merge a bunch of shuffle tests into sse2.ll

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112398 91177308-0d34-0410-b5e6-96231b3b80d8

9 files changed, 164 insertions, 158 deletions

diff --git a/test/CodeGen/X86/sse2.ll b/test/CodeGen/X86/sse2.ll
index 20b8eac9c8..6fc019071f 100644
--- a/test/CodeGen/X86/sse2.ll
+++ b/test/CodeGen/X86/sse2.ll
@@ -1,14 +1,14 @@
 ; Tests for SSE2 and below, without SSE3+.
 ; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=pentium4 -O3 | FileCheck %s
 
-define void @t1(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
+define void @test1(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
 	%tmp3 = load <2 x double>* %A, align 16
 	%tmp7 = insertelement <2 x double> undef, double %B, i32 0
 	%tmp9 = shufflevector <2 x double> %tmp3, <2 x double> %tmp7, <2 x i32> < i32 2, i32 1 >
 	store <2 x double> %tmp9, <2 x double>* %r, align 16
 	ret void
         
-; CHECK: t1:
+; CHECK: test1:
 ; CHECK: 	movl	8(%esp), %eax
 ; CHECK-NEXT: 	movapd	(%eax), %xmm0
 ; CHECK-NEXT: 	movlpd	12(%esp), %xmm0
@@ -17,14 +17,14 @@ define void @t1(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
 ; CHECK-NEXT: 	ret
 }
 
-define void @t2(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
+define void @test2(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
 	%tmp3 = load <2 x double>* %A, align 16
 	%tmp7 = insertelement <2 x double> undef, double %B, i32 0
 	%tmp9 = shufflevector <2 x double> %tmp3, <2 x double> %tmp7, <2 x i32> < i32 0, i32 2 >
 	store <2 x double> %tmp9, <2 x double>* %r, align 16
 	ret void
         
-; CHECK: t2:
+; CHECK: test2:
 ; CHECK: 	movl	8(%esp), %eax
 ; CHECK-NEXT: 	movapd	(%eax), %xmm0
 ; CHECK-NEXT: 	movhpd	12(%esp), %xmm0
@@ -32,3 +32,163 @@ define void @t2(<2 x double>* %r, <2 x double>* %A, double %B) nounwind  {
 ; CHECK-NEXT: 	movapd	%xmm0, (%eax)
 ; CHECK-NEXT: 	ret
 }
+
+
+define void @test3(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B) nounwind {
+	%tmp = load <4 x float>* %B		; <<4 x float>> [#uses=2]
+	%tmp3 = load <4 x float>* %A		; <<4 x float>> [#uses=2]
+	%tmp.upgrd.1 = extractelement <4 x float> %tmp3, i32 0		; <float> [#uses=1]
+	%tmp7 = extractelement <4 x float> %tmp, i32 0		; <float> [#uses=1]
+	%tmp8 = extractelement <4 x float> %tmp3, i32 1		; <float> [#uses=1]
+	%tmp9 = extractelement <4 x float> %tmp, i32 1		; <float> [#uses=1]
+	%tmp10 = insertelement <4 x float> undef, float %tmp.upgrd.1, i32 0		; <<4 x float>> [#uses=1]
+	%tmp11 = insertelement <4 x float> %tmp10, float %tmp7, i32 1		; <<4 x float>> [#uses=1]
+	%tmp12 = insertelement <4 x float> %tmp11, float %tmp8, i32 2		; <<4 x float>> [#uses=1]
+	%tmp13 = insertelement <4 x float> %tmp12, float %tmp9, i32 3		; <<4 x float>> [#uses=1]
+	store <4 x float> %tmp13, <4 x float>* %res
+	ret void
+; CHECK: @test3
+; CHECK: 	unpcklps	
+}
+
+define void @test4(<4 x float> %X, <4 x float>* %res) nounwind {
+	%tmp5 = shufflevector <4 x float> %X, <4 x float> undef, <4 x i32> < i32 2, i32 6, i32 3, i32 7 >		; <<4 x float>> [#uses=1]
+	store <4 x float> %tmp5, <4 x float>* %res
+	ret void
+; CHECK: @test4
+; CHECK: 	pshufd	$50, %xmm0, %xmm0
+}
+
+define <4 x i32> @test5(i8** %ptr) nounwind {
+; CHECK: test5:
+; CHECK: pxor
+; CHECK: punpcklbw
+; CHECK: punpcklwd
