Let the inline asm 'q' constraint match float, and on 64-bit double too.

[oota-llvm.git] / test / CodeGen / X86 / vec_shuffle-37.ll

diff --git a/test/CodeGen/X86/vec_shuffle-37.ll b/test/CodeGen/X86/vec_shuffle-37.ll
index d5f21f5f14597bd7d9839523e3f1dc3b645f6e07..2efdb14b4044683ae773fd0f179c6b659df0c7f0 100644 (file)
--- a/test/CodeGen/X86/vec_shuffle-37.ll
+++ b/test/CodeGen/X86/vec_shuffle-37.ll
@@ -1,14 +1,25 @@
-; 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 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-win32 | 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
+; CHECK-NEXT: movaps  %xmm0, %xmm1
+; CHECK-NEXT: movlps  (%rax), %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
+}