-; 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
+; RUN: llc < %s -mtriple=x86_64-linux -mcpu=core2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=core2 | FileCheck %s
+; RUN: llc -O0 < %s -march=x86 -mcpu=core2 | FileCheck %s --check-prefix=CHECK_O0
-; Test yonah where we convert a shuffle to pextrw and pinrsw
-define <16 x i8> @shuf1(<16 x i8> %T0) nounwind readnone {
+define <4 x i32> @t00(<4 x i32>* %a0) nounwind ssp {
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
+; CHECK: movaps ({{%rdi|%rcx}}), %[[XMM0:xmm[0-9]+]]
+; CHECK: movaps %[[XMM0]], %[[XMM1:xmm[0-9]+]]
+; CHECK-NEXT: movss %xmm{{[0-9]+}}, %[[XMM1]]
+; CHECK-NEXT: shufps $36, %[[XMM1]], %[[XMM0]]
+ %0 = load <4 x i32>* undef, align 16
+ %1 = load <4 x i32>* %a0, align 16
+ %2 = shufflevector <4 x i32> %1, <4 x i32> %0, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
+ ret <4 x i32> %2
}
+define void @t01(double* %a0) nounwind ssp {
+entry:
+; CHECK_O0: movsd (%eax), %xmm0
+; CHECK_O0: unpcklpd %xmm0, %xmm0
+ %tmp93 = load double* %a0, align 8
+ %vecinit94 = insertelement <2 x double> undef, double %tmp93, i32 1
+ store <2 x double> %vecinit94, <2 x double>* undef
+ ret void
+}
+
+define void @t02(<8 x i32>* %source, <2 x i32>* %dest) nounwind noinline {
+entry:
+; CHECK: t02
+; CHECK: movaps
+; CHECK: shufps
+; CHECK: pshufd
+; CHECK: movq
+; CHECK: ret
+ %0 = bitcast <8 x i32>* %source to <4 x i32>*
+ %arrayidx = getelementptr inbounds <4 x i32>* %0, i64 3
+ %tmp2 = load <4 x i32>* %arrayidx, align 16
+ %tmp3 = extractelement <4 x i32> %tmp2, i32 0
+ %tmp5 = insertelement <2 x i32> <i32 undef, i32 0>, i32 %tmp3, i32 0
+ %arrayidx7 = getelementptr inbounds <8 x i32>* %source, i64 1
+ %1 = bitcast <8 x i32>* %arrayidx7 to <4 x i32>*
+ %tmp8 = load <4 x i32>* %1, align 16
+ %tmp9 = extractelement <4 x i32> %tmp8, i32 1
+ %tmp11 = insertelement <2 x i32> %tmp5, i32 %tmp9, i32 1
+ store <2 x i32> %tmp11, <2 x i32>* %dest, align 8
+ ret void
+}