+
+	%tmp = load i8** %ptr		; <i8*> [#uses=1]
+	%tmp.upgrd.1 = bitcast i8* %tmp to float*		; <float*> [#uses=1]
+	%tmp.upgrd.2 = load float* %tmp.upgrd.1		; <float> [#uses=1]
+	%tmp.upgrd.3 = insertelement <4 x float> undef, float %tmp.upgrd.2, i32 0		; <<4 x float>> [#uses=1]
+	%tmp9 = insertelement <4 x float> %tmp.upgrd.3, float 0.000000e+00, i32 1		; <<4 x float>> [#uses=1]
+	%tmp10 = insertelement <4 x float> %tmp9, float 0.000000e+00, i32 2		; <<4 x float>> [#uses=1]
+	%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 3		; <<4 x float>> [#uses=1]
+	%tmp21 = bitcast <4 x float> %tmp11 to <16 x i8>		; <<16 x i8>> [#uses=1]
+	%tmp22 = shufflevector <16 x i8> %tmp21, <16 x i8> zeroinitializer, <16 x i32> < i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23 >		; <<16 x i8>> [#uses=1]
+	%tmp31 = bitcast <16 x i8> %tmp22 to <8 x i16>		; <<8 x i16>> [#uses=1]
+	%tmp.upgrd.4 = shufflevector <8 x i16> zeroinitializer, <8 x i16> %tmp31, <8 x i32> < i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11 >		; <<8 x i16>> [#uses=1]
+	%tmp36 = bitcast <8 x i16> %tmp.upgrd.4 to <4 x i32>		; <<4 x i32>> [#uses=1]
+	ret <4 x i32> %tmp36
+}
+
+define void @test6(<4 x float>* %res, <4 x float>* %A) nounwind {
+        %tmp1 = load <4 x float>* %A            ; <<4 x float>> [#uses=1]
+        %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> < i32 0, i32 5, i32 6, i32 7 >          ; <<4 x float>> [#uses=1]
+        store <4 x float> %tmp2, <4 x float>* %res
+        ret void
+        
+; CHECK: test6:
+; CHECK: 	movaps	(%eax), %xmm0
+; CHECK:	movaps	%xmm0, (%eax)
+}
+
+define void @test7() nounwind {
+        bitcast <4 x i32> zeroinitializer to <4 x float>                ; <<4 x float>>:1 [#uses=1]
+        shufflevector <4 x float> %1, <4 x float> zeroinitializer, <4 x i32> zeroinitializer         ; <<4 x float>>:2 [#uses=1]
+        store <4 x float> %2, <4 x float>* null
+        ret void
+        
+; CHECK: test7:
+; CHECK:	pxor	%xmm0, %xmm0
+; CHECK:	movaps	%xmm0, 0
+}
+
+@x = external global [4 x i32]
+
+define <2 x i64> @test8() nounwind {
+	%tmp = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 0)		; <i32> [#uses=1]
+	%tmp3 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 1)		; <i32> [#uses=1]
+	%tmp5 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 2)		; <i32> [#uses=1]
+	%tmp7 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 3)		; <i32> [#uses=1]
+	%tmp.upgrd.1 = insertelement <4 x i32> undef, i32 %tmp, i32 0		; <<4 x i32>> [#uses=1]
+	%tmp13 = insertelement <4 x i32> %tmp.upgrd.1, i32 %tmp3, i32 1		; <<4 x i32>> [#uses=1]
+	%tmp14 = insertelement <4 x i32> %tmp13, i32 %tmp5, i32 2		; <<4 x i32>> [#uses=1]
+	%tmp15 = insertelement <4 x i32> %tmp14, i32 %tmp7, i32 3		; <<4 x i32>> [#uses=1]
+	%tmp16 = bitcast <4 x i32> %tmp15 to <2 x i64>		; <<2 x i64>> [#uses=1]
+	ret <2 x i64> %tmp16
+; CHECK: test8:
+; CHECK: movups	(%eax), %xmm0
+}
+
+define <4 x float> @test9(i32 %dummy, float %a, float %b, float %c, float %d) nounwind {
+	%tmp = insertelement <4 x float> undef, float %a, i32 0		; <<4 x float>> [#uses=1]
+	%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1		; <<4 x float>> [#uses=1]
+	%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2		; <<4 x float>> [#uses=1]
