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/avx512vl-intrinsics-upgrade.ll

3519 lines
191 KiB
LLVM
Raw Normal View History

[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[AVX512] Remove masked store intrinsics. Clang now emits generic masked store intrinsics instead. The intrinsics will be autoupgraded to the same generic masked stores. llvm-svn: 271245
2016-05-31 09:50:02 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512vl --show-mc-encoding| FileCheck %s
[X86][AVX512] Autoupgrade the BROADCAST intrinsics llvm-svn: 274550
2016-07-05 21:58:47 +08:00
declare <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_pbroadcastd_256(<4 x i32> %x0, <8 x i32> %x1, i8 %mask, i32 * %y_ptr) {
; CHECK-LABEL: test_int_x86_avx512_pbroadcastd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpbroadcastd %xmm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x58,0xc8]
; CHECK-NEXT: vpbroadcastd %xmm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x58,0xc0]
; CHECK-NEXT: vpaddd (%rsi){1to8}, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0x75,0x38,0xfe,0x0e]
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%y_32 = load i32, i32 * %y_ptr
%y = insertelement <4 x i32> undef, i32 %y_32, i32 0
%res = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %y, <8 x i32> %x1, i8 -1)
%res1 = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %x0, <8 x i32> %x1, i8 %mask)
%res2 = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %x0, <8 x i32> zeroinitializer, i8 %mask)
%res3 = add <8 x i32> %res, %res1
%res4 = add <8 x i32> %res2, %res3
ret <8 x i32> %res4
}
declare <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_pbroadcastd_128(<4 x i32> %x0, <4 x i32> %x1, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_pbroadcastd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpbroadcastd %xmm0, %xmm2 ## encoding: [0x62,0xf2,0x7d,0x08,0x58,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpbroadcastd %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x58,0xc8]
; CHECK-NEXT: vpbroadcastd %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x58,0xc0]
; CHECK-NEXT: vpaddd %xmm1, %xmm2, %xmm1 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc9]
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> %x1, i8 -1)
%res1 = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> %x1, i8 %mask)
%res2 = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> zeroinitializer, i8 %mask)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res2, %res3
ret <4 x i32> %res4
}
declare <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_pbroadcastq_256(<2 x i64> %x0, <4 x i64> %x1, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_pbroadcastq_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpbroadcastq %xmm0, %ymm2 ## encoding: [0x62,0xf2,0xfd,0x28,0x59,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpbroadcastq %xmm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x59,0xc8]
; CHECK-NEXT: vpbroadcastq %xmm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x59,0xc0]
; CHECK-NEXT: vpaddq %ymm1, %ymm2, %ymm1 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc9]
; CHECK-NEXT: vpaddq %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0xd4,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64> %x0, <4 x i64> %x1,i8 -1)
%res1 = call <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64> %x0, <4 x i64> %x1,i8 %mask)
%res2 = call <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64> %x0, <4 x i64> zeroinitializer,i8 %mask)
%res3 = add <4 x i64> %res, %res1
%res4 = add <4 x i64> %res2, %res3
ret <4 x i64> %res4
}
declare <2 x i64> @llvm.x86.avx512.pbroadcastq.128(<2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_pbroadcastq_128(<2 x i64> %x0, <2 x i64> %x1, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_pbroadcastq_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpbroadcastq %xmm0, %xmm2 ## encoding: [0x62,0xf2,0xfd,0x08,0x59,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpbroadcastq %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x59,0xc8]
; CHECK-NEXT: vpbroadcastq %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0x89,0x59,0xc0]
; CHECK-NEXT: vpaddq %xmm1, %xmm2, %xmm1 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc9]
; CHECK-NEXT: vpaddq %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0xd4,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.pbroadcastq.128(<2 x i64> %x0, <2 x i64> %x1,i8 -1)
%res1 = call <2 x i64> @llvm.x86.avx512.pbroadcastq.128(<2 x i64> %x0, <2 x i64> %x1,i8 %mask)
%res2 = call <2 x i64> @llvm.x86.avx512.pbroadcastq.128(<2 x i64> %x0, <2 x i64> zeroinitializer,i8 %mask)
%res3 = add <2 x i64> %res, %res1
%res4 = add <2 x i64> %res2, %res3
ret <2 x i64> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.256(<2 x double>, <4 x double>, i8) nounwind readonly
define <4 x double> @test_x86_vbroadcast_sd_pd_256(<2 x double> %a0, <4 x double> %a1, i8 %mask ) {
; CHECK-LABEL: test_x86_vbroadcast_sd_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vbroadcastsd %xmm0, %ymm2 ## encoding: [0x62,0xf2,0xfd,0x28,0x19,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vbroadcastsd %xmm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x19,0xc8]
; CHECK-NEXT: vbroadcastsd %xmm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x19,0xc0]
; CHECK-NEXT: vaddpd %ymm1, %ymm2, %ymm1 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc9]
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.256(<2 x double> %a0, <4 x double> zeroinitializer, i8 -1)
%res1 = call <4 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.256(<2 x double> %a0, <4 x double> %a1, i8 %mask)
