[llvm] 35a9631 - [X86][SelectionDAG] Handle the case for gather where index is SHL (#139703)
via llvm-commits
llvm-commits at lists.llvm.org
Mon May 19 09:12:52 PDT 2025
Author: Rohit Aggarwal
Date: 2025-05-19T17:12:48+01:00
New Revision: 35a9631279268b6d3d0f0826da0c09e78db6529a
URL: https://github.com/llvm/llvm-project/commit/35a9631279268b6d3d0f0826da0c09e78db6529a
DIFF: https://github.com/llvm/llvm-project/commit/35a9631279268b6d3d0f0826da0c09e78db6529a.diff
LOG: [X86][SelectionDAG] Handle the case for gather where index is SHL (#139703)
Fix the Gather's Index for SHL Opcode in which shift amount is 4 or greater.
It is in the continuity of #137813
---------
Co-authored-by: Rohit Aggarwal <Rohit.Aggarwal at amd.com>
Co-authored-by: Simon Pilgrim <llvm-dev at redking.me.uk>
Added:
Modified:
llvm/lib/Target/X86/X86ISelLowering.cpp
llvm/test/CodeGen/X86/masked_gather_scatter.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 3b6b0d7b86c9c..df305637b1e4b 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -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 =
diff --git a/llvm/test/CodeGen/X86/masked_gather_scatter.ll b/llvm/test/CodeGen/X86/masked_gather_scatter.ll
index a5c727e8df9d6..af018d83d520e 100644
--- a/llvm/test/CodeGen/X86/masked_gather_scatter.ll
+++ b/llvm/test/CodeGen/X86/masked_gather_scatter.ll
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
@@ -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:
More information about the llvm-commits
mailing list