+	%tmp13 = insertelement <4 x float> %tmp12, float %d, i32 3		; <<4 x float>> [#uses=1]
+	ret <4 x float> %tmp13
+; CHECK: test9:
+; CHECK: movups	8(%esp), %xmm0
+}
+
+define <4 x float> @test10(float %a, float %b, float %c, float %d) nounwind {
+	%tmp = insertelement <4 x float> undef, float %a, i32 0		; <<4 x float>> [#uses=1]
+	%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1		; <<4 x float>> [#uses=1]
+	%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2		; <<4 x float>> [#uses=1]
+	%tmp13 = insertelement <4 x float> %tmp12, float %d, i32 3		; <<4 x float>> [#uses=1]
+	ret <4 x float> %tmp13
+; CHECK: test10:
+; CHECK: movaps	4(%esp), %xmm0
+}
+
+define <2 x double> @test11(double %a, double %b) nounwind {
+	%tmp = insertelement <2 x double> undef, double %a, i32 0		; <<2 x double>> [#uses=1]
+	%tmp7 = insertelement <2 x double> %tmp, double %b, i32 1		; <<2 x double>> [#uses=1]
+	ret <2 x double> %tmp7
+; CHECK: test11:
+; CHECK: movapd	4(%esp), %xmm0
+}
+
+define void @test12() nounwind {
+        %tmp1 = load <4 x float>* null          ; <<4 x float>> [#uses=2]
+        %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> < float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00 >, <4 x i32> < i32 0, i32 1, i32 6, i32 7 >             ; <<4 x float>> [#uses=1]
+        %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 2, i32 3, i32 6, i32 7 >                ; <<4 x float>> [#uses=1]
+        %tmp4 = fadd <4 x float> %tmp2, %tmp3            ; <<4 x float>> [#uses=1]
+        store <4 x float> %tmp4, <4 x float>* null
+        ret void
+; CHECK: test12:
+; CHECK: movhlps
+; CHECK: shufps
+}
+
+define void @test13(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
+        %tmp3 = load <4 x float>* %B            ; <<4 x float>> [#uses=1]
+        %tmp5 = load <4 x float>* %C            ; <<4 x float>> [#uses=1]
+        %tmp11 = shufflevector <4 x float> %tmp3, <4 x float> %tmp5, <4 x i32> < i32 1, i32 4, i32 1, i32 5 >         ; <<4 x float>> [#uses=1]
+        store <4 x float> %tmp11, <4 x float>* %res
+        ret void
+; CHECK: test13
+; CHECK: shufps	$69, (%eax), %xmm0
+; CHECK: pshufd	$-40, %xmm0, %xmm0
+}
+
+define <4 x float> @test14(<4 x float>* %x, <4 x float>* %y) nounwind {
+        %tmp = load <4 x float>* %y             ; <<4 x float>> [#uses=2]
+        %tmp5 = load <4 x float>* %x            ; <<4 x float>> [#uses=2]
+        %tmp9 = fadd <4 x float> %tmp5, %tmp             ; <<4 x float>> [#uses=1]
+        %tmp21 = fsub <4 x float> %tmp5, %tmp            ; <<4 x float>> [#uses=1]
+        %tmp27 = shufflevector <4 x float> %tmp9, <4 x float> %tmp21, <4 x i32> < i32 0, i32 1, i32 4, i32 5 >                ; <<4 x float>> [#uses=1]
+        ret <4 x float> %tmp27
+; CHECK: test14:
+; CHECK: 	addps	%xmm1, %xmm0
+; CHECK: 	subps	%xmm1, %xmm2
+; CHECK: 	movlhps	%xmm2, %xmm0
+}
+
+define <4 x float> @test15(<4 x float>* %x, <4 x float>* %y) nounwind {
+entry:
+        %tmp = load <4 x float>* %y             ; <<4 x float>> [#uses=1]
+        %tmp3 = load <4 x float>* %x            ; <<4 x float>> [#uses=1]
+        %tmp4 = shufflevector <4 x float> %tmp3, <4 x float> %tmp, <4 x i32> < i32 2, i32 3, i32 6, i32 7 >           ; <<4 x float>> [#uses=1]
