Skip to content

[X86][SelectionDAG] Handle the case for gather where index is SHL #139703

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
May 19, 2025
Merged

[X86][SelectionDAG] Handle the case for gather where index is SHL #139703

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
2b79bbe
Handle the case for gather where index is SHL
May 13, 2025
5d2d469
Merge branch 'gatherSHLIndex' of github.com:rohitaggarwal007/llvm-pro…
May 13, 2025
9606a43
fix the test cases
May 13, 2025
c8ec5f8
fix formatting issue
May 13, 2025
91e3edf
Remove the compute number of sign bits and allow scale update
May 14, 2025
6b64ad5
Merge branch 'llvm:main' into gatherSHLIndex
rohitaggarwal007 May 16, 2025
d88e43f
Merge branch 'main' into gatherSHLIndex
RKSimon May 16, 2025
e0626d2
Fix the test cases
May 16, 2025
6540a08
Merge branch 'llvm:main' into gatherSHLIndex
rohitaggarwal007 May 19, 2025
e87eb2d
Remove the redundant condition
May 19, 2025
0aed7cb
Merge branch 'main' into gatherSHLIndex
RKSimon May 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56725,7 +56725,7 @@ static SDValue combineGatherScatter(SDNode *N, SelectionDAG &DAG,
return SDValue(N, 0);
}
if (auto MinShAmt = DAG.getValidMinimumShiftAmount(Index)) {
if (*MinShAmt >= 1 && (*MinShAmt + Log2ScaleAmt) < 4 &&
if (*MinShAmt >= 1 && Log2ScaleAmt < 3 &&
DAG.ComputeNumSignBits(Index.getOperand(0)) > 1) {
SDValue ShAmt = Index.getOperand(1);
SDValue NewShAmt =
Expand Down
144 changes: 33 additions & 111 deletions llvm/test/CodeGen/X86/masked_gather_scatter.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4808,16 +4808,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index(ptr %x, ptr %arr, <16
; X64-KNL-NEXT: vptestmd %zmm0, %zmm0, %k1
; X64-KNL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-KNL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-KNL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-KNL-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-KNL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-KNL-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-KNL-NEXT: kshiftrw $8, %k1, %k2
; X64-KNL-NEXT: vgatherqps (%rdi,%zmm2), %ymm3 {%k2}
; X64-KNL-NEXT: vgatherqps (%rdi,%zmm0), %ymm1 {%k1}
; X64-KNL-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-KNL-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-KNL-NEXT: vgatherdps (%rdi,%zmm0,8), %zmm1 {%k1}
; X64-KNL-NEXT: vmovaps %zmm1, %zmm0
; X64-KNL-NEXT: retq
;
; X86-KNL-LABEL: test_gather_structpt_16f32_mask_index:
Expand All @@ -4839,16 +4832,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index(ptr %x, ptr %arr, <16
; X64-SKX-SMALL-NEXT: vpmovd2m %zmm0, %k1
; X64-SKX-SMALL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-SMALL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-SMALL-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-SKX-SMALL-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-SMALL-NEXT: vgatherqps (%rdi,%zmm2), %ymm3 {%k2}
; X64-SKX-SMALL-NEXT: vgatherqps (%rdi,%zmm0), %ymm1 {%k1}
; X64-SKX-SMALL-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-SKX-SMALL-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vgatherdps (%rdi,%zmm0,8), %zmm1 {%k1}
; X64-SKX-SMALL-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-SMALL-NEXT: retq
;
; X64-SKX-LARGE-LABEL: test_gather_structpt_16f32_mask_index:
Expand All @@ -4859,16 +4845,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index(ptr %x, ptr %arr, <16
; X64-SKX-LARGE-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-LARGE-NEXT: movabsq ${{\.?LCPI[0-9]+_[0-9]+}}, %rax
; X64-SKX-LARGE-NEXT: vpandd (%rax){1to16}, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-LARGE-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-SKX-LARGE-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-LARGE-NEXT: vgatherqps (%rdi,%zmm2), %ymm3 {%k2}
