diff options
Diffstat (limited to 'test/CodeGen/X86/vec_cast2.ll')
| -rw-r--r-- | test/CodeGen/X86/vec_cast2.ll | 31 |
1 files changed, 17 insertions, 14 deletions
diff --git a/test/CodeGen/X86/vec_cast2.ll b/test/CodeGen/X86/vec_cast2.ll index 1ba11f51baa2b..dda50b7b94b7f 100644 --- a/test/CodeGen/X86/vec_cast2.ll +++ b/test/CodeGen/X86/vec_cast2.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py ; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=corei7-avx -mattr=+avx | FileCheck %s ; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=corei7-avx -mattr=+avx -x86-experimental-vector-widening-legalization | FileCheck %s --check-prefix=CHECK-WIDE @@ -46,17 +47,19 @@ define <4 x float> @foo1_4(<4 x i8> %src) { define <8 x float> @foo2_8(<8 x i8> %src) { ; CHECK-LABEL: foo2_8: ; CHECK: ## BB#0: -; CHECK-NEXT: vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero -; CHECK-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7] -; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 -; CHECK-NEXT: vandps LCPI2_0, %ymm0, %ymm0 +; CHECK-NEXT: vpand LCPI2_0, %xmm0, %xmm0 +; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1 +; CHECK-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] +; CHECK-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero +; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0 ; CHECK-NEXT: vcvtdq2ps %ymm0, %ymm0 ; CHECK-NEXT: retl ; ; CHECK-WIDE-LABEL: foo2_8: ; CHECK-WIDE: ## BB#0: ; CHECK-WIDE-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero -; CHECK-WIDE-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero +; CHECK-WIDE-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3] +; CHECK-WIDE-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero ; CHECK-WIDE-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0 ; CHECK-WIDE-NEXT: vcvtdq2ps %ymm0, %ymm0 ; CHECK-WIDE-NEXT: retl @@ -96,25 +99,25 @@ define <8 x i8> @foo3_8(<8 x float> %src) { ; CHECK-WIDE: ## BB#0: ; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %eax ; CHECK-WIDE-NEXT: vpinsrb $0, %eax, %xmm0, %xmm1 -; CHECK-WIDE-NEXT: vmovshdup %xmm0, %xmm2 ## xmm2 = xmm0[1,1,3,3] +; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilpd $1, %xmm0, %xmm2 ## xmm2 = xmm0[1,0] +; CHECK-WIDE-NEXT: vpermilpd {{.*#+}} xmm2 = xmm0[1,0] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilps $231, %xmm0, %xmm2 ## xmm2 = xmm0[3,1,2,3] +; CHECK-WIDE-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[3,1,2,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1 ; CHECK-WIDE-NEXT: vextractf128 $1, %ymm0, %xmm0 ; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %eax ; CHECK-WIDE-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vmovshdup %xmm0, %xmm2 ## xmm2 = xmm0[1,1,3,3] +; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilpd $1, %xmm0, %xmm2 ## xmm2 = xmm0[1,0] +; CHECK-WIDE-NEXT: vpermilpd {{.*#+}} xmm2 = xmm0[1,0] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilps $231, %xmm0, %xmm0 ## xmm0 = xmm0[3,1,2,3] +; CHECK-WIDE-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %eax ; CHECK-WIDE-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0 ; CHECK-WIDE-NEXT: vzeroupper @@ -133,13 +136,13 @@ define <4 x i8> @foo3_4(<4 x float> %src) { ; CHECK-WIDE: ## BB#0: ; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %eax ; CHECK-WIDE-NEXT: vpinsrb $0, %eax, %xmm0, %xmm1 -; CHECK-WIDE-NEXT: vmovshdup %xmm0, %xmm2 ## xmm2 = xmm0[1,1,3,3] +; CHECK-WIDE-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilpd $1, %xmm0, %xmm2 ## xmm2 = xmm0[1,0] +; CHECK-WIDE-NEXT: vpermilpd {{.*#+}} xmm2 = xmm0[1,0] ; CHECK-WIDE-NEXT: vcvttss2si %xmm2, %eax ; CHECK-WIDE-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1 -; CHECK-WIDE-NEXT: vpermilps $231, %xmm0, %xmm0 ## xmm0 = xmm0[3,1,2,3] +; CHECK-WIDE-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3] ; CHECK-WIDE-NEXT: vcvttss2si %xmm0, %eax ; CHECK-WIDE-NEXT: vpinsrb $3, %eax, %xmm1, %xmm0 ; CHECK-WIDE-NEXT: retl |