%res2 = call <4 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.256(<2 x double> %a0, <4 x double> zeroinitializer, i8 %mask)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res2, %res3
ret <4 x double> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.256(<4 x float>, <8 x float>, i8) nounwind readonly
define <8 x float> @test_x86_vbroadcast_ss_ps_256(<4 x float> %a0, <8 x float> %a1, i8 %mask ) {
; CHECK-LABEL: test_x86_vbroadcast_ss_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vbroadcastss %xmm0, %ymm2 ## encoding: [0x62,0xf2,0x7d,0x28,0x18,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vbroadcastss %xmm0, %ymm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x18,0xc8]
; CHECK-NEXT: vbroadcastss %xmm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x18,0xc0]
; CHECK-NEXT: vaddps %ymm1, %ymm2, %ymm1 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc9]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.256(<4 x float> %a0, <8 x float> zeroinitializer, i8 -1)
%res1 = call <8 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.256(<4 x float> %a0, <8 x float> %a1, i8 %mask)
%res2 = call <8 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.256(<4 x float> %a0, <8 x float> zeroinitializer, i8 %mask)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.128(<4 x float>, <4 x float>, i8) nounwind readonly
define <4 x float> @test_x86_vbroadcast_ss_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask ) {
; CHECK-LABEL: test_x86_vbroadcast_ss_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vbroadcastss %xmm0, %xmm2 ## encoding: [0x62,0xf2,0x7d,0x08,0x18,0xd0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vbroadcastss %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x18,0xc8]
; CHECK-NEXT: vbroadcastss %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x18,0xc0]
; CHECK-NEXT: vaddps %xmm1, %xmm2, %xmm1 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc9]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.128(<4 x float> %a0, <4 x float> zeroinitializer, i8 -1)
%res1 = call <4 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.128(<4 x float> %a0, <4 x float> %a1, i8 %mask)
%res2 = call <4 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.128(<4 x float> %a0, <4 x float> zeroinitializer, i8 %mask)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
declare <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movsldup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovsldup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0x7e,0x08,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0,2,2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x12,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[0,0,2,2]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovsldup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x12,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[0,0,2,2]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddps %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xca]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movsldup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movsldup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movsldup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovsldup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0x7e,0x28,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2,4,4,6,6]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovsldup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x12,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[0,0,2,2,4,4,6,6]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovsldup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x12,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[0,0,2,2,4,4,6,6]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddps %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xca]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movsldup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_movshdup_128(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovshdup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0x7e,0x08,0x16,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[1,1,3,3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x16,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[1,1,3,3]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovshdup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x16,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[1,1,3,3]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddps %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xca]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 %x2)
%res1 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> %x1, i8 -1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.movshdup.128(<4 x float> %x0, <4 x float> zeroinitializer, i8 %x2)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_movshdup_256(<8 x float> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movshdup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovshdup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0x7e,0x28,0x16,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[1,1,3,3,5,5,7,7]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovshdup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x16,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[1,1,3,3,5,5,7,7]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovshdup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x16,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[1,1,3,3,5,5,7,7]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddps %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xca]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 %x2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> %x1, i8 -1)
