maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/masked_gather_scatter_widen.ll

477 lines
21 KiB
LLVM
Raw Normal View History

[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq -x86-experimental-vector-widening-legalization < %s | FileCheck %s --check-prefix=CHECK --check-prefix=WIDEN --check-prefix=WIDEN_SKX
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f -x86-experimental-vector-widening-legalization < %s | FileCheck %s --check-prefix=CHECK --check-prefix=WIDEN --check-prefix=WIDEN_KNL
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=CHECK --check-prefix=PROMOTE --check-prefix=PROMOTE_SKX
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s --check-prefix=CHECK --check-prefix=PROMOTE --check-prefix=PROMOTE_KNL
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake -x86-experimental-vector-widening-legalization < %s | FileCheck %s --check-prefix=WIDEN_AVX2
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake < %s | FileCheck %s --check-prefix=PROMOTE_AVX2
define <2 x double> @test_gather_v2i32_index(double* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x double> %src0) {
; WIDEN_SKX-LABEL: test_gather_v2i32_index:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_SKX-NEXT: vpmovq2m %xmm1, %k1
; WIDEN_SKX-NEXT: vgatherdpd (%rdi,%xmm0,8), %xmm2 {%k1}
; WIDEN_SKX-NEXT: vmovapd %xmm2, %xmm0
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_gather_v2i32_index:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vgatherdpd (%rdi,%ymm0,8), %zmm2 {%k1}
; WIDEN_KNL-NEXT: vmovapd %xmm2, %xmm0
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_gather_v2i32_index:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $32, %xmm0, %xmm0
; PROMOTE_SKX-NEXT: vpsraq $32, %xmm0, %xmm0
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_SKX-NEXT: vpmovq2m %xmm1, %k1
; PROMOTE_SKX-NEXT: vgatherqpd (%rdi,%xmm0,8), %xmm2 {%k1}
; PROMOTE_SKX-NEXT: vmovapd %xmm2, %xmm0
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_gather_v2i32_index:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; PROMOTE_KNL-NEXT: vpsllq $32, %xmm0, %xmm0
; PROMOTE_KNL-NEXT: vpsraq $32, %zmm0, %zmm0
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vgatherqpd (%rdi,%zmm0,8), %zmm2 {%k1}
; PROMOTE_KNL-NEXT: vmovapd %xmm2, %xmm0
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_gather_v2i32_index:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vgatherdpd %xmm1, (%rdi,%xmm0,8), %xmm2
; WIDEN_AVX2-NEXT: vmovapd %xmm2, %xmm0
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_gather_v2i32_index:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpsllq $32, %xmm0, %xmm3
; PROMOTE_AVX2-NEXT: vpsrad $31, %xmm3, %xmm3
; PROMOTE_AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm3[1],xmm0[2],xmm3[3]
; PROMOTE_AVX2-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_AVX2-NEXT: vgatherqpd %xmm1, (%rdi,%xmm0,8), %xmm2
; PROMOTE_AVX2-NEXT: vmovapd %xmm2, %xmm0
; PROMOTE_AVX2-NEXT: retq
%gep.random = getelementptr double, double* %base, <2 x i32> %ind
%res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %gep.random, i32 4, <2 x i1> %mask, <2 x double> %src0)
ret <2 x double> %res
}
define void @test_scatter_v2i32_index(<2 x double> %a1, double* %base, <2 x i32> %ind, <2 x i1> %mask) {
; WIDEN_SKX-LABEL: test_scatter_v2i32_index:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_SKX-NEXT: vpmovq2m %xmm2, %k1
; WIDEN_SKX-NEXT: vscatterdpd %xmm0, (%rdi,%xmm1,8) {%k1}
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_scatter_v2i32_index:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vscatterdpd %zmm0, (%rdi,%ymm1,8) {%k1}
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_scatter_v2i32_index:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_SKX-NEXT: vpmovq2m %xmm2, %k1
; PROMOTE_SKX-NEXT: vpsllq $32, %xmm1, %xmm1
; PROMOTE_SKX-NEXT: vpsraq $32, %xmm1, %xmm1
; PROMOTE_SKX-NEXT: vscatterqpd %xmm0, (%rdi,%xmm1,8) {%k1}
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_scatter_v2i32_index:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; PROMOTE_KNL-NEXT: vpsllq $32, %xmm1, %xmm1
; PROMOTE_KNL-NEXT: vpsraq $32, %zmm1, %zmm1
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vscatterqpd %zmm0, (%rdi,%zmm1,8) {%k1}