; X64-SKX-LARGE-NEXT: vgatherqps (%rdi,%zmm0), %ymm1 {%k1}
; X64-SKX-LARGE-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-SKX-LARGE-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vgatherdps (%rdi,%zmm0,8), %zmm1 {%k1}
; X64-SKX-LARGE-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-LARGE-NEXT: retq
;
; X86-SKX-LABEL: test_gather_structpt_16f32_mask_index:
Expand Down Expand Up @@ -4898,16 +4877,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index_offset(ptr %x, ptr %a
; X64-KNL-NEXT: vptestmd %zmm0, %zmm0, %k1
; X64-KNL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-KNL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-KNL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-KNL-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-KNL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-KNL-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-KNL-NEXT: kshiftrw $8, %k1, %k2
; X64-KNL-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm3 {%k2}
; X64-KNL-NEXT: vgatherqps 4(%rdi,%zmm0), %ymm1 {%k1}
; X64-KNL-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-KNL-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-KNL-NEXT: vgatherdps 4(%rdi,%zmm0,8), %zmm1 {%k1}
; X64-KNL-NEXT: vmovaps %zmm1, %zmm0
; X64-KNL-NEXT: retq
;
; X86-KNL-LABEL: test_gather_structpt_16f32_mask_index_offset:
Expand All @@ -4929,16 +4901,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index_offset(ptr %x, ptr %a
; X64-SKX-SMALL-NEXT: vpmovd2m %zmm0, %k1
; X64-SKX-SMALL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-SMALL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-SMALL-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-SKX-SMALL-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-SMALL-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm3 {%k2}
; X64-SKX-SMALL-NEXT: vgatherqps 4(%rdi,%zmm0), %ymm1 {%k1}
; X64-SKX-SMALL-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-SKX-SMALL-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vgatherdps 4(%rdi,%zmm0,8), %zmm1 {%k1}
; X64-SKX-SMALL-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-SMALL-NEXT: retq
;
; X64-SKX-LARGE-LABEL: test_gather_structpt_16f32_mask_index_offset:
Expand All @@ -4949,16 +4914,9 @@ define <16 x float> @test_gather_structpt_16f32_mask_index_offset(ptr %x, ptr %a
; X64-SKX-LARGE-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-LARGE-NEXT: movabsq ${{\.?LCPI[0-9]+_[0-9]+}}, %rax
; X64-SKX-LARGE-NEXT: vpandd (%rax){1to16}, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-LARGE-NEXT: vextractf64x4 $1, %zmm1, %ymm3
; X64-SKX-LARGE-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-LARGE-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm3 {%k2}
; X64-SKX-LARGE-NEXT: vgatherqps 4(%rdi,%zmm0), %ymm1 {%k1}
; X64-SKX-LARGE-NEXT: vinsertf64x4 $1, %ymm3, %zmm1, %zmm0
; X64-SKX-LARGE-NEXT: vpaddd %zmm0, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vgatherdps 4(%rdi,%zmm0,8), %zmm1 {%k1}
; X64-SKX-LARGE-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-LARGE-NEXT: retq
;
; X86-SKX-LABEL: test_gather_structpt_16f32_mask_index_offset:
Expand Down Expand Up @@ -4988,23 +4946,11 @@ define {<16 x float>, <16 x float>} @test_gather_structpt_16f32_mask_index_pair(
; X64-KNL-NEXT: vptestmd %zmm0, %zmm0, %k1
; X64-KNL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-KNL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-KNL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-KNL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-KNL-NEXT: vpsllq $4, %zmm0, %zmm3
; X64-KNL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-KNL-NEXT: vextractf64x4 $1, %zmm1, %ymm4
; X64-KNL-NEXT: kshiftrw $8, %k1, %k2
; X64-KNL-NEXT: kmovw %k2, %k3
; X64-KNL-NEXT: vmovaps %ymm4, %ymm0
; X64-KNL-NEXT: vgatherqps (%rdi,%zmm2), %ymm0 {%k3}
; X64-KNL-NEXT: vmovaps %ymm1, %ymm5
; X64-KNL-NEXT: kmovw %k1, %k3
; X64-KNL-NEXT: vgatherqps (%rdi,%zmm3), %ymm5 {%k3}
; X64-KNL-NEXT: vinsertf64x4 $1, %ymm0, %zmm5, %zmm0
; X64-KNL-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm4 {%k2}
; X64-KNL-NEXT: vgatherqps 4(%rdi,%zmm3), %ymm1 {%k1}
; X64-KNL-NEXT: vinsertf64x4 $1, %ymm4, %zmm1, %zmm1
; X64-KNL-NEXT: vpaddd %zmm0, %zmm0, %zmm2
; X64-KNL-NEXT: kmovw %k1, %k2
; X64-KNL-NEXT: vmovaps %zmm1, %zmm0
; X64-KNL-NEXT: vgatherdps (%rdi,%zmm2,8), %zmm0 {%k2}
; X64-KNL-NEXT: vgatherdps 4(%rdi,%zmm2,8), %zmm1 {%k1}
; X64-KNL-NEXT: retq
;
; X86-KNL-LABEL: test_gather_structpt_16f32_mask_index_pair:
Expand All @@ -5028,23 +4974,11 @@ define {<16 x float>, <16 x float>} @test_gather_structpt_16f32_mask_index_pair(
; X64-SKX-SMALL-NEXT: vpmovd2m %zmm0, %k1
; X64-SKX-SMALL-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-SMALL-NEXT: vpandd {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to16}, %zmm0, %zmm0
; X64-SKX-SMALL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-SMALL-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm0, %zmm3
; X64-SKX-SMALL-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-SMALL-NEXT: vextractf64x4 $1, %zmm1, %ymm4
; X64-SKX-SMALL-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-SMALL-NEXT: kmovw %k2, %k3
; X64-SKX-SMALL-NEXT: vmovaps %ymm4, %ymm0
; X64-SKX-SMALL-NEXT: vgatherqps (%rdi,%zmm2), %ymm0 {%k3}
; X64-SKX-SMALL-NEXT: vmovaps %ymm1, %ymm5
; X64-SKX-SMALL-NEXT: kmovw %k1, %k3
; X64-SKX-SMALL-NEXT: vgatherqps (%rdi,%zmm3), %ymm5 {%k3}
; X64-SKX-SMALL-NEXT: vinsertf64x4 $1, %ymm0, %zmm5, %zmm0
; X64-SKX-SMALL-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm4 {%k2}
; X64-SKX-SMALL-NEXT: vgatherqps 4(%rdi,%zmm3), %ymm1 {%k1}
; X64-SKX-SMALL-NEXT: vinsertf64x4 $1, %ymm4, %zmm1, %zmm1
; X64-SKX-SMALL-NEXT: vpaddd %zmm0, %zmm0, %zmm2
; X64-SKX-SMALL-NEXT: kmovw %k1, %k2
; X64-SKX-SMALL-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-SMALL-NEXT: vgatherdps (%rdi,%zmm2,8), %zmm0 {%k2}
; X64-SKX-SMALL-NEXT: vgatherdps 4(%rdi,%zmm2,8), %zmm1 {%k1}
; X64-SKX-SMALL-NEXT: retq
;
; X64-SKX-LARGE-LABEL: test_gather_structpt_16f32_mask_index_pair:
Expand All @@ -5055,23 +4989,11 @@ define {<16 x float>, <16 x float>} @test_gather_structpt_16f32_mask_index_pair(
; X64-SKX-LARGE-NEXT: vmovdqu64 (%rsi), %zmm0
; X64-SKX-LARGE-NEXT: movabsq ${{\.?LCPI[0-9]+_[0-9]+}}, %rax
; X64-SKX-LARGE-NEXT: vpandd (%rax){1to16}, %zmm0, %zmm0
; X64-SKX-LARGE-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm2 = ymm2[0],zero,ymm2[1],zero,ymm2[2],zero,ymm2[3],zero,ymm2[4],zero,ymm2[5],zero,ymm2[6],zero,ymm2[7],zero
; X64-SKX-LARGE-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm0, %zmm3
; X64-SKX-LARGE-NEXT: vpsllq $4, %zmm2, %zmm2
; X64-SKX-LARGE-NEXT: vextractf64x4 $1, %zmm1, %ymm4
; X64-SKX-LARGE-NEXT: kshiftrw $8, %k1, %k2
; X64-SKX-LARGE-NEXT: vmovaps %ymm4, %ymm0
; X64-SKX-LARGE-NEXT: kmovw %k2, %k3
; X64-SKX-LARGE-NEXT: vgatherqps (%rdi,%zmm2), %ymm0 {%k3}
; X64-SKX-LARGE-NEXT: vmovaps %ymm1, %ymm5
; X64-SKX-LARGE-NEXT: kmovw %k1, %k3
; X64-SKX-LARGE-NEXT: vgatherqps (%rdi,%zmm3), %ymm5 {%k3}
; X64-SKX-LARGE-NEXT: vinsertf64x4 $1, %ymm0, %zmm5, %zmm0
; X64-SKX-LARGE-NEXT: vgatherqps 4(%rdi,%zmm2), %ymm4 {%k2}
; X64-SKX-LARGE-NEXT: vgatherqps 4(%rdi,%zmm3), %ymm1 {%k1}
; X64-SKX-LARGE-NEXT: vinsertf64x4 $1, %ymm4, %zmm1, %zmm1
; X64-SKX-LARGE-NEXT: vpaddd %zmm0, %zmm0, %zmm2
; X64-SKX-LARGE-NEXT: kmovw %k1, %k2
; X64-SKX-LARGE-NEXT: vmovaps %zmm1, %zmm0
; X64-SKX-LARGE-NEXT: vgatherdps (%rdi,%zmm2,8), %zmm0 {%k2}
; X64-SKX-LARGE-NEXT: vgatherdps 4(%rdi,%zmm2,8), %zmm1 {%k1}
; X64-SKX-LARGE-NEXT: retq
;
; X86-SKX-LABEL: test_gather_structpt_16f32_mask_index_pair:
Expand Down