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

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. 

The insertps-combine.ll regression is because XFormVExtractWithShuffleIntoLoad can't see through shuffles of different widths - this will be fixed in a follow-up commit.

llvm-svn: 368307
This commit is contained in:
Simon Pilgrim 2019-08-08 15:54:20 +00:00
parent 8558aac82c
commit 67c246bbe6
6 changed files with 259 additions and 239 deletions

View File

@ -34370,6 +34370,23 @@ bool X86TargetLowering::SimplifyDemandedVectorEltsForTargetNode(
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, 32> 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);
}
// Extract known zero/undef elements.
// TODO - Propagate input undef/zero elts.
for (int i = 0; i != NumElts; ++i) {

View File

@ -8319,7 +8319,7 @@ define float @test_mm512_reduce_max_ps(<16 x float> %__W) {
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
@ -8336,7 +8336,7 @@ define float @test_mm512_reduce_max_ps(<16 x float> %__W) {
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vzeroupper
; X64-NEXT: retq
@ -8445,7 +8445,7 @@ define float @test_mm512_reduce_min_ps(<16 x float> %__W) {
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
@ -8462,7 +8462,7 @@ define float @test_mm512_reduce_min_ps(<16 x float> %__W) {
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vzeroupper
; X64-NEXT: retq
@ -8623,7 +8623,7 @@ define float @test_mm512_mask_reduce_max_ps(i16 zeroext %__M, <16 x float> %__W)
; X86-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
@ -8643,7 +8643,7 @@ define float @test_mm512_mask_reduce_max_ps(i16 zeroext %__M, <16 x float> %__W)
; X64-NEXT: vmaxps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vzeroupper
; X64-NEXT: retq
@ -8808,7 +8808,7 @@ define float @test_mm512_mask_reduce_min_ps(i16 zeroext %__M, <16 x float> %__W)
; X86-NEXT: vminps %xmm1, %xmm0, %xmm0
; X86-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vmovss %xmm0, (%esp)
; X86-NEXT: flds (%esp)
@ -8828,7 +8828,7 @@ define float @test_mm512_mask_reduce_min_ps(i16 zeroext %__M, <16 x float> %__W)
; X64-NEXT: vminps %xmm1, %xmm0, %xmm0
; X64-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; 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: vzeroupper
; X64-NEXT: retq

View File

@ -285,12 +285,13 @@ define float @extract_lane_insertps_5123(<4 x float> %a0, <4 x float> *%p1) {
define float @extract_lane_insertps_6123(<4 x float> %a0, <4 x float> *%p1) {
; SSE-LABEL: extract_lane_insertps_6123:
; SSE: # %bb.0:
; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-NEXT: movaps (%rdi), %xmm0
; SSE-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; SSE-NEXT: retq
;
; AVX-LABEL: extract_lane_insertps_6123:
; AVX: # %bb.0:
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = mem[1,0]
; AVX-NEXT: retq
%a1 = load <4 x float>, <4 x float> *%p1
%res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 128)