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_scatter_v2i32_index:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vpmovsxdq %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vpsllq $3, %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vmovq %rdi, %xmm3
; WIDEN_AVX2-NEXT: vpbroadcastq %xmm3, %xmm3
; WIDEN_AVX2-NEXT: vpaddq %xmm1, %xmm3, %xmm1
; WIDEN_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
; WIDEN_AVX2-NEXT: je .LBB1_2
; WIDEN_AVX2-NEXT: # %bb.1: # %cond.store
; WIDEN_AVX2-NEXT: vmovq %xmm1, %rax
; WIDEN_AVX2-NEXT: vmovlpd %xmm0, (%rax)
; WIDEN_AVX2-NEXT: .LBB1_2: # %else
; WIDEN_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: je .LBB1_4
; WIDEN_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; WIDEN_AVX2-NEXT: vmovhpd %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: .LBB1_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_scatter_v2i32_index:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpsllq $32, %xmm1, %xmm3
; PROMOTE_AVX2-NEXT: vpsrad $31, %xmm3, %xmm3
; PROMOTE_AVX2-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm3[1],xmm1[2],xmm3[3]
; PROMOTE_AVX2-NEXT: vpsllq $3, %xmm1, %xmm1
; PROMOTE_AVX2-NEXT: vmovq %rdi, %xmm3
; PROMOTE_AVX2-NEXT: vpbroadcastq %xmm3, %xmm3
; PROMOTE_AVX2-NEXT: vpaddq %xmm1, %xmm3, %xmm1
; PROMOTE_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
; PROMOTE_AVX2-NEXT: je .LBB1_2
; PROMOTE_AVX2-NEXT: # %bb.1: # %cond.store
; PROMOTE_AVX2-NEXT: vmovq %xmm1, %rax
; PROMOTE_AVX2-NEXT: vmovlpd %xmm0, (%rax)
; PROMOTE_AVX2-NEXT: .LBB1_2: # %else
; PROMOTE_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: je .LBB1_4
; PROMOTE_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; PROMOTE_AVX2-NEXT: vmovhpd %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: .LBB1_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: retq
%gep = getelementptr double, double *%base, <2 x i32> %ind
call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> %a1, <2 x double*> %gep, i32 4, <2 x i1> %mask)
ret void
}
define <2 x i32> @test_gather_v2i32_data(<2 x i32*> %ptr, <2 x i1> %mask, <2 x i32> %src0) {
; WIDEN_SKX-LABEL: test_gather_v2i32_data:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_SKX-NEXT: vpmovq2m %xmm1, %k1
; WIDEN_SKX-NEXT: vpgatherqd (,%xmm0), %xmm2 {%k1}
; WIDEN_SKX-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_gather_v2i32_data:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm2 killed $xmm2 def $ymm2
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vpgatherqd (,%zmm0), %ymm2 {%k1}
; WIDEN_KNL-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_gather_v2i32_data:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_SKX-NEXT: vpmovq2m %xmm1, %k1
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; PROMOTE_SKX-NEXT: vpgatherqd (,%xmm0), %xmm1 {%k1}
; PROMOTE_SKX-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_gather_v2i32_data:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vpgatherqd (,%zmm0), %ymm1 {%k1}
; PROMOTE_KNL-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_gather_v2i32_data:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; WIDEN_AVX2-NEXT: vpslld $31, %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vpgatherqd %xmm1, (,%xmm0), %xmm2
; WIDEN_AVX2-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_gather_v2i32_data:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; PROMOTE_AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; PROMOTE_AVX2-NEXT: vpslld $31, %xmm1, %xmm1
; PROMOTE_AVX2-NEXT: vpgatherqd %xmm1, (,%xmm0), %xmm2
; PROMOTE_AVX2-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero
; PROMOTE_AVX2-NEXT: retq
%res = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> %ptr, i32 4, <2 x i1> %mask, <2 x i32> %src0)
ret <2 x i32>%res
}
define void @test_scatter_v2i32_data(<2 x i32>%a1, <2 x i32*> %ptr, <2 x i1>%mask) {
; WIDEN_SKX-LABEL: test_scatter_v2i32_data:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_SKX-NEXT: vpmovq2m %xmm2, %k1
; WIDEN_SKX-NEXT: vpscatterqd %xmm0, (,%xmm1) {%k1}
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_scatter_v2i32_data:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vpscatterqd %ymm0, (,%zmm1) {%k1}
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_scatter_v2i32_data:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_SKX-NEXT: vpmovq2m %xmm2, %k1
