maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] SimplifyDemandedVectorElts - attempt to recombine target shuffle using DemandedElts mask (REAPPLIED) 

If we don't demand all elements, then attempt to combine to a simpler shuffle.

At the moment we can only do this if Depth == 0 as combineX86ShufflesRecursively uses Depth to track whether the shuffle has really changed or not - we'll need to change this before we can properly start merging combineX86ShufflesRecursively into SimplifyDemandedVectorElts (see D66004).

This reapplies rL368307 (reverted at rL369167) after the fix for the infinite loop reported at PR43024 was applied at rG3f087e38a2e7b87a5adaaac1c1b61e51220e7ff3
This commit is contained in:
Simon Pilgrim 2019-11-04 11:37:42 +00:00
parent 3169f0129a
commit 31ed36d044
5 changed files with 284 additions and 265 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -34750,6 +34750,23 @@ bool X86TargetLowering::SimplifyDemandedVectorEltsForTargetNode(
return true; return true;
} }
// If we don't demand all elements, then attempt to combine to a simpler
// shuffle.
// TODO: Handle other depths, but first we need to handle the fact that
// it might combine to the same shuffle.
if (!DemandedElts.isAllOnesValue() && Depth == 0) {
SmallVector<int, 64> DemandedMask(NumElts, SM_SentinelUndef);
for (int i = 0; i != NumElts; ++i)
if (DemandedElts[i])
DemandedMask[i] = i;
SDValue NewShuffle = combineX86ShufflesRecursively(
{Op}, 0, Op, DemandedMask, {}, Depth, /*HasVarMask*/ false,
/*AllowVarMask*/ true, TLO.DAG, Subtarget);
if (NewShuffle)
return TLO.CombineTo(Op, NewShuffle);
}
return false; return false;
} }

16
llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll
View File

@ -8320,7 +8320,7 @@ define float @test_mm512_reduce_max_ps(<16 x float> %__W) {
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X86-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X86-NEXT: vmaxss %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxss %xmm1, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp) ; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp) ; X86-NEXT: flds (%esp)
@ -8337,7 +8337,7 @@ define float @test_mm512_reduce_max_ps(<16 x float> %__W) {
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X64-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X64-NEXT: vmaxss %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxss %xmm1, %xmm0, %xmm0
; X64-NEXT: vzeroupper ; X64-NEXT: vzeroupper
; X64-NEXT: retq ; X64-NEXT: retq
@ -8446,7 +8446,7 @@ define float @test_mm512_reduce_min_ps(<16 x float> %__W) {
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X86-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X86-NEXT: vminss %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminss %xmm1, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp) ; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp) ; X86-NEXT: flds (%esp)
@ -8463,7 +8463,7 @@ define float @test_mm512_reduce_min_ps(<16 x float> %__W) {
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X64-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X64-NEXT: vminss %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminss %xmm1, %xmm0, %xmm0
; X64-NEXT: vzeroupper ; X64-NEXT: vzeroupper
; X64-NEXT: retq ; X64-NEXT: retq
@ -8624,7 +8624,7 @@ define float @test_mm512_mask_reduce_max_ps(i16 zeroext %__M, <16 x float> %__W)
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X86-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X86-NEXT: vmaxss %xmm1, %xmm0, %xmm0 ; X86-NEXT: vmaxss %xmm1, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp) ; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp) ; X86-NEXT: flds (%esp)
@ -8644,7 +8644,7 @@ define float @test_mm512_mask_reduce_max_ps(i16 zeroext %__M, <16 x float> %__W)
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X64-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X64-NEXT: vmaxss %xmm1, %xmm0, %xmm0 ; X64-NEXT: vmaxss %xmm1, %xmm0, %xmm0
; X64-NEXT: vzeroupper ; X64-NEXT: vzeroupper
; X64-NEXT: retq ; X64-NEXT: retq
@ -8809,7 +8809,7 @@ define float @test_mm512_mask_reduce_min_ps(i16 zeroext %__M, <16 x float> %__W)
