merge a bunch more sse3 tests into sse3.ll

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79115 91177308-0d34-0410-b5e6-96231b3b80d8

11 files changed, 252 insertions, 174 deletions

diff --git a/test/CodeGen/X86/sse3.ll b/test/CodeGen/X86/sse3.ll
index 5e7908c..013bdbb 100644
--- a/test/CodeGen/X86/sse3.ll
+++ b/test/CodeGen/X86/sse3.ll
@@ -5,7 +5,7 @@
 ; Test for v8xi16 lowering where we extract the first element of the vector and
 ; placed it in the second element of the result.
 
-define void @shuf1(<8 x i16>* %dest, <8 x i16>* %old) nounwind {
+define void @t0(<8 x i16>* %dest, <8 x i16>* %old) nounwind {
 entry:
 	%tmp3 = load <8 x i16>* %old
 	%tmp6 = shufflevector <8 x i16> %tmp3,
@@ -14,11 +14,259 @@ entry:
 	store <8 x i16> %tmp6, <8 x i16>* %dest
 	ret void
         
-; X64: shuf1:
+; X64: t0:
 ; X64: 	movddup	(%rsi), %xmm0
 ; X64:  pshuflw	$0, %xmm0, %xmm0
 ; X64:	xorl	%eax, %eax
 ; X64:	pinsrw	$0, %eax, %xmm0
 ; X64:	movaps	%xmm0, (%rdi)
 ; X64:	ret
-}
\ No newline at end of file
+}
+
+define <8 x i16> @t1(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+	%tmp1 = load <8 x i16>* %A
+	%tmp2 = load <8 x i16>* %B
+	%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> < i32 8, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >
+	ret <8 x i16> %tmp3
+        
+; X64: t1:
+; X64: 	movl	(%rsi), %eax
+; X64: 	movaps	(%rdi), %xmm0
+; X64: 	pinsrw	$0, %eax, %xmm0
+; X64: 	ret
+}
+
+define <8 x i16> @t2(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 9, i32 1, i32 2, i32 9, i32 4, i32 5, i32 6, i32 7 >
+	ret <8 x i16> %tmp
+; X64: t2:
+; X64:	pextrw	$1, %xmm1, %eax
+; X64:	pinsrw	$0, %eax, %xmm0
+; X64:	pinsrw	$3, %eax, %xmm0
+; X64:	ret
+}
+
+define <8 x i16> @t3(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %A, <8 x i32> < i32 8, i32 3, i32 2, i32 13, i32 7, i32 6, i32 5, i32 4 >
+	ret <8 x i16> %tmp
+; X64: t3:
+; X64: 	pextrw	$5, %xmm0, %eax
+; X64: 	pshuflw	$44, %xmm0, %xmm0
+; X64: 	pshufhw	$27, %xmm0, %xmm0
+; X64: 	pinsrw	$3, %eax, %xmm0
+; X64: 	ret
+}
+
+define <8 x i16> @t4(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 0, i32 7, i32 2, i32 3, i32 1, i32 5, i32 6, i32 5 >
+	ret <8 x i16> %tmp
+; X64: t4:
+; X64: 	pextrw	$7, %xmm0, %eax
+; X64: 	pshufhw	$100, %xmm0, %xmm1
+; X64: 	pinsrw	$1, %eax, %xmm1
+; X64: 	pextrw	$1, %xmm0, %eax
+; X64: 	movaps	%xmm1, %xmm0
+; X64: 	pinsrw	$4, %eax, %xmm0
+; X64: 	ret
+}
+
+define <8 x i16> @t5(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 0, i32 1, i32 10, i32 11, i32 2, i32 3 >
+	ret <8 x i16> %tmp
+; X64: 	t5:
+; X64: 		movlhps	%xmm1, %xmm0
+; X64: 		pshufd	$114, %xmm0, %xmm0
+; X64: 		ret
+}
+
+define <8 x i16> @t6(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >
+	ret <8 x i16> %tmp
+; X64: 	t6:
+; X64: 		movss	%xmm1, %xmm0
+; X64: 		ret
+}
+
+define <8 x i16> @t7(<8 x i16> %A, <8 x i16> %B) nounwind {
+	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 0, i32 0, i32 3, i32 2, i32 4, i32 6, i32 4, i32 7 >
+	ret <8 x i16> %tmp
+; X64: 	t7:
+; X64: 		pshuflw	$176, %xmm0, %xmm0
+; X64: 		pshufhw	$200, %xmm0, %xmm0
+; X64: 		ret
+}
+
+define void @t8(<2 x i64>* %res, <2 x i64>* %A) nounwind {
+	%tmp = load <2 x i64>* %A
+	%tmp.upgrd.1 = bitcast <2 x i64> %tmp to <8 x i16>
+	%tmp0 = extractelement <8 x i16> %tmp.upgrd.1, i32 0
+	%tmp1 = extractelement <8 x i16> %tmp.upgrd.1, i32 1
+	%tmp2 = extractelement <8 x i16> %tmp.upgrd.1, i32 2
+	%tmp3 = extractelement <8 x i16> %tmp.upgrd.1, i32 3
+	%tmp4 = extractelement <8 x i16> %tmp.upgrd.1, i32 4
+	%tmp5 = extractelement <8 x i16> %tmp.upgrd.1, i32 5
+	%tmp6 = extractelement <8 x i16> %tmp.upgrd.1, i32 6
+	%tmp7 = extractelement <8 x i16> %tmp.upgrd.1, i32 7
+	%tmp8 = insertelement <8 x i16> undef, i16 %tmp2, i32 0
+	%tmp9 = insertelement <8 x i16> %tmp8, i16 %tmp1, i32 1
+	%tmp10 = insertelement <8 x i16> %tmp9, i16 %tmp0, i32 2
+	%tmp11 = insertelement <8 x i16> %tmp10, i16 %tmp3, i32 3
+	%tmp12 = insertelement <8 x i16> %tmp11, i16 %tmp6, i32 4
+	%tmp13 = insertelement <8 x i16> %tmp12, i16 %tmp5, i32 5
+	%tmp14 = insertelement <8 x i16> %tmp13, i16 %tmp4, i32 6
+	%tmp15 = insertelement <8 x i16> %tmp14, i16 %tmp7, i32 7
+	%tmp15.upgrd.2 = bitcast <8 x i16> %tmp15 to <2 x i64>
+	store <2 x i64> %tmp15.upgrd.2, <2 x i64>* %res
+	ret void
+; X64: 	t8:
+; X64: 		pshuflw	$198, (%rsi), %xmm0
+; X64: 		pshufhw	$198, %xmm0, %xmm0
+; X64: 		movaps	%xmm0, (%rdi)
+; X64: 		ret
+}
+
+define void @t9(<4 x float>* %r, <2 x i32>* %A) nounwind {
+	%tmp = load <4 x float>* %r
+	%tmp.upgrd.3 = bitcast <2 x i32>* %A to double*
+	%tmp.upgrd.4 = load double* %tmp.upgrd.3
+	%tmp.upgrd.5 = insertelement <2 x double> undef, double %tmp.upgrd.4, i32 0
+	%tmp5 = insertelement <2 x double> %tmp.upgrd.5, double undef, i32 1	
+	%tmp6 = bitcast <2 x double> %tmp5 to <4 x float>	
+	%tmp.upgrd.6 = extractelement <4 x float> %tmp, i32 0	
+	%tmp7 = extractelement <4 x float> %tmp, i32 1		
+	%tmp8 = extractelement <4 x float> %tmp6, i32 0		
+	%tmp9 = extractelement <4 x float> %tmp6, i32 1		
+	%tmp10 = insertelement <4 x float> undef, float %tmp.upgrd.6, i32 0	
+	%tmp11 = insertelement <4 x float> %tmp10, float %tmp7, i32 1
+	%tmp12 = insertelement <4 x float> %tmp11, float %tmp8, i32 2
+	%tmp13 = insertelement <4 x float> %tmp12, float %tmp9, i32 3
+	store <4 x float> %tmp13, <4 x float>* %r
+	ret void
+; X64: 	t9:
+; X64: 		movsd	(%rsi), %xmm0
+; X64: 		movhps	%xmm0, (%rdi)
+; X64: 		ret
+}
+
+
+
+; FIXME: This testcase produces icky code. It can be made much better!
+; PR2585
+
+@g1 = external constant <4 x i32>
+@g2 = external constant <4 x i16>
+
+define internal void @t10() nounwind {
+        load <4 x i32>* @g1, align 16 
+        bitcast <4 x i32> %1 to <8 x i16>
+        shufflevector <8 x i16> %2, <8 x i16> undef, <8 x i32> < i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef >
+        bitcast <8 x i16> %3 to <2 x i64>  
+        extractelement <2 x i64> %4, i32 0 
+        bitcast i64 %5 to <4 x i16>        
+        store <4 x i16> %6, <4 x i16>* @g2, align 8
+        ret void
+; X64: 	t10:
+; X64: 		movq	_g1@GOTPCREL(%rip), %rax
+; X64: 		movaps	(%rax), %xmm0
+; X64: 		pextrw	$4, %xmm0, %eax
+; X64: 		movaps	%xmm0, %xmm1
+; X64: 		movlhps	%xmm1, %xmm1
+; X64: 		pshuflw	$8, %xmm1, %xmm1
+; X64: 		pinsrw	$2, %eax, %xmm1
+; X64: 		pextrw	$6, %xmm0, %eax
+; X64: 		pinsrw	$3, %eax, %xmm1
+; X64: 		movq	_g2@GOTPCREL(%rip), %rax
+; X64: 		movq	%xmm1, (%rax)
+; X64: 		ret
+}
+
+
+; Pack various elements via shuffles.
+define <8 x i16> @t11(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
+entry:
+	%tmp7 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 1, i32 8, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef , i32 undef >
+	ret <8 x i16> %tmp7
+
+; X64: t11:
+; X64:	movd	%xmm1, %eax
+; X64:	movlhps	%xmm0, %xmm0
+; X64:	pshuflw	$1, %xmm0, %xmm0
+; X64:	pinsrw	$1, %eax, %xmm0
+; X64:	ret
+}
+
+
+define <8 x i16> @t12(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
+entry:
+	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 0, i32 1, i32 undef, i32 undef, i32 3, i32 11, i32 undef , i32 undef >
+	ret <8 x i16> %tmp9
+
+; X64: t12:
+; X64: 	pextrw	$3, %xmm1, %eax
+; X64: 	movlhps	%xmm0, %xmm0
+; X64: 	pshufhw	$3, %xmm0, %xmm0
+; X64: 	pinsrw	$5, %eax, %xmm0
+; X64: 	ret
+}
+
+
+define <8 x i16> @t13(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
+entry:
+	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 11, i32 3, i32 undef , i32 undef >
+	ret <8 x i16> %tmp9
+; X64: t13:
+; X64: 	punpcklqdq	%xmm0, %xmm1
+; X64: 	pextrw	$3, %xmm1, %eax
+; X64: 	pshufd	$52, %xmm1, %xmm0
+; X64: 	pinsrw	$4, %eax, %xmm0
+; X64: 	ret
+}
+
+
+define <8 x i16> @t14(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
+entry:
+	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 2, i32 undef , i32 undef >
+	ret <8 x i16> %tmp9
+; X64: t14:
+; X64: 	punpcklqdq	%xmm0, %xmm1
+; X64: 	pshufhw	$8, %xmm1, %xmm0
+; X64: 	ret
+}
+
+
+
+define <8 x i16> @t15(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
+entry:
+        %tmp8 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 undef, i32 undef, i32 7, i32 2, i32 8, i32 undef, i32 undef , i32 undef >
+        ret <8 x i16> %tmp8
+; X64: 	t15:
+; X64: 		pextrw	$7, %xmm0, %eax
+; X64: 		punpcklqdq	%xmm1, %xmm0
+; X64: 		pshuflw	$128, %xmm0, %xmm0
+; X64: 		pinsrw	$2, %eax, %xmm0
+; X64: 		ret
+}
+
+
+; Test yonah where we convert a shuffle to pextrw and pinrsw
+define <16 x i8> @t16(<16 x i8> %T0) nounwind readnone {
+entry:
+        %tmp8 = shufflevector <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 1, i8 1, i8 1, i8 1, i8 0, i8 0, i8 0, i8 0,  i8 0, i8 0, i8 0, i8 0>, <16 x i8> %T0, <16 x i32> < i32 0, i32 1, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef , i32 undef >
+        %tmp9 = shufflevector <16 x i8> %tmp8, <16 x i8> %T0,  <16 x i32> < i32 0, i32 1, i32 2, i32 17,  i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef , i32 undef >
+        ret <16 x i8> %tmp9
+; X64: 	t16:
+; X64: 		movaps	LCPI17_0(%rip), %xmm1
+; X64: 		movd	%xmm1, %eax
+; X64: 		pinsrw	$0, %eax, %xmm1
+; X64: 		pextrw	$8, %xmm0, %eax
+; X64: 		pinsrw	$1, %eax, %xmm1
+; X64: 		pextrw	$1, %xmm1, %ecx
+; X64: 		movd	%xmm1, %edx
+; X64: 		pinsrw	$0, %edx, %xmm1
+; X64: 		movzbl	%cl, %ecx
+; X64: 		andw	$65280, %ax
+; X64: 		orw	%cx, %ax
+; X64: 		movaps	%xmm1, %xmm0
+; X64: 		pinsrw	$1, %eax, %xmm0
+; X64: 		ret
+}
diff --git a/test/CodeGen/X86/vec_shuffle-12.ll b/test/CodeGen/X86/vec_shuffle-12.ll
deleted file mode 100644
index 98b455a..0000000
--- a/test/CodeGen/X86/vec_shuffle-12.ll
+++ /dev/null
@@ -1,28 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah > %t
-; RUN: not grep punpck %t
-; RUN: grep pextrw %t | count 4
-; RUN: grep pinsrw %t | count 6
-; RUN: grep pshuflw %t | count 1
-; RUN: grep pshufhw %t | count 2
-
-define <8 x i16> @t1(<8 x i16>* %A, <8 x i16>* %B) nounwind {
-	%tmp1 = load <8 x i16>* %A
-	%tmp2 = load <8 x i16>* %B
-	%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> < i32 8, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >
-	ret <8 x i16> %tmp3
-}
-
-define <8 x i16> @t2(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 9, i32 1, i32 2, i32 9, i32 4, i32 5, i32 6, i32 7 >
-	ret <8 x i16> %tmp
-}
-
-define <8 x i16> @t3(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %A, <8 x i32> < i32 8, i32 3, i32 2, i32 13, i32 7, i32 6, i32 5, i32 4 >
-	ret <8 x i16> %tmp
-}
-
-define <8 x i16> @t4(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 0, i32 7, i32 2, i32 3, i32 1, i32 5, i32 6, i32 5 >
-	ret <8 x i16> %tmp
-}
diff --git a/test/CodeGen/X86/vec_shuffle-13.ll b/test/CodeGen/X86/vec_shuffle-13.ll
deleted file mode 100644
index 61cd128..0000000
--- a/test/CodeGen/X86/vec_shuffle-13.ll
+++ /dev/null
@@ -1,21 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah > %t
-; RUN: grep movlhps %t | count 1
-; RUN: grep pshufd %t | count 1
-; RUN: grep movss %t | count 1
-; RUN: grep pshuflw %t | count 1
-; RUN: grep pshufhw %t | count 1
-
-define <8 x i16> @t1(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 0, i32 1, i32 10, i32 11, i32 2, i32 3 >
-	ret <8 x i16> %tmp
-}
-
-define <8 x i16> @t2(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 >
-	ret <8 x i16> %tmp
-}
-
-define <8 x i16> @t3(<8 x i16> %A, <8 x i16> %B) nounwind {
-	%tmp = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 0, i32 0, i32 3, i32 2, i32 4, i32 6, i32 4, i32 7 >
-	ret <8 x i16> %tmp
-}
diff --git a/test/CodeGen/X86/vec_shuffle-2.ll b/test/CodeGen/X86/vec_shuffle-2.ll
deleted file mode 100644
index b049565..0000000
--- a/test/CodeGen/X86/vec_shuffle-2.ll
+++ /dev/null
@@ -1,47 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep pshufhw %t | count 1
-; RUN: grep pshuflw %t | count 1
-; RUN: grep movhps  %t | count 1
-
-define void @test1(<2 x i64>* %res, <2 x i64>* %A) nounwind {
-	%tmp = load <2 x i64>* %A		; <<2 x i64>> [#uses=1]
-	%tmp.upgrd.1 = bitcast <2 x i64> %tmp to <8 x i16>		; <<8 x i16>> [#uses=8]
-	%tmp0 = extractelement <8 x i16> %tmp.upgrd.1, i32 0		; <i16> [#uses=1]
-	%tmp1 = extractelement <8 x i16> %tmp.upgrd.1, i32 1		; <i16> [#uses=1]
-	%tmp2 = extractelement <8 x i16> %tmp.upgrd.1, i32 2		; <i16> [#uses=1]
-	%tmp3 = extractelement <8 x i16> %tmp.upgrd.1, i32 3		; <i16> [#uses=1]
-	%tmp4 = extractelement <8 x i16> %tmp.upgrd.1, i32 4		; <i16> [#uses=1]
-	%tmp5 = extractelement <8 x i16> %tmp.upgrd.1, i32 5		; <i16> [#uses=1]
-	%tmp6 = extractelement <8 x i16> %tmp.upgrd.1, i32 6		; <i16> [#uses=1]
-	%tmp7 = extractelement <8 x i16> %tmp.upgrd.1, i32 7		; <i16> [#uses=1]
-	%tmp8 = insertelement <8 x i16> undef, i16 %tmp2, i32 0		; <<8 x i16>> [#uses=1]
-	%tmp9 = insertelement <8 x i16> %tmp8, i16 %tmp1, i32 1		; <<8 x i16>> [#uses=1]
-	%tmp10 = insertelement <8 x i16> %tmp9, i16 %tmp0, i32 2		; <<8 x i16>> [#uses=1]
-	%tmp11 = insertelement <8 x i16> %tmp10, i16 %tmp3, i32 3		; <<8 x i16>> [#uses=1]
-	%tmp12 = insertelement <8 x i16> %tmp11, i16 %tmp6, i32 4		; <<8 x i16>> [#uses=1]
-	%tmp13 = insertelement <8 x i16> %tmp12, i16 %tmp5, i32 5		; <<8 x i16>> [#uses=1]
-	%tmp14 = insertelement <8 x i16> %tmp13, i16 %tmp4, i32 6		; <<8 x i16>> [#uses=1]
-	%tmp15 = insertelement <8 x i16> %tmp14, i16 %tmp7, i32 7		; <<8 x i16>> [#uses=1]
-	%tmp15.upgrd.2 = bitcast <8 x i16> %tmp15 to <2 x i64>		; <<2 x i64>> [#uses=1]
-	store <2 x i64> %tmp15.upgrd.2, <2 x i64>* %res
-	ret void
-}
-
-define void @test2(<4 x float>* %r, <2 x i32>* %A) nounwind {
-	%tmp = load <4 x float>* %r		; <<4 x float>> [#uses=2]
-	%tmp.upgrd.3 = bitcast <2 x i32>* %A to double*		; <double*> [#uses=1]
-	%tmp.upgrd.4 = load double* %tmp.upgrd.3		; <double> [#uses=1]
-	%tmp.upgrd.5 = insertelement <2 x double> undef, double %tmp.upgrd.4, i32 0		; <<2 x double>> [#uses=1]
-	%tmp5 = insertelement <2 x double> %tmp.upgrd.5, double undef, i32 1		; <<2 x double>> [#uses=1]
-	%tmp6 = bitcast <2 x double> %tmp5 to <4 x float>		; <<4 x float>> [#uses=2]
-	%tmp.upgrd.6 = extractelement <4 x float> %tmp, i32 0		; <float> [#uses=1]
-	%tmp7 = extractelement <4 x float> %tmp, i32 1		; <float> [#uses=1]
-	%tmp8 = extractelement <4 x float> %tmp6, i32 0		; <float> [#uses=1]
-	%tmp9 = extractelement <4 x float> %tmp6, i32 1		; <float> [#uses=1]
-	%tmp10 = insertelement <4 x float> undef, float %tmp.upgrd.6, 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>* %r
-	ret void
-}
diff --git a/test/CodeGen/X86/vec_shuffle-21.ll b/test/CodeGen/X86/vec_shuffle-21.ll
deleted file mode 100644
index eec2691..0000000
--- a/test/CodeGen/X86/vec_shuffle-21.ll
+++ /dev/null
@@ -1,21 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep pshuflw %t | count 1
-; RUN: grep pextrw %t | count 2
-; RUN: grep pinsrw %t | count 2
-; PR2585
-
-; FIXME: This testcase produces icky code. It can be made much better!
-
-external constant <4 x i32>             ; <<4 x i32>*>:0 [#uses=1]
-external constant <4 x i16>             ; <<4 x i16>*>:1 [#uses=1]
-
-define internal void @""() {
-        load <4 x i32>* @0, align 16            ; <<4 x i32>>:1 [#uses=1]
-        bitcast <4 x i32> %1 to <8 x i16>               ; <<8 x i16>>:2[#uses=1]
-        shufflevector <8 x i16> %2, <8 x i16> undef, <8 x i32> < i32 0, i32 2, i32 4, i32 6, i32 undef, i32 undef, i32 undef, i32 undef >               ; <<8x i16>>:3 [#uses=1]
-        bitcast <8 x i16> %3 to <2 x i64>               ; <<2 x i64>>:4 [#uses=1]
-        extractelement <2 x i64> %4, i32 0              ; <i64>:5 [#uses=1]
-        bitcast i64 %5 to <4 x i16>             ; <<4 x i16>>:6 [#uses=1]
-        store <4 x i16> %6, <4 x i16>* @1, align 8
-        ret void
-}
diff --git a/test/CodeGen/X86/vec_shuffle-28.ll b/test/CodeGen/X86/vec_shuffle-28.ll
index f7e5001..fbd5bf5 100644
--- a/test/CodeGen/X86/vec_shuffle-28.ll
+++ b/test/CodeGen/X86/vec_shuffle-28.ll
@@ -1,7 +1,3 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep movd %t | count 1
-; RUN: grep pshuflw %t | count 1
-; RUN: grep pinsrw %t | count 1
 ; RUN: llvm-as < %s | llc -march=x86 -mcpu=core2 -o %t -f
 ; RUN: grep pshufb %t | count 1
 
diff --git a/test/CodeGen/X86/vec_shuffle-31.ll b/test/CodeGen/X86/vec_shuffle-31.ll
index efcd030..b57ea4e 100644
--- a/test/CodeGen/X86/vec_shuffle-31.ll
+++ b/test/CodeGen/X86/vec_shuffle-31.ll
@@ -1,8 +1,3 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep pextrw %t | count 1
-; RUN: grep movlhps %t | count 1
-; RUN: grep pshufhw %t | count 1
-; RUN: grep pinsrw %t | count 1
 ; RUN: llvm-as < %s | llc -march=x86 -mcpu=core2 -o %t -f
 ; RUN: grep pshufb %t | count 1
 
diff --git a/test/CodeGen/X86/vec_shuffle-32.ll b/test/CodeGen/X86/vec_shuffle-32.ll
deleted file mode 100644
index 3a81948..0000000
--- a/test/CodeGen/X86/vec_shuffle-32.ll
+++ /dev/null
@@ -1,13 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep punpcklqdq %t | count 1
-; RUN: grep pextrw %t | count 1
-; RUN: grep pshufd %t | count 1
-; RUN: grep pinsrw %t | count 1
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=core2 -o %t -f
-; RUN: grep pshufb %t | count 1
-
-define <8 x i16> @shuf4(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
-entry:
-	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 11, i32 3, i32 undef , i32 undef >
-	ret <8 x i16> %tmp9
-}
diff --git a/test/CodeGen/X86/vec_shuffle-33.ll b/test/CodeGen/X86/vec_shuffle-33.ll
deleted file mode 100644
index e3d6304..0000000
--- a/test/CodeGen/X86/vec_shuffle-33.ll
+++ /dev/null
@@ -1,11 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep punpcklqdq %t | count 1
-; RUN: grep pshufhw %t | count 1
-; RUN: not grep pextrw %t
-; RUN: not grep pinsrw %t
-
-define <8 x i16> @shuf5(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
-entry:
-	%tmp9 = shufflevector <8 x i16> %T0, <8 x i16> %T1, <8 x i32> < i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 2, i32 undef , i32 undef >
-	ret <8 x i16> %tmp9
-}
diff --git a/test/CodeGen/X86/vec_shuffle-34.ll b/test/CodeGen/X86/vec_shuffle-34.ll
index 99c95d1..6123602 100644
--- a/test/CodeGen/X86/vec_shuffle-34.ll
+++ b/test/CodeGen/X86/vec_shuffle-34.ll
@@ -1,10 +1,4 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -o %t -f
-; RUN: grep pextrw %t | count 1
-; RUN: grep punpcklqdq %t | count 1
-; RUN: grep pshuflw %t | count 1
-; RUN: grep pinsrw %t | count 1
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=core2 -o %t -f
-; RUN: grep pshufb %t | count 2
+; RUN: llvm-as < %s | llc -march=x86 -mcpu=core2 | grep pshufb | count 2
 
 define <8 x i16> @shuf2(<8 x i16> %T0, <8 x i16> %T1) nounwind readnone {
 entry:
diff --git a/test/CodeGen/X86/vec_shuffle-37.ll b/test/CodeGen/X86/vec_shuffle-37.ll
deleted file mode 100644
index d5f21f5..0000000
--- a/test/CodeGen/X86/vec_shuffle-37.ll
+++ /dev/null
@@ -1,14 +0,0 @@
-; RUN: llvm-as < %s | llc -march=x86 -mcpu=yonah -stack-alignment=16 -o %t -f
-; RUN: grep pextrw %t | count 2
-; RUN: grep pinsrw %t | count 4
-; RUN: grep orw %t | count 1
-; RUN: grep andw %t | count 1
-
-; Test yonah where we convert a shuffle to pextrw and pinrsw
-define <16 x i8> @shuf1(<16 x i8> %T0) nounwind readnone {
-entry:
-	%tmp8 = shufflevector <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 1, i8 1, i8 1, i8 1, i8 0, i8 0, i8 0, i8 0,  i8 0, i8 0, i8 0, i8 0>, <16 x i8> %T0, <16 x i32> < i32 0, i32 1, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef , i32 undef >
-	%tmp9 = shufflevector <16 x i8> %tmp8, <16 x i8> %T0,  <16 x i32> < i32 0, i32 1, i32 2, i32 17,  i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef , i32 undef >
-	ret <16 x i8> %tmp9
-}
-