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_SKX-NEXT: vpscatterqd %xmm0, (,%xmm1) {%k1}
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_scatter_v2i32_data:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vpscatterqd %ymm0, (,%zmm1) {%k1}
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_scatter_v2i32_data:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
; WIDEN_AVX2-NEXT: je .LBB3_2
; WIDEN_AVX2-NEXT: # %bb.1: # %cond.store
; WIDEN_AVX2-NEXT: vmovq %xmm1, %rax
; WIDEN_AVX2-NEXT: vmovss %xmm0, (%rax)
; WIDEN_AVX2-NEXT: .LBB3_2: # %else
; WIDEN_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: je .LBB3_4
; WIDEN_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; WIDEN_AVX2-NEXT: vextractps $1, %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: .LBB3_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_scatter_v2i32_data:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
; PROMOTE_AVX2-NEXT: je .LBB3_2
; PROMOTE_AVX2-NEXT: # %bb.1: # %cond.store
; PROMOTE_AVX2-NEXT: vmovq %xmm1, %rax
; PROMOTE_AVX2-NEXT: vmovss %xmm0, (%rax)
; PROMOTE_AVX2-NEXT: .LBB3_2: # %else
; PROMOTE_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: je .LBB3_4
; PROMOTE_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; PROMOTE_AVX2-NEXT: vextractps $2, %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: .LBB3_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: retq
call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> %a1, <2 x i32*> %ptr, i32 4, <2 x i1> %mask)
ret void
}
define <2 x i32> @test_gather_v2i32_data_index(i32* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x i32> %src0) {
; WIDEN_SKX-LABEL: test_gather_v2i32_data_index:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_SKX-NEXT: vpmovq2m %xmm1, %k1
; WIDEN_SKX-NEXT: vpgatherdd (%rdi,%xmm0,4), %xmm2 {%k1}
; WIDEN_SKX-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_gather_v2i32_data_index:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; WIDEN_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vpgatherdd (%rdi,%zmm0,4), %zmm2 {%k1}
; WIDEN_KNL-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_gather_v2i32_data_index:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_SKX-NEXT: vpmovq2m %xmm1, %k1
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; PROMOTE_SKX-NEXT: vpgatherdd (%rdi,%xmm0,4), %xmm1 {%k1}
; PROMOTE_SKX-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_gather_v2i32_data_index:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm1, %xmm1
; PROMOTE_KNL-NEXT: vptestmq %zmm1, %zmm1, %k0
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k1}
; PROMOTE_KNL-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_gather_v2i32_data_index:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,2],zero,zero
; WIDEN_AVX2-NEXT: vpslld $31, %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vpgatherdd %xmm1, (%rdi,%xmm0,4), %xmm2
; WIDEN_AVX2-NEXT: vmovdqa %xmm2, %xmm0
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_gather_v2i32_data_index:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; PROMOTE_AVX2-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,2],zero,zero
; PROMOTE_AVX2-NEXT: vpslld $31, %xmm1, %xmm1
; PROMOTE_AVX2-NEXT: vpgatherdd %xmm1, (%rdi,%xmm0,4), %xmm2
; PROMOTE_AVX2-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero
; PROMOTE_AVX2-NEXT: retq
%gep.random = getelementptr i32, i32* %base, <2 x i32> %ind
%res = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> %gep.random, i32 4, <2 x i1> %mask, <2 x i32> %src0)
ret <2 x i32> %res
}
define void @test_scatter_v2i32_data_index(<2 x i32> %a1, i32* %base, <2 x i32> %ind, <2 x i1> %mask) {
; WIDEN_SKX-LABEL: test_scatter_v2i32_data_index:
; WIDEN_SKX: # %bb.0:
; WIDEN_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_SKX-NEXT: vpmovq2m %xmm2, %k1
; WIDEN_SKX-NEXT: vpscatterdd %xmm0, (%rdi,%xmm1,4) {%k1}
; WIDEN_SKX-NEXT: retq
;
; WIDEN_KNL-LABEL: test_scatter_v2i32_data_index:
; WIDEN_KNL: # %bb.0:
; WIDEN_KNL-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
; WIDEN_KNL-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; WIDEN_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; WIDEN_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; WIDEN_KNL-NEXT: kshiftlw $14, %k0, %k0