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X86-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X86-NEXT: vminss %xmm1, %xmm0, %xmm0 ; X86-NEXT: vminss %xmm1, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%esp) ; X86-NEXT: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp) ; X86-NEXT: flds (%esp)
@ -8829,7 +8829,7 @@ define float @test_mm512_mask_reduce_min_ps(i16 zeroext %__M, <16 x float> %__W)
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0] ; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,0,3,2] ; X64-NEXT: vmovshdup {{.*#+}} xmm1 = xmm0[1,1,3,3]
; X64-NEXT: vminss %xmm1, %xmm0, %xmm0 ; X64-NEXT: vminss %xmm1, %xmm0, %xmm0
; X64-NEXT: vzeroupper ; X64-NEXT: vzeroupper
; X64-NEXT: retq ; X64-NEXT: retq

224
llvm/test/CodeGen/X86/shrink_vmul.ll
View File

@ -2085,85 +2085,88 @@ define void @PR34947(<9 x i16>* %p0, <9 x i32>* %p1) nounwind {
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx ; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax ; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movdqa (%eax), %xmm5 ; X86-SSE-NEXT: movdqa (%eax), %xmm5
; X86-SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero ; X86-SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movdqa (%ecx), %xmm2 ; X86-SSE-NEXT: movdqa (%ecx), %xmm2
; X86-SSE-NEXT: movdqa 16(%ecx), %xmm6 ; X86-SSE-NEXT: movdqa 16(%ecx), %xmm6
; X86-SSE-NEXT: pxor %xmm0, %xmm0 ; X86-SSE-NEXT: pxor %xmm1, %xmm1
; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] ; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X86-SSE-NEXT: movdqa %xmm5, %xmm4 ; X86-SSE-NEXT: movdqa %xmm5, %xmm4
; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3] ; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] ; X86-SSE-NEXT: movdqa %xmm5, %xmm3
; X86-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm5[3,1,2,3] ; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; X86-SSE-NEXT: movd %xmm0, %eax ; X86-SSE-NEXT: movdqa %xmm5, %xmm1
; X86-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[3,1,2,3] ; X86-SSE-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; X86-SSE-NEXT: movd %xmm0, %esi ; X86-SSE-NEXT: movd %xmm1, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm6[3,1,2,3]
; X86-SSE-NEXT: movd %xmm1, %esi
; X86-SSE-NEXT: xorl %edx, %edx ; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi ; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm0 ; X86-SSE-NEXT: movd %edx, %xmm1
; X86-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm5[2,3,0,1] ; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm3[2,3,0,1]
; X86-SSE-NEXT: movd %xmm3, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm6[2,3,0,1]
; X86-SSE-NEXT: movd %xmm3, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm7
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm0[0],xmm7[1],xmm0[1]
; X86-SSE-NEXT: movd %xmm5, %eax
; X86-SSE-NEXT: movd %xmm6, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm3
; X86-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,2,3]
; X86-SSE-NEXT: movd %xmm5, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,2,3]
; X86-SSE-NEXT: movd %xmm5, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm5
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm5[0],xmm3[1],xmm5[1]
; X86-SSE-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm7[0]
; X86-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm4[3,1,2,3]
; X86-SSE-NEXT: movd %xmm6, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm2[3,1,2,3]
; X86-SSE-NEXT: movd %xmm6, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm6
; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm4[2,3,0,1]
; X86-SSE-NEXT: movd %xmm7, %eax ; X86-SSE-NEXT: movd %xmm7, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm2[2,3,0,1] ; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm6[2,3,0,1]
; X86-SSE-NEXT: movd %xmm7, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm7
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm1[0],xmm7[1],xmm1[1]
; X86-SSE-NEXT: movd %xmm3, %eax
; X86-SSE-NEXT: movd %xmm6, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,2,3]
; X86-SSE-NEXT: movd %xmm3, %eax
; X86-SSE-NEXT: movd %edx, %xmm3
; X86-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,2,3]
; X86-SSE-NEXT: movd %xmm6, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm6
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1]
; X86-SSE-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm7[0]
; X86-SSE-NEXT: movdqa %xmm5, %xmm7
; X86-SSE-NEXT: psrld $16, %xmm7
; X86-SSE-NEXT: movd %xmm7, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm2[1,1,2,3]
; X86-SSE-NEXT: movd %xmm7, %esi ; X86-SSE-NEXT: movd %xmm7, %esi
; X86-SSE-NEXT: xorl %edx, %edx ; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi ; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm7 ; X86-SSE-NEXT: movd %edx, %xmm7
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm6[0],xmm7[1],xmm6[1]
; X86-SSE-NEXT: movd %xmm4, %eax ; X86-SSE-NEXT: movd %xmm4, %eax
; X86-SSE-NEXT: movd %xmm2, %esi ; X86-SSE-NEXT: movd %xmm2, %esi
; X86-SSE-NEXT: xorl %edx, %edx ; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi ; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,2,3] ; X86-SSE-NEXT: psrlq $48, %xmm5
; X86-SSE-NEXT: movd %xmm5, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm2[3,1,2,3]
; X86-SSE-NEXT: movd %xmm5, %esi
; X86-SSE-NEXT: movd %edx, %xmm5
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,0,1]
; X86-SSE-NEXT: movd %xmm4, %eax ; X86-SSE-NEXT: movd %xmm4, %eax
; X86-SSE-NEXT: movd %edx, %xmm4 ; X86-SSE-NEXT: movd %edx, %xmm4
; X86-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,2,3] ; X86-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; X86-SSE-NEXT: movd %xmm2, %esi ; X86-SSE-NEXT: movd %xmm2, %esi
; X86-SSE-NEXT: xorl %edx, %edx ; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi ; X86-SSE-NEXT: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm2 ; X86-SSE-NEXT: movd %edx, %xmm2
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; X86-SSE-NEXT: punpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm2[0]
; X86-SSE-NEXT: movd %xmm0, %eax
; X86-SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm4[0,0]
; X86-SSE-NEXT: movdqa {{.*#+}} xmm0 = [8199,8199,8199,8199]
; X86-SSE-NEXT: pmuludq %xmm0, %xmm7
; X86-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm7[0,2,2,3]
; X86-SSE-NEXT: pmuludq %xmm0, %xmm5
; X86-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[0,2,2,3]
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1] ; X86-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1]
; X86-SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm7[0] ; X86-SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm1[0,0]
; X86-SSE-NEXT: movd %xmm1, %eax ; X86-SSE-NEXT: pmuludq %xmm0, %xmm3
; X86-SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm6[0,0] ; X86-SSE-NEXT: pmuludq %xmm0, %xmm6
; X86-SSE-NEXT: movdqa {{.*#+}} xmm1 = [8199,8199,8199,8199]
; X86-SSE-NEXT: pmuludq %xmm1, %xmm4
; X86-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
; X86-SSE-NEXT: pmuludq %xmm1, %xmm2
; X86-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1]
; X86-SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm0[0,0]
; X86-SSE-NEXT: pmuludq %xmm1, %xmm3
; X86-SSE-NEXT: pmuludq %xmm1, %xmm5
; X86-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3] ; X86-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm3[0,2,2,3]
; X86-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm5[0,2,2,3] ; X86-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm6[0,2,2,3]
; X86-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; X86-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; X86-SSE-NEXT: xorl %edx, %edx ; X86-SSE-NEXT: xorl %edx, %edx
; X86-SSE-NEXT: divl 32(%ecx) ; X86-SSE-NEXT: divl 32(%ecx)
@ -2324,92 +2327,95 @@ define void @PR34947(<9 x i16>* %p0, <9 x i32>* %p1) nounwind {
; X64-SSE-LABEL: PR34947: ; X64-SSE-LABEL: PR34947:
; X64-SSE: # %bb.0: ; X64-SSE: # %bb.0:
; X64-SSE-NEXT: movdqa (%rdi), %xmm5 ; X64-SSE-NEXT: movdqa (%rdi), %xmm5
; X64-SSE-NEXT: movd {{.*#+}} xmm1 = mem[0],zero,zero,zero ; X64-SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-SSE-NEXT: movdqa (%rsi), %xmm2 ; X64-SSE-NEXT: movdqa (%rsi), %xmm2
; X64-SSE-NEXT: movdqa 16(%rsi), %xmm6 ; X64-SSE-NEXT: movdqa 16(%rsi), %xmm6
; X64-SSE-NEXT: pxor %xmm0, %xmm0 ; X64-SSE-NEXT: pxor %xmm1, %xmm1
; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] ; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; X64-SSE-NEXT: movdqa %xmm5, %xmm3 ; X64-SSE-NEXT: movdqa %xmm5, %xmm3
; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3] ; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] ; X64-SSE-NEXT: movdqa %xmm5, %xmm7
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm5[3,1,2,3] ; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm7 = xmm7[4],xmm1[4],xmm7[5],xmm1[5],xmm7[6],xmm1[6],xmm7[7],xmm1[7]
; X64-SSE-NEXT: movd %xmm0, %eax ; X64-SSE-NEXT: movdqa %xmm5, %xmm1
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[3,1,2,3] ; X64-SSE-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; X64-SSE-NEXT: movd %xmm0, %ecx ; X64-SSE-NEXT: movd %xmm1, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm6[3,1,2,3]
; X64-SSE-NEXT: movd %xmm1, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm8 ; X64-SSE-NEXT: movd %edx, %xmm8
; X64-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[2,3,0,1] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm7[2,3,0,1]
; X64-SSE-NEXT: movd %xmm4, %eax ; X64-SSE-NEXT: movd %xmm1, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm6[2,3,0,1] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm6[2,3,0,1]
; X64-SSE-NEXT: movd %xmm4, %ecx ; X64-SSE-NEXT: movd %xmm1, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm7 ; X64-SSE-NEXT: movd %edx, %xmm1
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm8[0],xmm7[1],xmm8[1] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
; X64-SSE-NEXT: movd %xmm5, %eax ; X64-SSE-NEXT: movd %xmm7, %eax
; X64-SSE-NEXT: movd %xmm6, %ecx ; X64-SSE-NEXT: movd %xmm6, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm4 ; X64-SSE-NEXT: movd %edx, %xmm4
; X64-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm7[1,1,2,3]
; X64-SSE-NEXT: movd %xmm5, %eax ; X64-SSE-NEXT: movd %xmm7, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm6[1,1,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,2,3]
; X64-SSE-NEXT: movd %xmm5, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm5
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm7[0]
; X64-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm3[3,1,2,3]
; X64-SSE-NEXT: movd %xmm6, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm2[3,1,2,3]
; X64-SSE-NEXT: movd %xmm6, %ecx ; X64-SSE-NEXT: movd %xmm6, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm6 ; X64-SSE-NEXT: movd %edx, %xmm6
; X64-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm3[2,3,0,1] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
; X64-SSE-NEXT: movd %xmm7, %eax ; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm1[0]
; X64-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm2[2,3,0,1] ; X64-SSE-NEXT: movdqa %xmm5, %xmm1
; X64-SSE-NEXT: movd %xmm7, %ecx ; X64-SSE-NEXT: psrld $16, %xmm1
; X64-SSE-NEXT: movd %xmm1, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,2,3]
; X64-SSE-NEXT: movd %xmm1, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm7 ; X64-SSE-NEXT: movd %edx, %xmm7
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm6[0],xmm7[1],xmm6[1]
; X64-SSE-NEXT: movd %xmm3, %eax ; X64-SSE-NEXT: movd %xmm3, %eax
; X64-SSE-NEXT: movd %xmm2, %ecx ; X64-SSE-NEXT: movd %xmm2, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm0 ; X64-SSE-NEXT: movd %edx, %xmm1
; X64-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,2,3] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm7[0],xmm1[1],xmm7[1]
; X64-SSE-NEXT: psrlq $48, %xmm5
; X64-SSE-NEXT: movd %xmm5, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm2[3,1,2,3]
; X64-SSE-NEXT: movd %xmm5, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm5
; X64-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,0,1]
; X64-SSE-NEXT: movd %xmm3, %eax ; X64-SSE-NEXT: movd %xmm3, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,1,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; X64-SSE-NEXT: movd %xmm2, %ecx ; X64-SSE-NEXT: movd %xmm2, %ecx
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx ; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm2 ; X64-SSE-NEXT: movd %edx, %xmm2
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm7[0] ; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; X64-SSE-NEXT: movd %xmm1, %eax ; X64-SSE-NEXT: movd %xmm0, %eax
; X64-SSE-NEXT: xorl %edx, %edx ; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl 32(%rsi) ; X64-SSE-NEXT: divl 32(%rsi)
; X64-SSE-NEXT: movdqa {{.*#+}} xmm1 = [8199,8199,8199,8199] ; X64-SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm5[0,0]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm0 ; X64-SSE-NEXT: movdqa {{.*#+}} xmm0 = [8199,8199,8199,8199]