+        ret <4 x float> %tmp4
+; CHECK: test15:
+; CHECK: 	movhlps	%xmm1, %xmm0
+}
diff --git a/test/CodeGen/X86/vec_shuffle-10.ll b/test/CodeGen/X86/vec_shuffle-10.ll
deleted file mode 100644
index 6efe6e0581..0000000000
--- a/test/CodeGen/X86/vec_shuffle-10.ll
+++ /dev/null
@@ -1,25 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep unpcklps %t | count 1
-; RUN: grep pshufd   %t | count 1
-; RUN: not grep {sub.*esp} %t
-
-define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B) nounwind {
-	%tmp = load <4 x float>* %B		; <<4 x float>> [#uses=2]
-	%tmp3 = load <4 x float>* %A		; <<4 x float>> [#uses=2]
-	%tmp.upgrd.1 = extractelement <4 x float> %tmp3, i32 0		; <float> [#uses=1]
-	%tmp7 = extractelement <4 x float> %tmp, i32 0		; <float> [#uses=1]
-	%tmp8 = extractelement <4 x float> %tmp3, i32 1		; <float> [#uses=1]
-	%tmp9 = extractelement <4 x float> %tmp, i32 1		; <float> [#uses=1]
-	%tmp10 = insertelement <4 x float> undef, float %tmp.upgrd.1, i32 0		; <<4 x float>> [#uses=1]
-	%tmp11 = insertelement <4 x float> %tmp10, float %tmp7, i32 1		; <<4 x float>> [#uses=1]
-	%tmp12 = insertelement <4 x float> %tmp11, float %tmp8, i32 2		; <<4 x float>> [#uses=1]
-	%tmp13 = insertelement <4 x float> %tmp12, float %tmp9, i32 3		; <<4 x float>> [#uses=1]
-	store <4 x float> %tmp13, <4 x float>* %res
-	ret void
-}
-
-define void @test2(<4 x float> %X, <4 x float>* %res) nounwind {
-	%tmp5 = shufflevector <4 x float> %X, <4 x float> undef, <4 x i32> < i32 2, i32 6, i32 3, i32 7 >		; <<4 x float>> [#uses=1]
-	store <4 x float> %tmp5, <4 x float>* %res
-	ret void
-}
diff --git a/test/CodeGen/X86/vec_shuffle-3.ll b/test/CodeGen/X86/vec_shuffle-3.ll
deleted file mode 100644
index f313f3ed14..0000000000
--- a/test/CodeGen/X86/vec_shuffle-3.ll
+++ /dev/null
@@ -1,20 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep movlhps %t | count 1
-; RUN: grep movhlps %t | count 1
-
-define <4 x float> @test1(<4 x float>* %x, <4 x float>* %y) nounwind {
-        %tmp = load <4 x float>* %y             ; <<4 x float>> [#uses=2]
-        %tmp5 = load <4 x float>* %x            ; <<4 x float>> [#uses=2]
-        %tmp9 = fadd <4 x float> %tmp5, %tmp             ; <<4 x float>> [#uses=1]
-        %tmp21 = fsub <4 x float> %tmp5, %tmp            ; <<4 x float>> [#uses=1]
-        %tmp27 = shufflevector <4 x float> %tmp9, <4 x float> %tmp21, <4 x i32> < i32 0, i32 1, i32 4, i32 5 >                ; <<4 x float>> [#uses=1]
-        ret <4 x float> %tmp27
-}
-
-define <4 x float> @movhl(<4 x float>* %x, <4 x float>* %y) nounwind {
-entry:
-        %tmp = load <4 x float>* %y             ; <<4 x float>> [#uses=1]
-        %tmp3 = load <4 x float>* %x            ; <<4 x float>> [#uses=1]
-        %tmp4 = shufflevector <4 x float> %tmp3, <4 x float> %tmp, <4 x i32> < i32 2, i32 3, i32 6, i32 7 >           ; <<4 x float>> [#uses=1]
-        ret <4 x float> %tmp4
-}
diff --git a/test/CodeGen/X86/vec_shuffle-4.ll b/test/CodeGen/X86/vec_shuffle-4.ll
deleted file mode 100644
index 722f4b0334..0000000000
--- a/test/CodeGen/X86/vec_shuffle-4.ll
+++ /dev/null
@@ -1,12 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 > %t
-; RUN: grep shuf %t | count 2
-; RUN: not grep unpck %t
-
-define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
-        %tmp3 = load <4 x float>* %B            ; <<4 x float>> [#uses=1]
-        %tmp5 = load <4 x float>* %C            ; <<4 x float>> [#uses=1]
-        %tmp11 = shufflevector <4 x float> %tmp3, <4 x float> %tmp5, <4 x i32> < i32 1, i32 4, i32 1, i32 5 >         ; <<4 x float>> [#uses=1]
-        store <4 x float> %tmp11, <4 x float>* %res
-        ret void
-}
-
diff --git a/test/CodeGen/X86/vec_shuffle-5.ll b/test/CodeGen/X86/vec_shuffle-5.ll
deleted file mode 100644
index c24167a615..0000000000
--- a/test/CodeGen/X86/vec_shuffle-5.ll
+++ /dev/null
@@ -1,13 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep movhlps %t | count 1
-; RUN: grep shufps  %t | count 1
-
-define void @test() nounwind {
-        %tmp1 = load <4 x float>* null          ; <<4 x float>> [#uses=2]
-        %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> < float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00 >, <4 x i32> < i32 0, i32 1, i32 6, i32 7 >             ; <<4 x float>> [#uses=1]
-        %tmp3 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 2, i32 3, i32 6, i32 7 >                ; <<4 x float>> [#uses=1]
-        %tmp4 = fadd <4 x float> %tmp2, %tmp3            ; <<4 x float>> [#uses=1]
-        store <4 x float> %tmp4, <4 x float>* null
-        ret void
-}
-
diff --git a/test/CodeGen/X86/vec_shuffle-6.ll b/test/CodeGen/X86/vec_shuffle-6.ll
deleted file mode 100644
index e035a96aeb..0000000000
--- a/test/CodeGen/X86/vec_shuffle-6.ll
+++ /dev/null
@@ -1,42 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep movapd %t | count 1
-; RUN: grep movaps %t | count 1
-; RUN: grep movups %t | count 2
-
-target triple = "i686-apple-darwin"
-@x = external global [4 x i32]
-
-define <2 x i64> @test1() nounwind {
-	%tmp = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 0)		; <i32> [#uses=1]
-	%tmp3 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 1)		; <i32> [#uses=1]
-	%tmp5 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 2)		; <i32> [#uses=1]
-	%tmp7 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 3)		; <i32> [#uses=1]
-	%tmp.upgrd.1 = insertelement <4 x i32> undef, i32 %tmp, i32 0		; <<4 x i32>> [#uses=1]
-	%tmp13 = insertelement <4 x i32> %tmp.upgrd.1, i32 %tmp3, i32 1		; <<4 x i32>> [#uses=1]
-	%tmp14 = insertelement <4 x i32> %tmp13, i32 %tmp5, i32 2		; <<4 x i32>> [#uses=1]
-	%tmp15 = insertelement <4 x i32> %tmp14, i32 %tmp7, i32 3		; <<4 x i32>> [#uses=1]
-	%tmp16 = bitcast <4 x i32> %tmp15 to <2 x i64>		; <<2 x i64>> [#uses=1]
-	ret <2 x i64> %tmp16
-}
-
-define <4 x float> @test2(i32 %dummy, float %a, float %b, float %c, float %d) nounwind {
-	%tmp = insertelement <4 x float> undef, float %a, i32 0		; <<4 x float>> [#uses=1]
-	%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1		; <<4 x float>> [#uses=1]
-	%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2		; <<4 x float>> [#uses=1]
-	%tmp13 = insertelement <4 x float> %tmp12, float %d, i32 3		; <<4 x float>> [#uses=1]
-	ret <4 x float> %tmp13
-}
-
-define <4 x float> @test3(float %a, float %b, float %c, float %d) nounwind {
-	%tmp = insertelement <4 x float> undef, float %a, i32 0		; <<4 x float>> [#uses=1]
-	%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1		; <<4 x float>> [#uses=1]