; WIDEN_KNL-NEXT: kshiftrw $14, %k0, %k1
; WIDEN_KNL-NEXT: vpscatterdd %zmm0, (%rdi,%zmm1,4) {%k1}
; WIDEN_KNL-NEXT: vzeroupper
; WIDEN_KNL-NEXT: retq
;
; PROMOTE_SKX-LABEL: test_scatter_v2i32_data_index:
; PROMOTE_SKX: # %bb.0:
; PROMOTE_SKX-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_SKX-NEXT: vpmovq2m %xmm2, %k1
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_SKX-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; PROMOTE_SKX-NEXT: vpscatterdd %xmm0, (%rdi,%xmm1,4) {%k1}
; PROMOTE_SKX-NEXT: retq
;
; PROMOTE_KNL-LABEL: test_scatter_v2i32_data_index:
; PROMOTE_KNL: # %bb.0:
; PROMOTE_KNL-NEXT: vpsllq $63, %xmm2, %xmm2
; PROMOTE_KNL-NEXT: vptestmq %zmm2, %zmm2, %k0
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; PROMOTE_KNL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; PROMOTE_KNL-NEXT: kshiftlw $14, %k0, %k0
; PROMOTE_KNL-NEXT: kshiftrw $14, %k0, %k1
; PROMOTE_KNL-NEXT: vpscatterdd %zmm0, (%rdi,%zmm1,4) {%k1}
; PROMOTE_KNL-NEXT: vzeroupper
; PROMOTE_KNL-NEXT: retq
;
; WIDEN_AVX2-LABEL: test_scatter_v2i32_data_index:
; WIDEN_AVX2: # %bb.0:
; WIDEN_AVX2-NEXT: vpmovsxdq %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vpsllq $2, %xmm1, %xmm1
; WIDEN_AVX2-NEXT: vmovq %rdi, %xmm3
; WIDEN_AVX2-NEXT: vpbroadcastq %xmm3, %xmm3
; WIDEN_AVX2-NEXT: vpaddq %xmm1, %xmm3, %xmm1
; WIDEN_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
; WIDEN_AVX2-NEXT: je .LBB5_2
; WIDEN_AVX2-NEXT: # %bb.1: # %cond.store
; WIDEN_AVX2-NEXT: vmovq %xmm1, %rax
; WIDEN_AVX2-NEXT: vmovss %xmm0, (%rax)
; WIDEN_AVX2-NEXT: .LBB5_2: # %else
; WIDEN_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; WIDEN_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: je .LBB5_4
; WIDEN_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; WIDEN_AVX2-NEXT: vextractps $1, %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; WIDEN_AVX2-NEXT: .LBB5_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; WIDEN_AVX2-NEXT: retq
;
; PROMOTE_AVX2-LABEL: test_scatter_v2i32_data_index:
; PROMOTE_AVX2: # %bb.0:
; PROMOTE_AVX2-NEXT: vpsllq $32, %xmm1, %xmm3
; PROMOTE_AVX2-NEXT: vpsrad $31, %xmm3, %xmm3
; PROMOTE_AVX2-NEXT: vpblendd {{.*#+}} xmm1 = xmm1[0],xmm3[1],xmm1[2],xmm3[3]
; PROMOTE_AVX2-NEXT: vpsllq $2, %xmm1, %xmm1
; PROMOTE_AVX2-NEXT: vmovq %rdi, %xmm3
; PROMOTE_AVX2-NEXT: vpbroadcastq %xmm3, %xmm3
; PROMOTE_AVX2-NEXT: vpaddq %xmm1, %xmm3, %xmm1
; PROMOTE_AVX2-NEXT: vpextrb $0, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
; PROMOTE_AVX2-NEXT: je .LBB5_2
; PROMOTE_AVX2-NEXT: # %bb.1: # %cond.store
; PROMOTE_AVX2-NEXT: vmovq %xmm1, %rax
; PROMOTE_AVX2-NEXT: vmovss %xmm0, (%rax)
; PROMOTE_AVX2-NEXT: .LBB5_2: # %else
; PROMOTE_AVX2-NEXT: vpextrb $8, %xmm2, %eax
; PROMOTE_AVX2-NEXT: testb $1, %al
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: je .LBB5_4
; PROMOTE_AVX2-NEXT: # %bb.3: # %cond.store1
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: vpextrq $1, %xmm1, %rax
; PROMOTE_AVX2-NEXT: vextractps $2, %xmm0, (%rax)
[ScalarizeMaskedMemIntrin] Don't emit 'icmp eq i1 %x, 1' to check mask values. That's just %x so use that directly. Had we emitted this IR earlier, InstCombine would have removed icmp so I'm going to assume using the i1 directly would be considered canonical. llvm-svn: 343244
2018-09-28 02:01:48 +08:00
; PROMOTE_AVX2-NEXT: .LBB5_4: # %else2
[X86] Support v2i32 gather/scatter indices with -x86-experimental-vector-widening-legalization Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp Reviewers: RKSimon, spatel, efriedma Reviewed By: efriedma Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits Differential Revision: https://reviews.llvm.org/D51337 llvm-svn: 340891
2018-08-29 10:12:49 +08:00
; PROMOTE_AVX2-NEXT: retq
%gep = getelementptr i32, i32 *%base, <2 x i32> %ind
call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> %a1, <2 x i32*> %gep, i32 4, <2 x i1> %mask)
ret void
}
declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)
declare void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double>, <2 x double*>, i32, <2 x i1>)
declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)
declare void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> , <2 x i32*> , i32 , <2 x i1>)