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), %eax
; 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 16(%ecx), %xmm6
; X86-SSE-NEXT: pxor %xmm0, %xmm0
; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; X86-SSE-NEXT: pxor %xmm1, %xmm1
; 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: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[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: pshufd {{.*#+}} xmm0 = xmm5[3,1,2,3]
; X86-SSE-NEXT: movd %xmm0, %eax
; X86-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[3,1,2,3]
; X86-SSE-NEXT: movd %xmm0, %esi
; X86-SSE-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
; X86-SSE-NEXT: movdqa %xmm5, %xmm3
; X86-SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
; X86-SSE-NEXT: movdqa %xmm5, %xmm1
; 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 %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: divl %esi
; X86-SSE-NEXT: movd %edx, %xmm0
; X86-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm5[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 %edx, %xmm1
; X86-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm3[2,3,0,1]
; 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: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; 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 %xmm2, %esi
; X86-SSE-NEXT: xorl %edx, %edx
; 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 %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: xorl %edx, %edx
; X86-SSE-NEXT: divl %esi
; 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: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm7[0]
; X86-SSE-NEXT: movd %xmm1, %eax
; X86-SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm6[0,0]
; 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: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm1[0,0]
; X86-SSE-NEXT: pmuludq %xmm0, %xmm3
; X86-SSE-NEXT: pmuludq %xmm0, %xmm6
; 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: xorl %edx, %edx
; 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: # %bb.0:
; 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 16(%rsi), %xmm6
; X64-SSE-NEXT: pxor %xmm0, %xmm0
; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; X64-SSE-NEXT: pxor %xmm1, %xmm1
; 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: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[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: pshufd {{.*#+}} xmm0 = xmm5[3,1,2,3]
; X64-SSE-NEXT: movd %xmm0, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[3,1,2,3]
; X64-SSE-NEXT: movd %xmm0, %ecx
; X64-SSE-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; X64-SSE-NEXT: movdqa %xmm5, %xmm7
; X64-SSE-NEXT: punpckhwd {{.*#+}} xmm7 = xmm7[4],xmm1[4],xmm7[5],xmm1[5],xmm7[6],xmm1[6],xmm7[7],xmm1[7]
; X64-SSE-NEXT: movdqa %xmm5, %xmm1
; 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 %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: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm8
; X64-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm5[2,3,0,1]
; X64-SSE-NEXT: movd %xmm4, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm6[2,3,0,1]
; X64-SSE-NEXT: movd %xmm4, %ecx
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm7[2,3,0,1]
; X64-SSE-NEXT: movd %xmm1, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm6[2,3,0,1]
; X64-SSE-NEXT: movd %xmm1, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm7
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm8[0],xmm7[1],xmm8[1]
; X64-SSE-NEXT: movd %xmm5, %eax
; X64-SSE-NEXT: movd %edx, %xmm1
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1]
; X64-SSE-NEXT: movd %xmm7, %eax
; X64-SSE-NEXT: movd %xmm6, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm4
; X64-SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm5[1,1,2,3]
; X64-SSE-NEXT: movd %xmm5, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm5 = 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: pshufd {{.*#+}} xmm7 = xmm7[1,1,2,3]
; X64-SSE-NEXT: movd %xmm7, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm6[1,1,2,3]
; X64-SSE-NEXT: movd %xmm6, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm6
; X64-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm3[2,3,0,1]
; X64-SSE-NEXT: movd %xmm7, %eax
; X64-SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm2[2,3,0,1]
; X64-SSE-NEXT: movd %xmm7, %ecx
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm1[0]
; X64-SSE-NEXT: movdqa %xmm5, %xmm1
; 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: divl %ecx
; 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 %xmm2, %ecx
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm0
; X64-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm3[1,1,2,3]
; X64-SSE-NEXT: movd %edx, %xmm1
; 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: 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: xorl %edx, %edx
; X64-SSE-NEXT: divl %ecx
; X64-SSE-NEXT: movd %edx, %xmm2
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm7[0]
; X64-SSE-NEXT: movd %xmm1, %eax
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1]
; X64-SSE-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; X64-SSE-NEXT: movd %xmm0, %eax
; X64-SSE-NEXT: xorl %edx, %edx
; X64-SSE-NEXT: divl 32(%rsi)
; X64-SSE-NEXT: movdqa {{.*#+}} xmm1 = [8199,8199,8199,8199]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm0
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; X64-SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm6[0,0]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm2
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm4
; X64-SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,0],xmm5[0,0]
; X64-SSE-NEXT: movdqa {{.*#+}} xmm0 = [8199,8199,8199,8199]
; X64-SSE-NEXT: pmuludq %xmm0, %xmm7
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm7[0,2,2,3]
; X64-SSE-NEXT: pmuludq %xmm0, %xmm1
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; X64-SSE-NEXT: pmuludq %xmm0, %xmm4
; X64-SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
; X64-SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,0],xmm8[0,0]
; X64-SSE-NEXT: pmuludq %xmm1, %xmm5
; X64-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm5[0,2,2,3]
; X64-SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; X64-SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,0],xmm8[0,0]
; X64-SSE-NEXT: pmuludq %xmm0, %xmm6
; X64-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm6[0,2,2,3]
; 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: movl %eax, (%rax)
; X64-SSE-NEXT: movdqa %xmm2, (%rax)
; X64-SSE-NEXT: movdqa %xmm0, (%rax)
; X64-SSE-NEXT: movdqa %xmm1, (%rax)
; X64-SSE-NEXT: retq
;
; X64-AVX1-LABEL: PR34947:

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: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; 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: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE2-NEXT: movq %xmm0, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE2-NEXT: movq %xmm2, (%rdi)
; SSE2-NEXT: psrad $31, %xmm2
; SSE2-NEXT: pcmpeqd %xmm4, %xmm2
; SSE2-NEXT: pcmpeqd %xmm0, %xmm0
; SSE2-NEXT: pxor %xmm2, %xmm0
; SSE2-NEXT: movd %xmm1, 8(%rdi)
; SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSE2-NEXT: movd %xmm0, 8(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq
;
; 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: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
; 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: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT: movq %xmm0, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSSE3-NEXT: movq %xmm2, (%rdi)
; SSSE3-NEXT: psrad $31, %xmm2
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm2
; SSSE3-NEXT: pcmpeqd %xmm0, %xmm0
; SSSE3-NEXT: pxor %xmm2, %xmm0
; SSSE3-NEXT: movd %xmm1, 8(%rdi)
; SSSE3-NEXT: pcmpeqd %xmm1, %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
; SSSE3-NEXT: movd %xmm0, 8(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: smulo_v3i32:
@ -1767,35 +1767,34 @@ 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: pslld $8, %xmm1
; SSE2-NEXT: psrad $8, %xmm1
; SSE2-NEXT: pxor %xmm4, %xmm4
; SSE2-NEXT: pxor %xmm3, %xmm3
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: pcmpgtd %xmm1, %xmm2
; SSE2-NEXT: pand %xmm0, %xmm2
; SSE2-NEXT: pcmpgtd %xmm0, %xmm4
; SSE2-NEXT: pand %xmm1, %xmm4
; SSE2-NEXT: paddd %xmm2, %xmm4
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
; SSE2-NEXT: pcmpgtd %xmm0, %xmm3
; SSE2-NEXT: pand %xmm1, %xmm3
; SSE2-NEXT: paddd %xmm2, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; 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: pmuludq %xmm5, %xmm2
; SSE2-NEXT: pmuludq %xmm4, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSE2-NEXT: psubd %xmm4, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1]
; SSE2-NEXT: psubd %xmm3, %xmm5
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[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: movdqa %xmm4, %xmm1
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSE2-NEXT: movdqa %xmm3, %xmm1
; SSE2-NEXT: pslld $8, %xmm1
; SSE2-NEXT: psrad $8, %xmm1
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3]
; SSE2-NEXT: psrad $31, %xmm4
; SSE2-NEXT: pcmpeqd %xmm3, %xmm4
; SSE2-NEXT: pcmpeqd %xmm3, %xmm3
; SSE2-NEXT: pxor %xmm3, %xmm4
; SSE2-NEXT: pxor %xmm3, %xmm1
; SSE2-NEXT: por %xmm4, %xmm1
; SSE2-NEXT: pcmpeqd %xmm3, %xmm1
; SSE2-NEXT: psrad $31, %xmm3
; SSE2-NEXT: pcmpeqd %xmm5, %xmm3
; SSE2-NEXT: pcmpeqd %xmm4, %xmm4
; SSE2-NEXT: pxor %xmm4, %xmm3
; SSE2-NEXT: pxor %xmm4, %xmm1
; SSE2-NEXT: por %xmm3, %xmm1
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: movw %ax, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
@ -1805,12 +1804,13 @@ define <4 x i32> @smulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) noun
; SSE2-NEXT: movw %dx, 3(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 2(%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: shrl $16, %ecx
; SSE2-NEXT: movb %cl, 8(%rdi)
; SSE2-NEXT: shrl $16, %edx
; SSE2-NEXT: movb %dl, 5(%rdi)
; SSE2-NEXT: movd %xmm5, %eax
; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0
@ -1822,35 +1822,34 @@ 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: pslld $8, %xmm1
; SSSE3-NEXT: psrad $8, %xmm1
; SSSE3-NEXT: pxor %xmm4, %xmm4
; SSSE3-NEXT: pxor %xmm3, %xmm3
; SSSE3-NEXT: pxor %xmm2, %xmm2
; SSSE3-NEXT: pcmpgtd %xmm1, %xmm2
; SSSE3-NEXT: pand %xmm0, %xmm2
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm4
; SSSE3-NEXT: pand %xmm1, %xmm4
; SSSE3-NEXT: paddd %xmm2, %xmm4
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm0[1,1,3,3]
; SSSE3-NEXT: pcmpgtd %xmm0, %xmm3
; SSSE3-NEXT: pand %xmm1, %xmm3
; SSSE3-NEXT: paddd %xmm2, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; 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: pmuludq %xmm5, %xmm2
; SSSE3-NEXT: pmuludq %xmm4, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSSE3-NEXT: psubd %xmm4, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm1[0],xmm5[1],xmm1[1]
; SSSE3-NEXT: psubd %xmm3, %xmm5
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[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: movdqa %xmm4, %xmm1
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSSE3-NEXT: movdqa %xmm3, %xmm1
; SSSE3-NEXT: pslld $8, %xmm1
; SSSE3-NEXT: psrad $8, %xmm1
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm5 = xmm4[3,1,2,3]
; SSSE3-NEXT: psrad $31, %xmm4
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm4
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm3
; SSSE3-NEXT: pxor %xmm3, %xmm4
; SSSE3-NEXT: pxor %xmm3, %xmm1
; SSSE3-NEXT: por %xmm4, %xmm1
; SSSE3-NEXT: pcmpeqd %xmm3, %xmm1
; SSSE3-NEXT: psrad $31, %xmm3
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm3
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm4
; SSSE3-NEXT: pxor %xmm4, %xmm3
; SSSE3-NEXT: pxor %xmm4, %xmm1
; SSSE3-NEXT: por %xmm3, %xmm1
; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: movw %ax, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
@ -1860,12 +1859,13 @@ define <4 x i32> @smulo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) noun
; SSSE3-NEXT: movw %dx, 3(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 2(%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: shrl $16, %ecx
; SSSE3-NEXT: movb %cl, 8(%rdi)
; SSSE3-NEXT: shrl $16, %edx
; SSSE3-NEXT: movb %dl, 5(%rdi)
; SSSE3-NEXT: movd %xmm5, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0

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 %xmm1, %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm1
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT: movd %xmm2, 8(%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: 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 %xmm1, %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm4[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSSE3-NEXT: movd %xmm2, 8(%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: retq
;
@ -1567,90 +1563,90 @@ 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 {
; SSE2-LABEL: umulo_v4i24:
; 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: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm0
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm4, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0]
; SSE2-NEXT: pand %xmm0, %xmm1
; SSE2-NEXT: pand %xmm0, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm1, %xmm2
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,3,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSE2-NEXT: pmuludq %xmm0, %xmm1
; 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: pcmpeqd %xmm4, %xmm3
; SSE2-NEXT: pcmpeqd %xmm5, %xmm5
; SSE2-NEXT: pxor %xmm5, %xmm3
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm2[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1]
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm1[3,1,2,3]
; SSE2-NEXT: psrld $24, %xmm1
; SSE2-NEXT: pcmpeqd %xmm4, %xmm1
; SSE2-NEXT: pxor %xmm5, %xmm1
; SSE2-NEXT: por %xmm3, %xmm1
; SSE2-NEXT: movd %xmm0, %eax
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSE2-NEXT: pshufd {{.*#+}} xmm6 = xmm1[0,2,2,3]
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
; SSE2-NEXT: psrld $24, %xmm0
; SSE2-NEXT: pcmpeqd %xmm4, %xmm0
; SSE2-NEXT: pxor %xmm5, %xmm0
; SSE2-NEXT: por %xmm3, %xmm0
; SSE2-NEXT: movd %xmm2, %eax
; SSE2-NEXT: movw %ax, (%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE2-NEXT: movd %xmm0, %ecx
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSE2-NEXT: movd %xmm2, %ecx
; SSE2-NEXT: movw %cx, 6(%rdi)
; SSE2-NEXT: movd %xmm2, %edx
; SSE2-NEXT: movd %xmm1, %edx
; SSE2-NEXT: movw %dx, 3(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 2(%rdi)
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
; SSE2-NEXT: movd %xmm1, %eax
; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: shrl $16, %ecx
; SSE2-NEXT: movb %cl, 8(%rdi)
; SSE2-NEXT: shrl $16, %edx
; SSE2-NEXT: movb %dl, 5(%rdi)
; SSE2-NEXT: movd %xmm6, %eax
; SSE2-NEXT: movw %ax, 9(%rdi)
; SSE2-NEXT: shrl $16, %eax
; SSE2-NEXT: movb %al, 11(%rdi)
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: umulo_v4i24:
; 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: pand %xmm2, %xmm1
; SSSE3-NEXT: pand %xmm2, %xmm0
; SSSE3-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm1, %xmm0
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm4, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,3,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1]
; SSSE3-NEXT: movdqa %xmm0, %xmm2
; SSSE3-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,0,255,255,255,0,255,255,255,0,255,255,255,0]
; SSSE3-NEXT: pand %xmm0, %xmm1
; SSSE3-NEXT: pand %xmm0, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm1, %xmm2
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm2[1,3,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm0, %xmm1
; 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: pcmpeqd %xmm4, %xmm3
; SSSE3-NEXT: pcmpeqd %xmm5, %xmm5
; SSSE3-NEXT: pxor %xmm5, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm2[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm6[0],xmm1[1],xmm6[1]
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm1[3,1,2,3]
; SSSE3-NEXT: psrld $24, %xmm1
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm1
; SSSE3-NEXT: pxor %xmm5, %xmm1
; SSSE3-NEXT: por %xmm3, %xmm1
; SSSE3-NEXT: movd %xmm0, %eax
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm2[0,2,2,3]
; SSSE3-NEXT: pshufd {{.*#+}} xmm6 = xmm1[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1]
; SSSE3-NEXT: psrld $24, %xmm0
; SSSE3-NEXT: pcmpeqd %xmm4, %xmm0
; SSSE3-NEXT: pxor %xmm5, %xmm0
; SSSE3-NEXT: por %xmm3, %xmm0
; SSSE3-NEXT: movd %xmm2, %eax
; SSSE3-NEXT: movw %ax, (%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSSE3-NEXT: movd %xmm0, %ecx
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
; SSSE3-NEXT: movd %xmm2, %ecx
; SSSE3-NEXT: movw %cx, 6(%rdi)
; SSSE3-NEXT: movd %xmm2, %edx
; SSSE3-NEXT: movd %xmm1, %edx
; SSSE3-NEXT: movw %dx, 3(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 2(%rdi)
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
; SSSE3-NEXT: movd %xmm1, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: shrl $16, %ecx
; SSSE3-NEXT: movb %cl, 8(%rdi)
; SSSE3-NEXT: shrl $16, %edx
; SSSE3-NEXT: movb %dl, 5(%rdi)
; SSSE3-NEXT: movd %xmm6, %eax
; SSSE3-NEXT: movw %ax, 9(%rdi)
; SSSE3-NEXT: shrl $16, %eax
; SSSE3-NEXT: movb %al, 11(%rdi)
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: umulo_v4i24: