3 files changed, 70 insertions, 15 deletions
diff --git a/test/CodeGen/X86/palignr.ll b/test/CodeGen/X86/palignr.ll
new file mode 100644
index 0000000..3812c72
--- /dev/null
+++ b/test/CodeGen/X86/palignr.ll
@@ -0,0 +1,58 @@
+; RUN: llc < %s -march=x86 -mcpu=core2 | FileCheck %s
+; RUN: llc < %s -march=x86 -mcpu=yonah | FileCheck --check-prefix=YONAH %s
+
+define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK: pshufd
+; CHECK-YONAH: pshufd
+  %C = shufflevector <4 x i32> %A, <4 x i32> undef, <4 x i32> < i32 1, i32 2, i32 3, i32 0 >
+	ret <4 x i32> %C
+}
+
+define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK: palignr
+; CHECK-YONAH: shufps
+  %C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 1, i32 2, i32 3, i32 4 >
+	ret <4 x i32> %C
+}
+
+define <4 x i32> @test3(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 1, i32 2, i32 undef, i32 4 >
+	ret <4 x i32> %C
+}
+
+define <4 x i32> @test4(<4 x i32> %A, <4 x i32> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 6, i32 7, i32 undef, i32 1 >
+	ret <4 x i32> %C
+}
+
+define <4 x float> @test5(<4 x float> %A, <4 x float> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> < i32 6, i32 7, i32 undef, i32 1 >
+	ret <4 x float> %C
+}
+
+define <8 x i16> @test6(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 3, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10 >
+	ret <8 x i16> %C
+}
+
+define <8 x i16> @test7(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 undef, i32 6, i32 undef, i32 8, i32 9, i32 10, i32 11, i32 12 >
+	ret <8 x i16> %C
+}
+
+define <8 x i16> @test8(<8 x i16> %A, <8 x i16> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 undef, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0 >
+	ret <8 x i16> %C
+}
+
+define <16 x i8> @test9(<16 x i8> %A, <16 x i8> %B) nounwind {
+; CHECK: palignr
+  %C = shufflevector <16 x i8> %A, <16 x i8> %B, <16 x i32> < i32 5, i32 6, i32 7, i32 undef, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20 >
+	ret <16 x i8> %C
+}
diff --git a/test/CodeGen/X86/vec_shuffle-22.ll b/test/CodeGen/X86/vec_shuffle-22.ll
index 5307ced..1cf37d4 100644
--- a/test/CodeGen/X86/vec_shuffle-22.ll
+++ b/test/CodeGen/X86/vec_shuffle-22.ll
@@ -1,19 +1,15 @@
-; RUN: llc < %s -march=x86 -mcpu=pentium-m -o %t
-; RUN: grep movlhps %t | count 1
-; RUN: grep pshufd %t | count 1
-; RUN: llc < %s -march=x86 -mcpu=core2 -o %t
-; RUN: grep movlhps %t | count 1
-; RUN: grep movddup %t | count 1
+; RUN: llc < %s -march=x86 -mcpu=pentium-m  | FileCheck %s
 
 define <4 x float> @t1(<4 x float> %a) nounwind  {
-entry:
-        %tmp1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> < i32 0, i32 1, i32 0, i32 1 >       ; <<4 x float>> [#uses=1]
-        ret <4 x float> %tmp1
+; CHECK: movlhps
+  %tmp1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> < i32 0, i32 1, i32 0, i32 1 >       ; <<4 x float>> [#uses=1]
+  ret <4 x float> %tmp1
 }
 
 define <4 x i32> @t2(<4 x i32>* %a) nounwind {
-entry:
-        %tmp1 = load <4 x i32>* %a;
+; CHECK: pshufd
+; CHECK: ret
+  %tmp1 = load <4 x i32>* %a;
 	%tmp2 = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> < i32 0, i32 1, i32 0, i32 1 >		; <<4 x i32>> [#uses=1]
 	ret <4 x i32> %tmp2
 }
diff --git a/test/CodeGen/X86/vec_shuffle-9.ll b/test/CodeGen/X86/vec_shuffle-9.ll
index 2bef24d..fc16a26 100644
--- a/test/CodeGen/X86/vec_shuffle-9.ll
+++ b/test/CodeGen/X86/vec_shuffle-9.ll
@@ -1,9 +1,10 @@
-; RUN: llc < %s -march=x86 -mattr=+sse2 -o %t
-; RUN: grep punpck %t | count 2
-; RUN: not grep pextrw %t
+; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
 
 define <4 x i32> @test(i8** %ptr) {
-entry:
+; CHECK: xorps
+; 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]