diff options
Diffstat (limited to 'test/CodeGen/X86/vec_insert-5.ll')
-rw-r--r-- | test/CodeGen/X86/vec_insert-5.ll | 95 |
1 files changed, 58 insertions, 37 deletions
diff --git a/test/CodeGen/X86/vec_insert-5.ll b/test/CodeGen/X86/vec_insert-5.ll index 5cb9f694bd..b72044aee3 100644 --- a/test/CodeGen/X86/vec_insert-5.ll +++ b/test/CodeGen/X86/vec_insert-5.ll @@ -2,66 +2,87 @@ ; There are no MMX operations in @t1 define void @t1(i32 %a, x86_mmx* %P) nounwind { - %tmp12 = shl i32 %a, 12 - %tmp21 = insertelement <2 x i32> undef, i32 %tmp12, i32 1 - %tmp22 = insertelement <2 x i32> %tmp21, i32 0, i32 0 - %tmp23 = bitcast <2 x i32> %tmp22 to x86_mmx - store x86_mmx %tmp23, x86_mmx* %P - ret void - ; CHECK-LABEL: t1: -; CHECK-NOT: %mm -; CHECK: shll $12 -; CHECK-NOT: %mm +; CHECK: # BB#0: +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx +; CHECK-NEXT: shll $12, %ecx +; CHECK-NEXT: movd %ecx, %xmm0 +; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,0,0,1] +; CHECK-NEXT: movlpd %xmm0, (%eax) +; CHECK-NEXT: retl + %tmp12 = shl i32 %a, 12 + %tmp21 = insertelement <2 x i32> undef, i32 %tmp12, i32 1 + %tmp22 = insertelement <2 x i32> %tmp21, i32 0, i32 0 + %tmp23 = bitcast <2 x i32> %tmp22 to x86_mmx + store x86_mmx %tmp23, x86_mmx* %P + ret void } define <4 x float> @t2(<4 x float>* %P) nounwind { - %tmp1 = load <4 x float>* %P - %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 4, i32 4, i32 4, i32 0 > - ret <4 x float> %tmp2 - ; CHECK-LABEL: t2: -; CHECK: pslldq $12 +; CHECK: # BB#0: +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-NEXT: movaps (%eax), %xmm1 +; CHECK-NEXT: xorps %xmm0, %xmm0 +; CHECK-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0] +; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[2,0] +; CHECK-NEXT: retl + %tmp1 = load <4 x float>* %P + %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 4, i32 4, i32 4, i32 0 > + ret <4 x float> %tmp2 } define <4 x float> @t3(<4 x float>* %P) nounwind { - %tmp1 = load <4 x float>* %P - %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 2, i32 3, i32 4, i32 4 > - ret <4 x float> %tmp2 - ; CHECK-LABEL: t3: -; CHECK: psrldq $8 +; CHECK: # BB#0: +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-NEXT: movaps (%eax), %xmm0 +; CHECK-NEXT: xorps %xmm1, %xmm1 +; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,3],xmm1[0,0] +; CHECK-NEXT: retl + %tmp1 = load <4 x float>* %P + %tmp2 = shufflevector <4 x float> %tmp1, <4 x float> zeroinitializer, <4 x i32> < i32 2, i32 3, i32 4, i32 4 > + ret <4 x float> %tmp2 } define <4 x float> @t4(<4 x float>* %P) nounwind { - %tmp1 = load <4 x float>* %P - %tmp2 = shufflevector <4 x float> zeroinitializer, <4 x float> %tmp1, <4 x i32> < i32 7, i32 0, i32 0, i32 0 > - ret <4 x float> %tmp2 - ; CHECK-LABEL: t4: -; CHECK: psrldq $12 +; CHECK: # BB#0: +; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-NEXT: movaps (%eax), %xmm0 +; CHECK-NEXT: xorps %xmm1, %xmm1 +; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,0],xmm1[0,0] +; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,0] +; CHECK-NEXT: retl + %tmp1 = load <4 x float>* %P + %tmp2 = shufflevector <4 x float> zeroinitializer, <4 x float> %tmp1, <4 x i32> < i32 7, i32 0, i32 0, i32 0 > + ret <4 x float> %tmp2 } define <16 x i8> @t5(<16 x i8> %x) nounwind { - %s = shufflevector <16 x i8> %x, <16 x i8> zeroinitializer, <16 x i32> <i32 1, 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, i32 undef, i32 17> - ret <16 x i8> %s - ; CHECK-LABEL: t5: -; CHECK: psrldq $1 +; CHECK: # BB#0: +; CHECK-NEXT: psrldq {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero +; CHECK-NEXT: retl + %s = shufflevector <16 x i8> %x, <16 x i8> zeroinitializer, <16 x i32> <i32 1, 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, i32 undef, i32 17> + ret <16 x i8> %s } define <16 x i8> @t6(<16 x i8> %x) nounwind { - %s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <i32 1, 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, i32 undef, i32 undef> - ret <16 x i8> %s - ; CHECK-LABEL: t6: -; CHECK: palignr $1 +; CHECK: # BB#0: +; CHECK-NEXT: psrldq {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero +; CHECK-NEXT: retl + %s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <i32 1, 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, i32 undef, i32 undef> + ret <16 x i8> %s } define <16 x i8> @t7(<16 x i8> %x) nounwind { - %s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <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, i32 undef, i32 1, i32 2> - ret <16 x i8> %s - ; CHECK-LABEL: t7: -; CHECK: pslldq $13 +; CHECK: # BB#0: +; CHECK-NEXT: pslldq {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[0,1,2] +; CHECK-NEXT: retl + %s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <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, i32 undef, i32 1, i32 2> + ret <16 x i8> %s } |