Remove DisableTailCalls from TargetOptions and the code in resetTargetOptions

[oota-llvm.git] / test / CodeGen / X86 / vec_cast2.ll

diff --git a/test/CodeGen/X86/vec_cast2.ll b/test/CodeGen/X86/vec_cast2.ll
index d37a93dddfb538d11e556a950d634a1583e42d98..1ba11f51baa2b177e08076b67061f74de94b2790 100644 (file)
--- a/test/CodeGen/X86/vec_cast2.ll
+++ b/test/CodeGen/X86/vec_cast2.ll
@@ -16,13 +16,9 @@ define <8 x float> @foo1_8(<8 x i8> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo1_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:    vpslld $24, %xmm1, %xmm1
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm1, %xmm1
-; CHECK-WIDE-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; CHECK-WIDE-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; CHECK-WIDE-NEXT:    vpslld $24, %xmm0, %xmm0
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm0, %xmm0
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm1
+; CHECK-WIDE-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; CHECK-WIDE-NEXT:    vcvtdq2ps %ymm0, %ymm0
 ; CHECK-WIDE-NEXT:    retl
@@ -40,9 +36,7 @@ define <4 x float> @foo1_4(<4 x i8> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo1_4:
 ; CHECK-WIDE:       ## BB#0:
-; 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:    vpslld $24, %xmm0, %xmm0
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm0, %xmm0
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    retl
   %res = sitofp <4 x i8> %src to <4 x float>
@@ -62,10 +56,7 @@ define <8 x float> @foo2_8(<8 x i8> %src) {
 ; 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:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
-; CHECK-WIDE-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; CHECK-WIDE-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; CHECK-WIDE-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; 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:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; CHECK-WIDE-NEXT:    vcvtdq2ps %ymm0, %ymm0
 ; CHECK-WIDE-NEXT:    retl
@@ -103,37 +94,29 @@ define <8 x i8> @foo3_8(<8 x float> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo3_8:
 ; CHECK-WIDE:       ## BB#0:
-; CHECK-WIDE-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[3,1,2,3]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %ecx
-; CHECK-WIDE-NEXT:    movzbl %cl, %ecx
-; CHECK-WIDE-NEXT:    orl %eax, %ecx
-; CHECK-WIDE-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm0, %edx
-; CHECK-WIDE-NEXT:    movzbl %dl, %edx
-; CHECK-WIDE-NEXT:    orl %eax, %edx
-; CHECK-WIDE-NEXT:    vpinsrw $0, %edx, %xmm0, %xmm1
-; CHECK-WIDE-NEXT:    vpinsrw $1, %ecx, %xmm1, %xmm1
+; 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:    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:    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:    vcvttss2si %xmm2, %eax
+; CHECK-WIDE-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
 ; CHECK-WIDE-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; CHECK-WIDE-NEXT:    vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; 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:    vcvttss2si %xmm2, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm0, %ecx
-; CHECK-WIDE-NEXT:    movzbl %cl, %ecx
-; CHECK-WIDE-NEXT:    orl %eax, %ecx
-; CHECK-WIDE-NEXT:    vpinsrw $2, %ecx, %xmm1, %xmm1
-; CHECK-WIDE-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[3,1,2,3]
+; CHECK-WIDE-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
+; CHECK-WIDE-NEXT:    vpermilpd $1, %xmm0, %xmm2 ## xmm2 = xmm0[1,0]
 ; CHECK-WIDE-NEXT:    vcvttss2si %xmm2, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm0, %ecx
-; CHECK-WIDE-NEXT:    movzbl %cl, %ecx
-; CHECK-WIDE-NEXT:    orl %eax, %ecx
-; CHECK-WIDE-NEXT:    vpinsrw $3, %ecx, %xmm1, %xmm0
+; CHECK-WIDE-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
+; CHECK-WIDE-NEXT:    vpermilps $231, %xmm0, %xmm0 ## xmm0 = xmm0[3,1,2,3]
+; CHECK-WIDE-NEXT:    vcvttss2si %xmm0, %eax
+; CHECK-WIDE-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm0
 ; CHECK-WIDE-NEXT:    vzeroupper
 ; CHECK-WIDE-NEXT:    retl
   %res = fptosi <8 x float> %src to <8 x i8>
@@ -148,21 +131,17 @@ define <4 x i8> @foo3_4(<4 x float> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo3_4:
 ; CHECK-WIDE:       ## BB#0:
-; CHECK-WIDE-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[3,1,2,3]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %ecx
-; CHECK-WIDE-NEXT:    movzbl %cl, %ecx
-; CHECK-WIDE-NEXT:    orl %eax, %ecx
-; CHECK-WIDE-NEXT:    vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm1, %eax
-; CHECK-WIDE-NEXT:    shll $8, %eax
-; CHECK-WIDE-NEXT:    vcvttss2si %xmm0, %edx
-; CHECK-WIDE-NEXT:    movzbl %dl, %edx
-; CHECK-WIDE-NEXT:    orl %eax, %edx
-; CHECK-WIDE-NEXT:    vpinsrw $0, %edx, %xmm0, %xmm0
-; CHECK-WIDE-NEXT:    vpinsrw $1, %ecx, %xmm0, %xmm0
+; 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:    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:    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:    vcvttss2si %xmm0, %eax
+; CHECK-WIDE-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm0
 ; CHECK-WIDE-NEXT:    retl
   %res = fptosi <4 x float> %src to <4 x i8>
   ret <4 x i8> %res