-	%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2		; <<4 x float>> [#uses=1]
-	%tmp13 = insertelement <4 x float> %tmp12, float %d, i32 3		; <<4 x float>> [#uses=1]
-	ret <4 x float> %tmp13
-}
-
-define <2 x double> @test4(double %a, double %b) nounwind {
-	%tmp = insertelement <2 x double> undef, double %a, i32 0		; <<2 x double>> [#uses=1]
-	%tmp7 = insertelement <2 x double> %tmp, double %b, i32 1		; <<2 x double>> [#uses=1]
-	ret <2 x double> %tmp7
-}
diff --git a/test/CodeGen/X86/vec_shuffle-7.ll b/test/CodeGen/X86/vec_shuffle-7.ll
deleted file mode 100644
index a68f3747b5..0000000000
--- a/test/CodeGen/X86/vec_shuffle-7.ll
+++ /dev/null
@@ -1,11 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep pxor %t | count 1
-; RUN: not grep shufps %t
-
-define void @test() nounwind {
-        bitcast <4 x i32> zeroinitializer to <4 x float>                ; <<4 x float>>:1 [#uses=1]
-        shufflevector <4 x float> %1, <4 x float> zeroinitializer, <4 x i32> zeroinitializer         ; <<4 x float>>:2 [#uses=1]
-        store <4 x float> %2, <4 x float>* null
-        ret void
-}
-
diff --git a/test/CodeGen/X86/vec_shuffle-8.ll b/test/CodeGen/X86/vec_shuffle-8.ll
deleted file mode 100644
index 7e8371f8ab..0000000000
--- a/test/CodeGen/X86/vec_shuffle-8.ll
+++ /dev/null
@@ -1,10 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 | \
-; RUN:   not grep shufps
-
-define void @test(<4 x float>* %res, <4 x float>* %A) nounwind {
-        %tmp1 = load <4 x float>* %A            ; <<4 x float>> [#uses=1]
-        %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> < i32 0, i32 5, i32 6, i32 7 >          ; <<4 x float>> [#uses=1]
-        store <4 x float> %tmp2, <4 x float>* %res
-        ret void
-}
-
diff --git a/test/CodeGen/X86/vec_shuffle-9.ll b/test/CodeGen/X86/vec_shuffle-9.ll
deleted file mode 100644
index 016c20c6f7..0000000000
--- a/test/CodeGen/X86/vec_shuffle-9.ll
+++ /dev/null
@@ -1,21 +0,0 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
-
-define <4 x i32> @test(i8** %ptr) nounwind {
-; CHECK: pxor
-; CHECK: punpcklbw
-; CHECK: punpcklwd
-
-	%tmp = load i8** %ptr		; <i8*> [#uses=1]
-	%tmp.upgrd.1 = bitcast i8* %tmp to float*		; <float*> [#uses=1]
-	%tmp.upgrd.2 = load float* %tmp.upgrd.1		; <float> [#uses=1]
-	%tmp.upgrd.3 = insertelement <4 x float> undef, float %tmp.upgrd.2, i32 0		; <<4 x float>> [#uses=1]
-	%tmp9 = insertelement <4 x float> %tmp.upgrd.3, float 0.000000e+00, i32 1		; <<4 x float>> [#uses=1]
-	%tmp10 = insertelement <4 x float> %tmp9, float 0.000000e+00, i32 2		; <<4 x float>> [#uses=1]
-	%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 3		; <<4 x float>> [#uses=1]
-	%tmp21 = bitcast <4 x float> %tmp11 to <16 x i8>		; <<16 x i8>> [#uses=1]
-	%tmp22 = shufflevector <16 x i8> %tmp21, <16 x i8> zeroinitializer, <16 x i32> < i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23 >		; <<16 x i8>> [#uses=1]
-	%tmp31 = bitcast <16 x i8> %tmp22 to <8 x i16>		; <<8 x i16>> [#uses=1]
-	%tmp.upgrd.4 = shufflevector <8 x i16> zeroinitializer, <8 x i16> %tmp31, <8 x i32> < i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11 >		; <<8 x i16>> [#uses=1]
-	%tmp36 = bitcast <8 x i16> %tmp.upgrd.4 to <4 x i32>		; <<4 x i32>> [#uses=1]
-	ret <4 x i32> %tmp36
-}