4 x i32> %bitcast11.i6, %not.i7               ; <<4 x i32>> [#uses=1]
-       call void null(<4 x float> %mul313, <4 x float> %cmpunord.i11, <4 x float> %tmp83, <4 x float> zeroinitializer, %struct.__ImageExecInfo* null, <4 x i32> zeroinitializer) nounwind
        %orps.i9 = or <4 x i32> %andnps.i8, %andps.i5           ; <<4 x i32>> [#uses=1]
        %bitcast17.i10 = bitcast <4 x i32> %orps.i9 to <4 x float>              ; <<4 x float>> [#uses=1]
-       %tmp84 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %mul313, <4 x float> zeroinitializer) nounwind               ; <<4 x float>> [#uses=1]
+
        %bitcast6.i = bitcast <4 x float> zeroinitializer to <4 x i32>          ; <<4 x i32>> [#uses=2]
        %andps.i = and <4 x i32> zeroinitializer, %bitcast6.i           ; <<4 x i32>> [#uses=1]
        %bitcast11.i = bitcast <4 x float> %tmp84 to <4 x i32>          ; <<4 x i32>> [#uses=1]