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] ; X64-SSE-NEXT: pmuludq %xmm0, %xmm7
; X64-SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm6[0,0] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm7[0,2,2,3]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm2 ; X64-SSE-NEXT: pmuludq %xmm0, %xmm1
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm4 ; X64-SSE-NEXT: pmuludq %xmm0, %xmm4
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
; X64-SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm8[0,0] ; X64-SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm8[0,0]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm5 ; X64-SSE-NEXT: pmuludq %xmm0, %xmm6
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm5[0,2,2,3] ; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1] ; X64-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; X64-SSE-NEXT: imull $8199, %edx, %eax # imm = 0x2007 ; X64-SSE-NEXT: imull $8199, %edx, %eax # imm = 0x2007
; X64-SSE-NEXT: movl %eax, (%rax) ; X64-SSE-NEXT: movl %eax, (%rax)
; X64-SSE-NEXT: movdqa %xmm2, (%rax) ; X64-SSE-NEXT: movdqa %xmm2, (%rax)
; X64-SSE-NEXT: movdqa %xmm0, (%rax) ; X64-SSE-NEXT: movdqa %xmm1, (%rax)
; X64-SSE-NEXT: retq ; X64-SSE-NEXT: retq
; ;
; X64-AVX1-LABEL: PR34947: ; X64-AVX1-LABEL: PR34947:

152
llvm/test/CodeGen/X86/vec_smulo.ll
View File

@ -195,17 +195,17 @@ define <3 x i32> @smulo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) noun
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1] ; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; SSE2-NEXT: psubd %xmm2, %xmm4 ; SSE2-NEXT: psubd %xmm2, %xmm4
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movq %xmm0, (%rdi) ; SSE2-NEXT: movq %xmm2, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: psrad $31, %xmm2 ; SSE2-NEXT: psrad $31, %xmm2
; SSE2-NEXT: pcmpeqd %xmm4, %xmm2 ; SSE2-NEXT: pcmpeqd %xmm4, %xmm2
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0 ; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm0 ; SSE2-NEXT: pxor %xmm2, %xmm1
; SSE2-NEXT: movd %xmm1, 8(%rdi) ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSE2-NEXT: movd %xmm0, 8(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq ; SSE2-NEXT: retq
; ;
; SSSE3-LABEL: smulo_v3i32: ; SSSE3-LABEL: smulo_v3i32:
@ -225,17 +225,17 @@ define <3 x i32> @smulo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) noun
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; SSSE3-NEXT: psubd %xmm2, %xmm4 ; SSSE3-NEXT: psubd %xmm2, %xmm4
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSSE3-NEXT: movq %xmm0, (%rdi) ; SSSE3-NEXT: movq %xmm2, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: psrad $31, %xmm2 ; SSSE3-NEXT: psrad $31, %xmm2
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm2 ; SSSE3-NEXT: pcmpeqd %xmm4, %xmm2
; SSSE3-NEXT: pcmpeqd %xmm0, %xmm0 ; SSSE3-NEXT: pcmpeqd %xmm1, %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm0 ; SSSE3-NEXT: pxor %xmm2, %xmm1
; SSSE3-NEXT: movd %xmm1, 8(%rdi) ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSSE3-NEXT: movd %xmm0, 8(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: retq ; SSSE3-NEXT: retq
; ;
; SSE41-LABEL: smulo_v3i32: ; SSE41-LABEL: smulo_v3i32:
@ -1769,52 +1769,52 @@ define <4 x i32> @smulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) noun
; SSE2-NEXT: psrad $8, %xmm0 ; SSE2-NEXT: psrad $8, %xmm0
; SSE2-NEXT: pslld $8, %xmm1 ; SSE2-NEXT: pslld $8, %xmm1
; SSE2-NEXT: psrad $8, %xmm1 ; SSE2-NEXT: psrad $8, %xmm1
; SSE2-NEXT: pxor %xmm4, %xmm4 ; SSE2-NEXT: pxor %xmm3, %xmm3
; SSE2-NEXT: pxor %xmm2, %xmm2 ; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pcmpgtd %xmm1, %xmm2 ; SSE2-NEXT: pcmpgtd %xmm1, %xmm2
; SSE2-NEXT: pand %xmm0, %xmm2 ; SSE2-NEXT: pand %xmm0, %xmm2
; SSE2-NEXT: pcmpgtd %xmm0, %xmm4 ; SSE2-NEXT: pcmpgtd %xmm0, %xmm3
; SSE2-NEXT: pand %xmm1, %xmm4 ; SSE2-NEXT: pand %xmm1, %xmm3
; SSE2-NEXT: paddd %xmm2, %xmm4 ; SSE2-NEXT: paddd %xmm2, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0 ; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm5, %xmm2 ; SSE2-NEXT: pmuludq %xmm4, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1] ; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1]
; SSE2-NEXT: psubd %xmm4, %xmm3 ; SSE2-NEXT: psubd %xmm3, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1] ; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSE2-NEXT: movdqa %xmm4, %xmm1 ; SSE2-NEXT: movdqa %xmm3, %xmm1
; SSE2-NEXT: pslld $8, %xmm1 ; SSE2-NEXT: pslld $8, %xmm1
; SSE2-NEXT: psrad $8, %xmm1 ; SSE2-NEXT: psrad $8, %xmm1
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1 ; SSE2-NEXT: pcmpeqd %xmm3, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3] ; SSE2-NEXT: psrad $31, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1] ; SSE2-NEXT: pcmpeqd %xmm5, %xmm3
; SSE2-NEXT: psrad $31, %xmm4 ; SSE2-NEXT: pcmpeqd %xmm4, %xmm4
; SSE2-NEXT: pcmpeqd %xmm3, %xmm4 ; SSE2-NEXT: pxor %xmm4, %xmm3
; SSE2-NEXT: pcmpeqd %xmm3, %xmm3 ; SSE2-NEXT: pxor %xmm4, %xmm1
; SSE2-NEXT: pxor %xmm3, %xmm4 ; SSE2-NEXT: por %xmm3, %xmm1
; SSE2-NEXT: pxor %xmm3, %xmm1
; SSE2-NEXT: por %xmm4, %xmm1
; SSE2-NEXT: movd %xmm0, %eax ; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: movw %ax, (%rdi) ; SSE2-NEXT: movw %ax, (%rdi)
; SSE2-NEXT: movd %xmm2, %ecx ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSE2-NEXT: movw %cx, 3(%rdi) ; SSE2-NEXT: movd %xmm0, %ecx
; SSE2-NEXT: movw %cx, 6(%rdi)
; SSE2-NEXT: movd %xmm2, %edx
; SSE2-NEXT: movw %dx, 3(%rdi)
; SSE2-NEXT: shrl $16, %eax ; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 2(%rdi) ; SSE2-NEXT: movb %al, 2(%rdi)
; SSE2-NEXT: shrl $16, %ecx ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
; SSE2-NEXT: movb %cl, 5(%rdi) ; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: movd %xmm5, %eax
; SSE2-NEXT: movw %ax, 9(%rdi) ; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: movd %xmm6, %ecx
; SSE2-NEXT: movw %cx, 6(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: shrl $16, %ecx ; SSE2-NEXT: shrl $16, %ecx
; SSE2-NEXT: movb %cl, 8(%rdi) ; SSE2-NEXT: movb %cl, 8(%rdi)
; SSE2-NEXT: shrl $16, %edx
; SSE2-NEXT: movb %dl, 5(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0 ; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq ; SSE2-NEXT: retq
; ;
@ -1824,52 +1824,52 @@ define <4 x i32> @smulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) noun
; SSSE3-NEXT: psrad $8, %xmm0 ; SSSE3-NEXT: psrad $8, %xmm0
; SSSE3-NEXT: pslld $8, %xmm1 ; SSSE3-NEXT: pslld $8, %xmm1
; SSSE3-NEXT: psrad $8, %xmm1 ; SSSE3-NEXT: psrad $8, %xmm1
; SSSE3-NEXT: pxor %xmm4, %xmm4 ; SSSE3-NEXT: pxor %xmm3, %xmm3
; SSSE3-NEXT: pxor %xmm2, %xmm2 ; SSSE3-NEXT: pxor %xmm2, %xmm2
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm2 ; SSSE3-NEXT: pcmpgtd %xmm1, %xmm2
; SSSE3-NEXT: pand %xmm0, %xmm2 ; SSSE3-NEXT: pand %xmm0, %xmm2
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm4 ; SSSE3-NEXT: pcmpgtd %xmm0, %xmm3
; SSSE3-NEXT: pand %xmm1, %xmm4 ; SSSE3-NEXT: pand %xmm1, %xmm3
; SSSE3-NEXT: paddd %xmm2, %xmm4 ; SSSE3-NEXT: paddd %xmm2, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm1, %xmm0 ; SSSE3-NEXT: pmuludq %xmm1, %xmm0
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,3,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm5, %xmm2 ; SSSE3-NEXT: pmuludq %xmm4, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1]
; SSSE3-NEXT: psubd %xmm4, %xmm3 ; SSSE3-NEXT: psubd %xmm3, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSSE3-NEXT: movdqa %xmm4, %xmm1 ; SSSE3-NEXT: movdqa %xmm3, %xmm1
; SSSE3-NEXT: pslld $8, %xmm1 ; SSSE3-NEXT: pslld $8, %xmm1
; SSSE3-NEXT: psrad $8, %xmm1 ; SSSE3-NEXT: psrad $8, %xmm1
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1 ; SSSE3-NEXT: pcmpeqd %xmm3, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3] ; SSSE3-NEXT: psrad $31, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1] ; SSSE3-NEXT: pcmpeqd %xmm5, %xmm3
; SSSE3-NEXT: psrad $31, %xmm4 ; SSSE3-NEXT: pcmpeqd %xmm4, %xmm4
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm4 ; SSSE3-NEXT: pxor %xmm4, %xmm3
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm3 ; SSSE3-NEXT: pxor %xmm4, %xmm1
; SSSE3-NEXT: pxor %xmm3, %xmm4 ; SSSE3-NEXT: por %xmm3, %xmm1
; SSSE3-NEXT: pxor %xmm3, %xmm1
; SSSE3-NEXT: por %xmm4, %xmm1
; SSSE3-NEXT: movd %xmm0, %eax ; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: movw %ax, (%rdi) ; SSSE3-NEXT: movw %ax, (%rdi)
; SSSE3-NEXT: movd %xmm2, %ecx ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSSE3-NEXT: movw %cx, 3(%rdi) ; SSSE3-NEXT: movd %xmm0, %ecx
; SSSE3-NEXT: movw %cx, 6(%rdi)
; SSSE3-NEXT: movd %xmm2, %edx
; SSSE3-NEXT: movw %dx, 3(%rdi)
; SSSE3-NEXT: shrl $16, %eax ; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 2(%rdi) ; SSSE3-NEXT: movb %al, 2(%rdi)
; SSSE3-NEXT: shrl $16, %ecx ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
; SSSE3-NEXT: movb %cl, 5(%rdi) ; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: movd %xmm5, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi) ; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: movd %xmm6, %ecx
; SSSE3-NEXT: movw %cx, 6(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: shrl $16, %ecx ; SSSE3-NEXT: shrl $16, %ecx
; SSSE3-NEXT: movb %cl, 8(%rdi) ; SSSE3-NEXT: movb %cl, 8(%rdi)
; SSSE3-NEXT: shrl $16, %edx
; SSSE3-NEXT: movb %dl, 5(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0 ; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: retq ; SSSE3-NEXT: retq
; ;

140
llvm/test/CodeGen/X86/vec_umulo.ll
View File

@ -179,12 +179,10 @@ define <3 x i32> @umulo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) noun
; SSE2-NEXT: pcmpeqd %xmm3, %xmm2 ; SSE2-NEXT: pcmpeqd %xmm3, %xmm2
; SSE2-NEXT: pcmpeqd %xmm1, %xmm1 ; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm1 ; SSE2-NEXT: pxor %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3] ; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; SSE2-NEXT: movd %xmm2, 8(%rdi)
; SSE2-NEXT: movq %xmm0, (%rdi) ; SSE2-NEXT: movq %xmm0, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE2-NEXT: movd %xmm0, 8(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0 ; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq ; SSE2-NEXT: retq
; ;
@ -201,12 +199,10 @@ define <3 x i32> @umulo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) noun
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm2 ; SSSE3-NEXT: pcmpeqd %xmm3, %xmm2
; SSSE3-NEXT: pcmpeqd %xmm1, %xmm1 ; SSSE3-NEXT: pcmpeqd %xmm1, %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm1 ; SSSE3-NEXT: pxor %xmm2, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; SSSE3-NEXT: movd %xmm2, 8(%rdi)
; SSSE3-NEXT: movq %xmm0, (%rdi) ; SSSE3-NEXT: movq %xmm0, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSSE3-NEXT: movd %xmm0, 8(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0 ; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: retq ; SSSE3-NEXT: retq
; ;
@ -1569,90 +1565,90 @@ define <2 x i32> @umulo_v2i64(<2 x i64> %a0, <2 x i64> %a1, <2 x i64>* %p2) noun
define <4 x i32> @umulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) nounwind { define <4 x i32> @umulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) nounwind {
; SSE2-LABEL: umulo_v4i24: ; SSE2-LABEL: umulo_v4i24:
; SSE2: # %bb.0: ; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0] ; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: pand %xmm2, %xmm1 ; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0]
; SSE2-NEXT: pand %xmm2, %xmm0 ; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3] ; SSE2-NEXT: pand %xmm0, %xmm2
; SSE2-NEXT: pmuludq %xmm1, %xmm0 ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3] ; SSE2-NEXT: pmuludq %xmm1, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,3,2,3]
; SSE2-NEXT: pmuludq %xmm4, %xmm2 ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3] ; SSE2-NEXT: pmuludq %xmm0, %xmm1
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1] ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
; SSE2-NEXT: pxor %xmm4, %xmm4 ; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: pcmpeqd %xmm4, %xmm3 ; SSE2-NEXT: pcmpeqd %xmm4, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,2,2,3] ; SSE2-NEXT: pcmpeqd %xmm5, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm2[0,2,2,3] ; SSE2-NEXT: pxor %xmm5, %xmm3
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1] ; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm1[3,1,2,3] ; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm1[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm1[2,3,0,1] ; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
; SSE2-NEXT: psrld $24, %xmm1 ; SSE2-NEXT: psrld $24, %xmm0
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1 ; SSE2-NEXT: pcmpeqd %xmm4, %xmm0
; SSE2-NEXT: pcmpeqd %xmm4, %xmm4 ; SSE2-NEXT: pxor %xmm5, %xmm0
; SSE2-NEXT: pxor %xmm4, %xmm3 ; SSE2-NEXT: por %xmm3, %xmm0
; SSE2-NEXT: pxor %xmm4, %xmm1 ; SSE2-NEXT: movd %xmm2, %eax
; SSE2-NEXT: por %xmm3, %xmm1
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: movw %ax, (%rdi) ; SSE2-NEXT: movw %ax, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,2,3]
; SSE2-NEXT: movd %xmm2, %ecx ; SSE2-NEXT: movd %xmm2, %ecx
; SSE2-NEXT: movw %cx, 3(%rdi) ; SSE2-NEXT: movw %cx, 6(%rdi)
; SSE2-NEXT: movd %xmm1, %edx
; SSE2-NEXT: movw %dx, 3(%rdi)
; SSE2-NEXT: shrl $16, %eax ; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 2(%rdi) ; SSE2-NEXT: movb %al, 2(%rdi)
; SSE2-NEXT: shrl $16, %ecx ; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
; SSE2-NEXT: movb %cl, 5(%rdi) ; SSE2-NEXT: movd %xmm1, %eax
; SSE2-NEXT: movd %xmm5, %eax
; SSE2-NEXT: movw %ax, 9(%rdi) ; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: movd %xmm6, %ecx
; SSE2-NEXT: movw %cx, 6(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: shrl $16, %ecx ; SSE2-NEXT: shrl $16, %ecx
; SSE2-NEXT: movb %cl, 8(%rdi) ; SSE2-NEXT: movb %cl, 8(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0 ; SSE2-NEXT: shrl $16, %edx
; SSE2-NEXT: movb %dl, 5(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: retq ; SSE2-NEXT: retq
; ;
; SSSE3-LABEL: umulo_v4i24: ; SSSE3-LABEL: umulo_v4i24:
; SSSE3: # %bb.0: ; SSSE3: # %bb.0:
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0] ; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: pand %xmm2, %xmm1 ; SSSE3-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0]
; SSSE3-NEXT: pand %xmm2, %xmm0 ; SSSE3-NEXT: pand %xmm0, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3] ; SSSE3-NEXT: pand %xmm0, %xmm2
; SSSE3-NEXT: pmuludq %xmm1, %xmm0 ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3] ; SSSE3-NEXT: pmuludq %xmm1, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,3,2,3]
; SSSE3-NEXT: pmuludq %xmm4, %xmm2 ; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3] ; SSSE3-NEXT: pmuludq %xmm0, %xmm1
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1] ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1]
; SSSE3-NEXT: pxor %xmm4, %xmm4 ; SSSE3-NEXT: pxor %xmm4, %xmm4
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm3 ; SSSE3-NEXT: pcmpeqd %xmm4, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,2,2,3] ; SSSE3-NEXT: pcmpeqd %xmm5, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm2[0,2,2,3] ; SSSE3-NEXT: pxor %xmm5, %xmm3
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1] ; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm1[3,1,2,3] ; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm1[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm1[2,3,0,1] ; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
; SSSE3-NEXT: psrld $24, %xmm1 ; SSSE3-NEXT: psrld $24, %xmm0
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1 ; SSSE3-NEXT: pcmpeqd %xmm4, %xmm0
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm4 ; SSSE3-NEXT: pxor %xmm5, %xmm0
; SSSE3-NEXT: pxor %xmm4, %xmm3 ; SSSE3-NEXT: por %xmm3, %xmm0
; SSSE3-NEXT: pxor %xmm4, %xmm1 ; SSSE3-NEXT: movd %xmm2, %eax
; SSSE3-NEXT: por %xmm3, %xmm1
; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: movw %ax, (%rdi) ; SSSE3-NEXT: movw %ax, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,2,3]
; SSSE3-NEXT: movd %xmm2, %ecx ; SSSE3-NEXT: movd %xmm2, %ecx
; SSSE3-NEXT: movw %cx, 3(%rdi) ; SSSE3-NEXT: movw %cx, 6(%rdi)
; SSSE3-NEXT: movd %xmm1, %edx
; SSSE3-NEXT: movw %dx, 3(%rdi)
; SSSE3-NEXT: shrl $16, %eax ; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 2(%rdi) ; SSSE3-NEXT: movb %al, 2(%rdi)
; SSSE3-NEXT: shrl $16, %ecx ; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
; SSSE3-NEXT: movb %cl, 5(%rdi) ; SSSE3-NEXT: movd %xmm1, %eax
; SSSE3-NEXT: movd %xmm5, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi) ; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: movd %xmm6, %ecx
; SSSE3-NEXT: movw %cx, 6(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: shrl $16, %ecx ; SSSE3-NEXT: shrl $16, %ecx
; SSSE3-NEXT: movb %cl, 8(%rdi) ; SSSE3-NEXT: movb %cl, 8(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0 ; SSSE3-NEXT: shrl $16, %edx
; SSSE3-NEXT: movb %dl, 5(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: retq ; SSSE3-NEXT: retq
; ;
; SSE41-LABEL: umulo_v4i24: ; SSE41-LABEL: umulo_v4i24: