-; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=core-avx2 -mattr=avx2 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mattr=avx2 | FileCheck %s
define <16 x i16> @test_x86_avx2_packssdw(<8 x i32> %a0, <8 x i32> %a1) {
; CHECK: vpackssdw
declare <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32>, <4 x i32>) nounwind readnone
-define <4 x i64> @test_x86_avx2_psll_dq(<4 x i64> %a0) {
- ; CHECK: vpslldq
- %res = call <4 x i64> @llvm.x86.avx2.psll.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.psll.dq(<4 x i64>, i32) nounwind readnone
-
-
-define <4 x i64> @test_x86_avx2_psll_dq_bs(<4 x i64> %a0) {
- ; CHECK: vpslldq
- %res = call <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64>, i32) nounwind readnone
-
-
define <4 x i64> @test_x86_avx2_psll_q(<4 x i64> %a0, <2 x i64> %a1) {
; CHECK: vpsllq
%res = call <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
declare <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32>, <4 x i32>) nounwind readnone
-define <4 x i64> @test_x86_avx2_psrl_dq(<4 x i64> %a0) {
- ; CHECK: vpsrldq
- %res = call <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64>, i32) nounwind readnone
-
-
-define <4 x i64> @test_x86_avx2_psrl_dq_bs(<4 x i64> %a0) {
- ; CHECK: vpsrldq
- %res = call <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64>, i32) nounwind readnone
-
-
define <4 x i64> @test_x86_avx2_psrl_q(<4 x i64> %a0, <2 x i64> %a1) {
; CHECK: vpsrlq
%res = call <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
define <16 x i16> @test_x86_avx2_mpsadbw(<32 x i8> %a0, <32 x i8> %a1) {
; CHECK: vmpsadbw
- %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+ %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i8 7) ; <<16 x i16>> [#uses=1]
ret <16 x i16> %res
}
-declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i32) nounwind readnone
+declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i8) nounwind readnone
define <16 x i16> @test_x86_avx2_packusdw(<8 x i32> %a0, <8 x i32> %a1) {
define <16 x i16> @test_x86_avx2_pblendw(<16 x i16> %a0, <16 x i16> %a1) {
; CHECK: vpblendw
- %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+ %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i8 7) ; <<16 x i16>> [#uses=1]
ret <16 x i16> %res
}
-declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone
+declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
define <32 x i8> @test_x86_avx2_pmaxsb(<32 x i8> %a0, <32 x i8> %a1) {
declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
-define <4 x i64> @test_x86_avx2_vbroadcasti128(i8* %a0) {
- ; CHECK: vbroadcasti128
- %res = call <4 x i64> @llvm.x86.avx2.vbroadcasti128(i8* %a0) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.vbroadcasti128(i8*) nounwind readonly
-
-define <4 x double> @test_x86_avx2_vbroadcast_sd_pd_256(<2 x double> %a0) {
- ; CHECK: vbroadcastsd
- %res = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0) ; <<4 x double>> [#uses=1]
- ret <4 x double> %res
-}
-declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
-
-
-define <4 x float> @test_x86_avx2_vbroadcast_ss_ps(<4 x float> %a0) {
- ; CHECK: vbroadcastss
- %res = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
- ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
-
-
-define <8 x float> @test_x86_avx2_vbroadcast_ss_ps_256(<4 x float> %a0) {
- ; CHECK: vbroadcastss
- %res = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0) ; <<8 x float>> [#uses=1]
- ret <8 x float> %res
-}
-declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
-
-
define <4 x i32> @test_x86_avx2_pblendd_128(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK: vpblendd
- %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>> [#uses=1]
+ %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i8 7) ; <<4 x i32>> [#uses=1]
ret <4 x i32> %res
}
-declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone
+declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i8) nounwind readnone
define <8 x i32> @test_x86_avx2_pblendd_256(<8 x i32> %a0, <8 x i32> %a1) {
; CHECK: vpblendd
- %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>> [#uses=1]
+ %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
ret <8 x i32> %res
}
-declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone
-
-
-define <16 x i8> @test_x86_avx2_pbroadcastb_128(<16 x i8> %a0) {
- ; CHECK: vpbroadcastb
- %res = call <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
- ret <16 x i8> %res
-}
-declare <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8>) nounwind readonly
-
-
-define <32 x i8> @test_x86_avx2_pbroadcastb_256(<16 x i8> %a0) {
- ; CHECK: vpbroadcastb
- %res = call <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8> %a0) ; <<32 x i8>> [#uses=1]
- ret <32 x i8> %res
-}
-declare <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8>) nounwind readonly
-
-
-define <8 x i16> @test_x86_avx2_pbroadcastw_128(<8 x i16> %a0) {
- ; CHECK: vpbroadcastw
- %res = call <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
- ret <8 x i16> %res
-}
-declare <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16>) nounwind readonly
-
-
-define <16 x i16> @test_x86_avx2_pbroadcastw_256(<8 x i16> %a0) {
- ; CHECK: vpbroadcastw
- %res = call <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16> %a0) ; <<16 x i16>> [#uses=1]
- ret <16 x i16> %res
-}
-declare <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16>) nounwind readonly
-
-
-define <4 x i32> @test_x86_avx2_pbroadcastd_128(<4 x i32> %a0) {
- ; CHECK: vpbroadcastd
- %res = call <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
- ret <4 x i32> %res
-}
-declare <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32>) nounwind readonly
-
-
-define <8 x i32> @test_x86_avx2_pbroadcastd_256(<4 x i32> %a0) {
- ; CHECK: vpbroadcastd
- %res = call <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32> %a0) ; <<8 x i32>> [#uses=1]
- ret <8 x i32> %res
-}
-declare <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32>) nounwind readonly
-
-
-define <2 x i64> @test_x86_avx2_pbroadcastq_128(<2 x i64> %a0) {
- ; CHECK: vpbroadcastq
- %res = call <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
- ret <2 x i64> %res
-}
-declare <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64>) nounwind readonly
-
-
-define <4 x i64> @test_x86_avx2_pbroadcastq_256(<2 x i64> %a0) {
- ; CHECK: vpbroadcastq
- %res = call <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64> %a0) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64>) nounwind readonly
+declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
define <8 x i32> @test_x86_avx2_permd(<8 x i32> %a0, <8 x i32> %a1) {
- ; CHECK: vpermd
+ ; Check that the arguments are swapped between the intrinsic definition
+ ; and its lowering. Indeed, the offsets are the first source in
+ ; the instruction.
+ ; CHECK: vpermd %ymm0, %ymm1, %ymm0
%res = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly
-define <8 x float> @test_x86_avx2_permps(<8 x float> %a0, <8 x float> %a1) {
- ; CHECK: vpermps
- %res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x float> %a1) ; <<8 x float>> [#uses=1]
+define <8 x float> @test_x86_avx2_permps(<8 x float> %a0, <8 x i32> %a1) {
+ ; Check that the arguments are swapped between the intrinsic definition
+ ; and its lowering. Indeed, the offsets are the first source in
+ ; the instruction.
+ ; CHECK: vpermps %ymm0, %ymm1, %ymm0
+ %res = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %a1) ; <<8 x float>> [#uses=1]
ret <8 x float> %res
}
-declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x float>) nounwind readonly
+declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>) nounwind readonly
define <4 x i64> @test_x86_avx2_vperm2i128(<4 x i64> %a0, <4 x i64> %a1) {
declare <4 x i64> @llvm.x86.avx2.vperm2i128(<4 x i64>, <4 x i64>, i8) nounwind readonly
-define <2 x i64> @test_x86_avx2_vextracti128(<4 x i64> %a0) {
- ; CHECK: vextracti128
- %res = call <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64> %a0, i8 7) ; <<2 x i64>> [#uses=1]
- ret <2 x i64> %res
-}
-declare <2 x i64> @llvm.x86.avx2.vextracti128(<4 x i64>, i8) nounwind readnone
-
-
-define <4 x i64> @test_x86_avx2_vinserti128(<4 x i64> %a0, <2 x i64> %a1) {
- ; CHECK: vinserti128
- %res = call <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64> %a0, <2 x i64> %a1, i8 7) ; <<4 x i64>> [#uses=1]
- ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64>, <2 x i64>, i8) nounwind readnone
-
-
define <2 x i64> @test_x86_avx2_maskload_q(i8* %a0, <2 x i64> %a1) {
; CHECK: vpmaskmovq
%res = call <2 x i64> @llvm.x86.avx2.maskload.q(i8* %a0, <2 x i64> %a1) ; <<2 x i64>> [#uses=1]
ret void
}
declare void @llvm.x86.avx.storeu.dq.256(i8*, <32 x i8>) nounwind
+
+define <2 x double> @test_x86_avx2_gather_d_pd(<2 x double> %a0, i8* %a1,
+ <4 x i32> %idx, <2 x double> %mask) {
+ ; CHECK: vgatherdpd
+ %res = call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> %a0,
+ i8* %a1, <4 x i32> %idx, <2 x double> %mask, i8 2) ;
+ ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double>, i8*,
+ <4 x i32>, <2 x double>, i8) nounwind readonly
+
+define <4 x double> @test_x86_avx2_gather_d_pd_256(<4 x double> %a0, i8* %a1,
+ <4 x i32> %idx, <4 x double> %mask) {
+ ; CHECK: vgatherdpd
+ %res = call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> %a0,
+ i8* %a1, <4 x i32> %idx, <4 x double> %mask, i8 2) ;
+ ret <4 x double> %res
+}
+declare <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double>, i8*,
+ <4 x i32>, <4 x double>, i8) nounwind readonly
+
+define <2 x double> @test_x86_avx2_gather_q_pd(<2 x double> %a0, i8* %a1,
+ <2 x i64> %idx, <2 x double> %mask) {
+ ; CHECK: vgatherqpd
+ %res = call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> %a0,
+ i8* %a1, <2 x i64> %idx, <2 x double> %mask, i8 2) ;
+ ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double>, i8*,
+ <2 x i64>, <2 x double>, i8) nounwind readonly
+
+define <4 x double> @test_x86_avx2_gather_q_pd_256(<4 x double> %a0, i8* %a1,
+ <4 x i64> %idx, <4 x double> %mask) {
+ ; CHECK: vgatherqpd
+ %res = call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> %a0,
+ i8* %a1, <4 x i64> %idx, <4 x double> %mask, i8 2) ;
+ ret <4 x double> %res
+}
+declare <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double>, i8*,
+ <4 x i64>, <4 x double>, i8) nounwind readonly
+
+define <4 x float> @test_x86_avx2_gather_d_ps(<4 x float> %a0, i8* %a1,
+ <4 x i32> %idx, <4 x float> %mask) {
+ ; CHECK: vgatherdps
+ %res = call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> %a0,
+ i8* %a1, <4 x i32> %idx, <4 x float> %mask, i8 2) ;
+ ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float>, i8*,
+ <4 x i32>, <4 x float>, i8) nounwind readonly
+
+define <8 x float> @test_x86_avx2_gather_d_ps_256(<8 x float> %a0, i8* %a1,
+ <8 x i32> %idx, <8 x float> %mask) {
+ ; CHECK: vgatherdps
+ %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,
+ i8* %a1, <8 x i32> %idx, <8 x float> %mask, i8 2) ;
+ ret <8 x float> %res
+}
+declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*,
+ <8 x i32>, <8 x float>, i8) nounwind readonly
+
+define <4 x float> @test_x86_avx2_gather_q_ps(<4 x float> %a0, i8* %a1,
+ <2 x i64> %idx, <4 x float> %mask) {
+ ; CHECK: vgatherqps
+ %res = call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> %a0,
+ i8* %a1, <2 x i64> %idx, <4 x float> %mask, i8 2) ;
+ ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float>, i8*,
+ <2 x i64>, <4 x float>, i8) nounwind readonly
+
+define <4 x float> @test_x86_avx2_gather_q_ps_256(<4 x float> %a0, i8* %a1,
+ <4 x i64> %idx, <4 x float> %mask) {
+ ; CHECK: vgatherqps
+ %res = call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> %a0,
+ i8* %a1, <4 x i64> %idx, <4 x float> %mask, i8 2) ;
+ ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float>, i8*,
+ <4 x i64>, <4 x float>, i8) nounwind readonly
+
+define <2 x i64> @test_x86_avx2_gather_d_q(<2 x i64> %a0, i8* %a1,
+ <4 x i32> %idx, <2 x i64> %mask) {
+ ; CHECK: vpgatherdq
+ %res = call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> %a0,
+ i8* %a1, <4 x i32> %idx, <2 x i64> %mask, i8 2) ;
+ ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64>, i8*,
+ <4 x i32>, <2 x i64>, i8) nounwind readonly
+
+define <4 x i64> @test_x86_avx2_gather_d_q_256(<4 x i64> %a0, i8* %a1,
+ <4 x i32> %idx, <4 x i64> %mask) {
+ ; CHECK: vpgatherdq
+ %res = call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> %a0,
+ i8* %a1, <4 x i32> %idx, <4 x i64> %mask, i8 2) ;
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64>, i8*,
+ <4 x i32>, <4 x i64>, i8) nounwind readonly
+
+define <2 x i64> @test_x86_avx2_gather_q_q(<2 x i64> %a0, i8* %a1,
+ <2 x i64> %idx, <2 x i64> %mask) {
+ ; CHECK: vpgatherqq
+ %res = call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> %a0,
+ i8* %a1, <2 x i64> %idx, <2 x i64> %mask, i8 2) ;
+ ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64>, i8*,
+ <2 x i64>, <2 x i64>, i8) nounwind readonly
+
+define <4 x i64> @test_x86_avx2_gather_q_q_256(<4 x i64> %a0, i8* %a1,
+ <4 x i64> %idx, <4 x i64> %mask) {
+ ; CHECK: vpgatherqq
+ %res = call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> %a0,
+ i8* %a1, <4 x i64> %idx, <4 x i64> %mask, i8 2) ;
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64>, i8*,
+ <4 x i64>, <4 x i64>, i8) nounwind readonly
+
+define <4 x i32> @test_x86_avx2_gather_d_d(<4 x i32> %a0, i8* %a1,
+ <4 x i32> %idx, <4 x i32> %mask) {
+ ; CHECK: vpgatherdd
+ %res = call <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32> %a0,
+ i8* %a1, <4 x i32> %idx, <4 x i32> %mask, i8 2) ;
+ ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32>, i8*,
+ <4 x i32>, <4 x i32>, i8) nounwind readonly
+
+define <8 x i32> @test_x86_avx2_gather_d_d_256(<8 x i32> %a0, i8* %a1,
+ <8 x i32> %idx, <8 x i32> %mask) {
+ ; CHECK: vpgatherdd
+ %res = call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> %a0,
+ i8* %a1, <8 x i32> %idx, <8 x i32> %mask, i8 2) ;
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32>, i8*,
+ <8 x i32>, <8 x i32>, i8) nounwind readonly
+
+define <4 x i32> @test_x86_avx2_gather_q_d(<4 x i32> %a0, i8* %a1,
+ <2 x i64> %idx, <4 x i32> %mask) {
+ ; CHECK: vpgatherqd
+ %res = call <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32> %a0,
+ i8* %a1, <2 x i64> %idx, <4 x i32> %mask, i8 2) ;
+ ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32>, i8*,
+ <2 x i64>, <4 x i32>, i8) nounwind readonly
+
+define <4 x i32> @test_x86_avx2_gather_q_d_256(<4 x i32> %a0, i8* %a1,
+ <4 x i64> %idx, <4 x i32> %mask) {
+ ; CHECK: vpgatherqd
+ %res = call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> %a0,
+ i8* %a1, <4 x i64> %idx, <4 x i32> %mask, i8 2) ;
+ ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32>, i8*,
+ <4 x i64>, <4 x i32>, i8) nounwind readonly
+
+; PR13298
+define <8 x float> @test_gather_mask(<8 x float> %a0, float* %a,
+ <8 x i32> %idx, <8 x float> %mask,
+ float* nocapture %out) {
+; CHECK: test_gather_mask
+; CHECK: vmovaps %ymm2, [[DEST:%.*]]
+; CHECK: vgatherdps [[DEST]]
+;; gather with mask
+ %a_i8 = bitcast float* %a to i8*
+ %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> %a0,
+ i8* %a_i8, <8 x i32> %idx, <8 x float> %mask, i8 4) ;
+
+;; for debugging, we'll just dump out the mask
+ %out_ptr = bitcast float * %out to <8 x float> *
+ store <8 x float> %mask, <8 x float> * %out_ptr, align 4
+
+ ret <8 x float> %res
+}