%res2 = call <8 x float> @llvm.x86.avx512.mask.movshdup.256(<8 x float> %x0, <8 x float> zeroinitializer, i8 %x2)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res2, %res3
ret <8 x float> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double>, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_movddup_128(<2 x double> %x0, <2 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovddup %xmm0, %xmm2 ## encoding: [0x62,0xf1,0xff,0x08,0x12,0xd0]
; CHECK-NEXT: ## xmm2 = xmm0[0,0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x09,0x12,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[0,0]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovddup %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0x89,0x12,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[0,0]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddpd %xmm2, %xmm1, %xmm1 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xca]
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 %x2)
%res1 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> %x1, i8 -1)
%res2 = call <2 x double> @llvm.x86.avx512.mask.movddup.128(<2 x double> %x0, <2 x double> zeroinitializer, i8 %x2)
%res3 = fadd <2 x double> %res, %res1
%res4 = fadd <2 x double> %res2, %res3
ret <2 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double>, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_movddup_256(<4 x double> %x0, <4 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_movddup_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovddup %ymm0, %ymm2 ## encoding: [0x62,0xf1,0xff,0x28,0x12,0xd0]
; CHECK-NEXT: ## ymm2 = ymm0[0,0,2,2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmovddup %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0xff,0x29,0x12,0xc8]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[0,0,2,2]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vmovddup %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0xff,0xa9,0x12,0xc0]
[X86][AVX512] Add support for masked shuffle comments This patch adds support for including the avx512 mask register information in the mask/maskz versions of shuffle instruction comments. This initial version just adds support for MOVDDUP/MOVSHDUP/MOVSLDUP to reduce the mass of test regenerations, other shuffle instructions can be added in due course. Differential Revision: http://reviews.llvm.org/D21953 llvm-svn: 274459
2016-07-03 21:08:29 +08:00
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[0,0,2,2]
[X86][AVX512] Autoupgrade the MOVDDUP/MOVSLDUP/MOVSHDUP intrinsics llvm-svn: 274439
2016-07-02 22:42:35 +08:00
; CHECK-NEXT: vaddpd %ymm2, %ymm1, %ymm1 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xca]
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 %x2)
%res1 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> %x1, i8 -1)
%res2 = call <4 x double> @llvm.x86.avx512.mask.movddup.256(<4 x double> %x0, <4 x double> zeroinitializer, i8 %x2)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res2, %res3
ret <4 x double> %res4
}
[X86][AVX512] Autoupgrade the VPERMILPD/VPERMILPS intrinsics llvm-svn: 274498
2016-07-04 20:40:54 +08:00
declare <4 x double> @llvm.x86.avx512.mask.vpermil.pd.256(<4 x double>, i32, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_vpermil_pd_256(<4 x double> %x0, <4 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpermil_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermilpd $6, %ymm0, %ymm2 ## encoding: [0x62,0xf3,0xfd,0x28,0x05,0xd0,0x06]
; CHECK-NEXT: ## ymm2 = ymm0[0,1,3,2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpermilpd $6, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf3,0xfd,0x29,0x05,0xc8,0x06]
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[0,1,3,2]
; CHECK-NEXT: vpermilpd $6, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf3,0xfd,0xa9,0x05,0xc0,0x06]
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[0,1,3,2]
; CHECK-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xc0]
; CHECK-NEXT: vaddpd %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.vpermil.pd.256(<4 x double> %x0, i32 22, <4 x double> %x2, i8 %x3)
%res1 = call <4 x double> @llvm.x86.avx512.mask.vpermil.pd.256(<4 x double> %x0, i32 22, <4 x double> zeroinitializer, i8 %x3)
%res2 = call <4 x double> @llvm.x86.avx512.mask.vpermil.pd.256(<4 x double> %x0, i32 22, <4 x double> %x2, i8 -1)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res2, %res3
ret <4 x double> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.vpermil.pd.128(<2 x double>, i32, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_vpermil_pd_128(<2 x double> %x0, <2 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpermil_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermilpd $1, %xmm0, %xmm2 ## encoding: [0x62,0xf3,0xfd,0x08,0x05,0xd0,0x01]
; CHECK-NEXT: ## xmm2 = xmm0[1,0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpermilpd $1, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf3,0xfd,0x09,0x05,0xc8,0x01]
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[1,0]
; CHECK-NEXT: vpermilpd $1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf3,0xfd,0x89,0x05,0xc0,0x01]
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[1,0]
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xc0]
; CHECK-NEXT: vaddpd %xmm2, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x58,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.vpermil.pd.128(<2 x double> %x0, i32 1, <2 x double> %x2, i8 %x3)
%res1 = call <2 x double> @llvm.x86.avx512.mask.vpermil.pd.128(<2 x double> %x0, i32 1, <2 x double> zeroinitializer, i8 %x3)
%res2 = call <2 x double> @llvm.x86.avx512.mask.vpermil.pd.128(<2 x double> %x0, i32 1, <2 x double> %x2, i8 -1)
%res3 = fadd <2 x double> %res, %res1
%res4 = fadd <2 x double> %res3, %res2
ret <2 x double> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.vpermil.ps.256(<8 x float>, i32, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_vpermil_ps_256(<8 x float> %x0, <8 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpermil_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermilps $22, %ymm0, %ymm2 ## encoding: [0x62,0xf3,0x7d,0x28,0x04,0xd0,0x16]
; CHECK-NEXT: ## ymm2 = ymm0[2,1,1,0,6,5,5,4]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpermilps $22, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf3,0x7d,0x29,0x04,0xc8,0x16]
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[2,1,1,0,6,5,5,4]
; CHECK-NEXT: vpermilps $22, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf3,0x7d,0xa9,0x04,0xc0,0x16]
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[2,1,1,0,6,5,5,4]
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xc0]
; CHECK-NEXT: vaddps %ymm2, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.vpermil.ps.256(<8 x float> %x0, i32 22, <8 x float> %x2, i8 %x3)
%res1 = call <8 x float> @llvm.x86.avx512.mask.vpermil.ps.256(<8 x float> %x0, i32 22, <8 x float> zeroinitializer, i8 %x3)
%res2 = call <8 x float> @llvm.x86.avx512.mask.vpermil.ps.256(<8 x float> %x0, i32 22, <8 x float> %x2, i8 -1)
%res3 = fadd <8 x float> %res, %res1
%res4 = fadd <8 x float> %res3, %res2
ret <8 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.vpermil.ps.128(<4 x float>, i32, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_vpermil_ps_128(<4 x float> %x0, <4 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_vpermil_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermilps $22, %xmm0, %xmm2 ## encoding: [0x62,0xf3,0x7d,0x08,0x04,0xd0,0x16]
; CHECK-NEXT: ## xmm2 = xmm0[2,1,1,0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpermilps $22, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf3,0x7d,0x09,0x04,0xc8,0x16]
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[2,1,1,0]
; CHECK-NEXT: vpermilps $22, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf3,0x7d,0x89,0x04,0xc0,0x16]
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[2,1,1,0]
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xc0]
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.vpermil.ps.128(<4 x float> %x0, i32 22, <4 x float> %x2, i8 %x3)
%res1 = call <4 x float> @llvm.x86.avx512.mask.vpermil.ps.128(<4 x float> %x0, i32 22, <4 x float> zeroinitializer, i8 %x3)
%res2 = call <4 x float> @llvm.x86.avx512.mask.vpermil.ps.128(<4 x float> %x0, i32 22, <4 x float> %x2, i8 -1)
%res3 = fadd <4 x float> %res, %res1
%res4 = fadd <4 x float> %res2, %res3
ret <4 x float> %res4
}
[X86][AVX512] Autoupgrade the VPERMPD/VPERMQ intrinsics llvm-svn: 274506
2016-07-04 22:19:05 +08:00
declare <4 x double> @llvm.x86.avx512.mask.perm.df.256(<4 x double>, i32, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_perm_df_256(<4 x double> %x0, i32 %x1, <4 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_perm_df_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermpd $3, %ymm0, %ymm2 ## encoding: [0x62,0xf3,0xfd,0x28,0x01,0xd0,0x03]
; CHECK-NEXT: ## ymm2 = ymm0[3,0,0,0]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpermpd $3, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf3,0xfd,0x29,0x01,0xc8,0x03]
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[3,0,0,0]
; CHECK-NEXT: vpermpd $3, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf3,0xfd,0xa9,0x01,0xc0,0x03]
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[3,0,0,0]
; CHECK-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xc0]
; CHECK-NEXT: vaddpd %ymm2, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x58,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.perm.df.256(<4 x double> %x0, i32 3, <4 x double> %x2, i8 %x3)
%res1 = call <4 x double> @llvm.x86.avx512.mask.perm.df.256(<4 x double> %x0, i32 3, <4 x double> zeroinitializer, i8 %x3)
%res2 = call <4 x double> @llvm.x86.avx512.mask.perm.df.256(<4 x double> %x0, i32 3, <4 x double> %x2, i8 -1)
%res3 = fadd <4 x double> %res, %res1
%res4 = fadd <4 x double> %res3, %res2
ret <4 x double> %res4
}
declare <4 x i64> @llvm.x86.avx512.mask.perm.di.256(<4 x i64>, i32, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_perm_di_256(<4 x i64> %x0, i32 %x1, <4 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_perm_di_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpermq $3, %ymm0, %ymm2 ## encoding: [0x62,0xf3,0xfd,0x28,0x00,0xd0,0x03]
; CHECK-NEXT: ## ymm2 = ymm0[3,0,0,0]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpermq $3, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf3,0xfd,0x29,0x00,0xc8,0x03]
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[3,0,0,0]
; CHECK-NEXT: vpermq $3, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf3,0xfd,0xa9,0x00,0xc0,0x03]
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[3,0,0,0]
; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0xd4,0xc0]
; CHECK-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0xd4,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.perm.di.256(<4 x i64> %x0, i32 3, <4 x i64> %x2, i8 %x3)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.perm.di.256(<4 x i64> %x0, i32 3, <4 x i64> zeroinitializer, i8 %x3)
%res2 = call <4 x i64> @llvm.x86.avx512.mask.perm.di.256(<4 x i64> %x0, i32 3, <4 x i64> %x2, i8 -1)
%res3 = add <4 x i64> %res, %res1
%res4 = add <4 x i64> %res3, %res2
ret <4 x i64> %res4
}
[AVX512] Remove masked store intrinsics. Clang now emits generic masked store intrinsics instead. The intrinsics will be autoupgraded to the same generic masked stores. llvm-svn: 271245
2016-05-31 09:50:02 +08:00
declare void @llvm.x86.avx512.mask.store.pd.128(i8*, <2 x double>, i8)
define void@test_int_x86_avx512_mask_store_pd_128(i8* %ptr1, i8* %ptr2, <2 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovapd %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x29,0x07]
; CHECK-NEXT: vmovapd %xmm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x08,0x29,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.pd.128(i8* %ptr1, <2 x double> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.pd.128(i8* %ptr2, <2 x double> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.pd.256(i8*, <4 x double>, i8)
define void@test_int_x86_avx512_mask_store_pd_256(i8* %ptr1, i8* %ptr2, <4 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovapd %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x29,0x07]
; CHECK-NEXT: vmovapd %ymm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x28,0x29,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.pd.256(i8* %ptr1, <4 x double> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.pd.256(i8* %ptr2, <4 x double> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.pd.128(i8*, <2 x double>, i8)
define void@test_int_x86_avx512_mask_storeu_pd_128(i8* %ptr1, i8* %ptr2, <2 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovupd %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x11,0x07]
; CHECK-NEXT: vmovupd %xmm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x08,0x11,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.pd.128(i8* %ptr1, <2 x double> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.pd.128(i8* %ptr2, <2 x double> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.pd.256(i8*, <4 x double>, i8)
define void@test_int_x86_avx512_mask_storeu_pd_256(i8* %ptr1, i8* %ptr2, <4 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovupd %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x11,0x07]
; CHECK-NEXT: vmovupd %ymm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x28,0x11,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.pd.256(i8* %ptr1, <4 x double> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.pd.256(i8* %ptr2, <4 x double> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.ps.128(i8*, <4 x float>, i8)
define void@test_int_x86_avx512_mask_store_ps_128(i8* %ptr1, i8* %ptr2, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovaps %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x29,0x07]
; CHECK-NEXT: vmovaps %xmm0, (%rsi) ## encoding: [0x62,0xf1,0x7c,0x08,0x29,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.ps.128(i8* %ptr1, <4 x float> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.ps.128(i8* %ptr2, <4 x float> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.ps.256(i8*, <8 x float>, i8)
define void@test_int_x86_avx512_mask_store_ps_256(i8* %ptr1, i8* %ptr2, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovaps %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x29,0x07]
; CHECK-NEXT: vmovaps %ymm0, (%rsi) ## encoding: [0x62,0xf1,0x7c,0x28,0x29,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.ps.256(i8* %ptr1, <8 x float> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.ps.256(i8* %ptr2, <8 x float> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.ps.128(i8*, <4 x float>, i8)
define void@test_int_x86_avx512_mask_storeu_ps_128(i8* %ptr1, i8* %ptr2, <4 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovups %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x11,0x07]
; CHECK-NEXT: vmovups %xmm0, (%rsi) ## encoding: [0x62,0xf1,0x7c,0x08,0x11,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.ps.128(i8* %ptr1, <4 x float> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.ps.128(i8* %ptr2, <4 x float> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.ps.256(i8*, <8 x float>, i8)
define void@test_int_x86_avx512_mask_storeu_ps_256(i8* %ptr1, i8* %ptr2, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovups %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x11,0x07]
; CHECK-NEXT: vmovups %ymm0, (%rsi) ## encoding: [0x62,0xf1,0x7c,0x28,0x11,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.ps.256(i8* %ptr1, <8 x float> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.ps.256(i8* %ptr2, <8 x float> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.q.128(i8*, <2 x i64>, i8)
define void@test_int_x86_avx512_mask_storeu_q_128(i8* %ptr1, i8* %ptr2, <2 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu64 %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfe,0x09,0x7f,0x07]
; CHECK-NEXT: vmovdqu64 %xmm0, (%rsi) ## encoding: [0x62,0xf1,0xfe,0x08,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.q.128(i8* %ptr1, <2 x i64> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.q.128(i8* %ptr2, <2 x i64> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.q.256(i8*, <4 x i64>, i8)
define void@test_int_x86_avx512_mask_storeu_q_256(i8* %ptr1, i8* %ptr2, <4 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu64 %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfe,0x29,0x7f,0x07]
; CHECK-NEXT: vmovdqu64 %ymm0, (%rsi) ## encoding: [0x62,0xf1,0xfe,0x28,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.q.256(i8* %ptr1, <4 x i64> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.q.256(i8* %ptr2, <4 x i64> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.d.128(i8*, <4 x i32>, i8)
define void@test_int_x86_avx512_mask_storeu_d_128(i8* %ptr1, i8* %ptr2, <4 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu32 %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x7f,0x07]
; CHECK-NEXT: vmovdqu32 %xmm0, (%rsi) ## encoding: [0x62,0xf1,0x7e,0x08,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.d.128(i8* %ptr1, <4 x i32> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.d.128(i8* %ptr2, <4 x i32> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.storeu.d.256(i8*, <8 x i32>, i8)
define void@test_int_x86_avx512_mask_storeu_d_256(i8* %ptr1, i8* %ptr2, <8 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_storeu_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu32 %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x7f,0x07]
; CHECK-NEXT: vmovdqu32 %ymm0, (%rsi) ## encoding: [0x62,0xf1,0x7e,0x28,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.storeu.d.256(i8* %ptr1, <8 x i32> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.storeu.d.256(i8* %ptr2, <8 x i32> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.q.128(i8*, <2 x i64>, i8)
define void@test_int_x86_avx512_mask_store_q_128(i8* %ptr1, i8* %ptr2, <2 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqa64 %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x7f,0x07]
; CHECK-NEXT: vmovdqa64 %xmm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x08,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.q.128(i8* %ptr1, <2 x i64> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.q.128(i8* %ptr2, <2 x i64> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.q.256(i8*, <4 x i64>, i8)
define void@test_int_x86_avx512_mask_store_q_256(i8* %ptr1, i8* %ptr2, <4 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqa64 %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x7f,0x07]
; CHECK-NEXT: vmovdqa64 %ymm0, (%rsi) ## encoding: [0x62,0xf1,0xfd,0x28,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.q.256(i8* %ptr1, <4 x i64> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.q.256(i8* %ptr2, <4 x i64> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.d.128(i8*, <4 x i32>, i8)
define void@test_int_x86_avx512_mask_store_d_128(i8* %ptr1, i8* %ptr2, <4 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqa32 %xmm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x7f,0x07]
; CHECK-NEXT: vmovdqa32 %xmm0, (%rsi) ## encoding: [0x62,0xf1,0x7d,0x08,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.d.128(i8* %ptr1, <4 x i32> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.d.128(i8* %ptr2, <4 x i32> %x1, i8 -1)
ret void
}
declare void @llvm.x86.avx512.mask.store.d.256(i8*, <8 x i32>, i8)
define void@test_int_x86_avx512_mask_store_d_256(i8* %ptr1, i8* %ptr2, <8 x i32> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_store_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqa32 %ymm0, (%rdi) {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x7f,0x07]
; CHECK-NEXT: vmovdqa32 %ymm0, (%rsi) ## encoding: [0x62,0xf1,0x7d,0x28,0x7f,0x06]
; CHECK-NEXT: retq ## encoding: [0xc3]
call void @llvm.x86.avx512.mask.store.d.256(i8* %ptr1, <8 x i32> %x1, i8 %x2)
call void @llvm.x86.avx512.mask.store.d.256(i8* %ptr2, <8 x i32> %x1, i8 -1)
ret void
}
[AVX512] Remove masked load intrinsics. Clang now emits generic masked load intrinsics instead. The intrinsics will be autoupgraded to the same generic masked loads. llvm-svn: 271478
2016-06-02 12:19:36 +08:00
define <8 x float> @test_mask_load_aligned_ps_256(<8 x float> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovaps (%rdi), %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x28,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovaps (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x28,0x07]
; CHECK-NEXT: vmovaps (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x28,0x0f]
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.load.ps.256(i8* %ptr, <8 x float> zeroinitializer, i8 -1)
%res1 = call <8 x float> @llvm.x86.avx512.mask.load.ps.256(i8* %ptr, <8 x float> %res, i8 %mask)
%res2 = call <8 x float> @llvm.x86.avx512.mask.load.ps.256(i8* %ptr, <8 x float> zeroinitializer, i8 %mask)
%res4 = fadd <8 x float> %res2, %res1
ret <8 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.load.ps.256(i8*, <8 x float>, i8)
define <8 x float> @test_mask_load_unaligned_ps_256(<8 x float> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovups (%rdi), %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x10,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovups (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x10,0x07]
; CHECK-NEXT: vmovups (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x10,0x0f]
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x74,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.loadu.ps.256(i8* %ptr, <8 x float> zeroinitializer, i8 -1)
%res1 = call <8 x float> @llvm.x86.avx512.mask.loadu.ps.256(i8* %ptr, <8 x float> %res, i8 %mask)
%res2 = call <8 x float> @llvm.x86.avx512.mask.loadu.ps.256(i8* %ptr, <8 x float> zeroinitializer, i8 %mask)
%res4 = fadd <8 x float> %res2, %res1
ret <8 x float> %res4
}
declare <8 x float> @llvm.x86.avx512.mask.loadu.ps.256(i8*, <8 x float>, i8)
define <4 x double> @test_mask_load_aligned_pd_256(<4 x double> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovapd (%rdi), %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x28,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovapd (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x28,0x07]
; CHECK-NEXT: vmovapd (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xa9,0x28,0x0f]
; CHECK-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.load.pd.256(i8* %ptr, <4 x double> zeroinitializer, i8 -1)
%res1 = call <4 x double> @llvm.x86.avx512.mask.load.pd.256(i8* %ptr, <4 x double> %res, i8 %mask)
%res2 = call <4 x double> @llvm.x86.avx512.mask.load.pd.256(i8* %ptr, <4 x double> zeroinitializer, i8 %mask)
%res4 = fadd <4 x double> %res2, %res1
ret <4 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.load.pd.256(i8*, <4 x double>, i8)
define <4 x double> @test_mask_load_unaligned_pd_256(<4 x double> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovupd (%rdi), %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x10,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovupd (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x10,0x07]
; CHECK-NEXT: vmovupd (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xa9,0x10,0x0f]
; CHECK-NEXT: vaddpd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.loadu.pd.256(i8* %ptr, <4 x double> zeroinitializer, i8 -1)
%res1 = call <4 x double> @llvm.x86.avx512.mask.loadu.pd.256(i8* %ptr, <4 x double> %res, i8 %mask)
%res2 = call <4 x double> @llvm.x86.avx512.mask.loadu.pd.256(i8* %ptr, <4 x double> zeroinitializer, i8 %mask)
%res4 = fadd <4 x double> %res2, %res1
ret <4 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.loadu.pd.256(i8*, <4 x double>, i8)
define <4 x float> @test_mask_load_aligned_ps_128(<4 x float> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovaps (%rdi), %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x28,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovaps (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x28,0x07]
; CHECK-NEXT: vmovaps (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x28,0x0f]
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.load.ps.128(i8* %ptr, <4 x float> zeroinitializer, i8 -1)
%res1 = call <4 x float> @llvm.x86.avx512.mask.load.ps.128(i8* %ptr, <4 x float> %res, i8 %mask)
%res2 = call <4 x float> @llvm.x86.avx512.mask.load.ps.128(i8* %ptr, <4 x float> zeroinitializer, i8 %mask)
%res4 = fadd <4 x float> %res2, %res1
ret <4 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.load.ps.128(i8*, <4 x float>, i8)
define <4 x float> @test_mask_load_unaligned_ps_128(<4 x float> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovups (%rdi), %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x10,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovups (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x10,0x07]
; CHECK-NEXT: vmovups (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x10,0x0f]
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x74,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.loadu.ps.128(i8* %ptr, <4 x float> zeroinitializer, i8 -1)
%res1 = call <4 x float> @llvm.x86.avx512.mask.loadu.ps.128(i8* %ptr, <4 x float> %res, i8 %mask)
%res2 = call <4 x float> @llvm.x86.avx512.mask.loadu.ps.128(i8* %ptr, <4 x float> zeroinitializer, i8 %mask)
%res4 = fadd <4 x float> %res2, %res1
ret <4 x float> %res4
}
declare <4 x float> @llvm.x86.avx512.mask.loadu.ps.128(i8*, <4 x float>, i8)
define <2 x double> @test_mask_load_aligned_pd_128(<2 x double> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovapd (%rdi), %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x28,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovapd (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x28,0x07]
; CHECK-NEXT: vmovapd (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0x28,0x0f]
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.load.pd.128(i8* %ptr, <2 x double> zeroinitializer, i8 -1)
%res1 = call <2 x double> @llvm.x86.avx512.mask.load.pd.128(i8* %ptr, <2 x double> %res, i8 %mask)
%res2 = call <2 x double> @llvm.x86.avx512.mask.load.pd.128(i8* %ptr, <2 x double> zeroinitializer, i8 %mask)
%res4 = fadd <2 x double> %res2, %res1
ret <2 x double> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.load.pd.128(i8*, <2 x double>, i8)
define <2 x double> @test_mask_load_unaligned_pd_128(<2 x double> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovupd (%rdi), %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x10,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovupd (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x10,0x07]
; CHECK-NEXT: vmovupd (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0x10,0x0f]
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0x58,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.loadu.pd.128(i8* %ptr, <2 x double> zeroinitializer, i8 -1)
%res1 = call <2 x double> @llvm.x86.avx512.mask.loadu.pd.128(i8* %ptr, <2 x double> %res, i8 %mask)
%res2 = call <2 x double> @llvm.x86.avx512.mask.loadu.pd.128(i8* %ptr, <2 x double> zeroinitializer, i8 %mask)
%res4 = fadd <2 x double> %res2, %res1
ret <2 x double> %res4
}
declare <2 x double> @llvm.x86.avx512.mask.loadu.pd.128(i8*, <2 x double>, i8)
declare <4 x i32> @llvm.x86.avx512.mask.loadu.d.128(i8*, <4 x i32>, i8)
define <4 x i32> @test_mask_load_unaligned_d_128(i8* %ptr, i8* %ptr2, <4 x i32> %data, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqu32 (%rdi), %xmm0 ## encoding: [0x62,0xf1,0x7e,0x08,0x6f,0x07]
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu32 (%rsi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0x7e,0x09,0x6f,0x06]
; CHECK-NEXT: vmovdqu32 (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0x89,0x6f,0x0f]
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x75,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.loadu.d.128(i8* %ptr, <4 x i32> zeroinitializer, i8 -1)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.loadu.d.128(i8* %ptr2, <4 x i32> %res, i8 %mask)
%res2 = call <4 x i32> @llvm.x86.avx512.mask.loadu.d.128(i8* %ptr, <4 x i32> zeroinitializer, i8 %mask)
%res4 = add <4 x i32> %res2, %res1
ret <4 x i32> %res4
}
declare <8 x i32> @llvm.x86.avx512.mask.loadu.d.256(i8*, <8 x i32>, i8)
define <8 x i32> @test_mask_load_unaligned_d_256(i8* %ptr, i8* %ptr2, <8 x i32> %data, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqu32 (%rdi), %ymm0 ## encoding: [0x62,0xf1,0x7e,0x28,0x6f,0x07]
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu32 (%rsi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0x7e,0x29,0x6f,0x06]
; CHECK-NEXT: vmovdqu32 (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7e,0xa9,0x6f,0x0f]
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x75,0x28,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.loadu.d.256(i8* %ptr, <8 x i32> zeroinitializer, i8 -1)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.loadu.d.256(i8* %ptr2, <8 x i32> %res, i8 %mask)
%res2 = call <8 x i32> @llvm.x86.avx512.mask.loadu.d.256(i8* %ptr, <8 x i32> zeroinitializer, i8 %mask)
%res4 = add <8 x i32> %res2, %res1
ret <8 x i32> %res4
}
declare <2 x i64> @llvm.x86.avx512.mask.loadu.q.128(i8*, <2 x i64>, i8)
define <2 x i64> @test_mask_load_unaligned_q_128(i8* %ptr, i8* %ptr2, <2 x i64> %data, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqu64 (%rdi), %xmm0 ## encoding: [0x62,0xf1,0xfe,0x08,0x6f,0x07]
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu64 (%rsi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0xfe,0x09,0x6f,0x06]
; CHECK-NEXT: vmovdqu64 (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfe,0x89,0x6f,0x0f]
; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.loadu.q.128(i8* %ptr, <2 x i64> zeroinitializer, i8 -1)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.loadu.q.128(i8* %ptr2, <2 x i64> %res, i8 %mask)
%res2 = call <2 x i64> @llvm.x86.avx512.mask.loadu.q.128(i8* %ptr, <2 x i64> zeroinitializer, i8 %mask)
%res4 = add <2 x i64> %res2, %res1
ret <2 x i64> %res4
}
declare <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8*, <4 x i64>, i8)
define <4 x i64> @test_mask_load_unaligned_q_256(i8* %ptr, i8* %ptr2, <4 x i64> %data, i8 %mask) {
; CHECK-LABEL: test_mask_load_unaligned_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqu64 (%rdi), %ymm0 ## encoding: [0x62,0xf1,0xfe,0x28,0x6f,0x07]
; CHECK-NEXT: kmovw %edx, %k1 ## encoding: [0xc5,0xf8,0x92,0xca]
; CHECK-NEXT: vmovdqu64 (%rsi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0xfe,0x29,0x6f,0x06]
; CHECK-NEXT: vmovdqu64 (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfe,0xa9,0x6f,0x0f]
; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 -1)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr2, <4 x i64> %res, i8 %mask)
%res2 = call <4 x i64> @llvm.x86.avx512.mask.loadu.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 %mask)
%res4 = add <4 x i64> %res2, %res1
ret <4 x i64> %res4
}
declare <4 x i32> @llvm.x86.avx512.mask.load.d.128(i8*, <4 x i32>, i8)
define <4 x i32> @test_mask_load_aligned_d_128(<4 x i32> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa32 (%rdi), %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0x6f,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovdqa32 (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x6f,0x07]
; CHECK-NEXT: vmovdqa32 (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x6f,0x0f]
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x75,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.load.d.128(i8* %ptr, <4 x i32> zeroinitializer, i8 -1)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.load.d.128(i8* %ptr, <4 x i32> %res, i8 %mask)
%res2 = call <4 x i32> @llvm.x86.avx512.mask.load.d.128(i8* %ptr, <4 x i32> zeroinitializer, i8 %mask)
%res4 = add <4 x i32> %res2, %res1
ret <4 x i32> %res4
}
declare <8 x i32> @llvm.x86.avx512.mask.load.d.256(i8*, <8 x i32>, i8)
define <8 x i32> @test_mask_load_aligned_d_256(<8 x i32> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa32 (%rdi), %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0x6f,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovdqa32 (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x6f,0x07]
; CHECK-NEXT: vmovdqa32 (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x6f,0x0f]
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x75,0x28,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.load.d.256(i8* %ptr, <8 x i32> zeroinitializer, i8 -1)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.load.d.256(i8* %ptr, <8 x i32> %res, i8 %mask)
%res2 = call <8 x i32> @llvm.x86.avx512.mask.load.d.256(i8* %ptr, <8 x i32> zeroinitializer, i8 %mask)
%res4 = add <8 x i32> %res2, %res1
ret <8 x i32> %res4
}
declare <2 x i64> @llvm.x86.avx512.mask.load.q.128(i8*, <2 x i64>, i8)
define <2 x i64> @test_mask_load_aligned_q_128(<2 x i64> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa64 (%rdi), %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovdqa64 (%rdi), %xmm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x6f,0x07]
; CHECK-NEXT: vmovdqa64 (%rdi), %xmm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0x6f,0x0f]
; CHECK-NEXT: vpaddq %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xf5,0x08,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.load.q.128(i8* %ptr, <2 x i64> zeroinitializer, i8 -1)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.load.q.128(i8* %ptr, <2 x i64> %res, i8 %mask)
%res2 = call <2 x i64> @llvm.x86.avx512.mask.load.q.128(i8* %ptr, <2 x i64> zeroinitializer, i8 %mask)
%res4 = add <2 x i64> %res2, %res1
ret <2 x i64> %res4
}
declare <4 x i64> @llvm.x86.avx512.mask.load.q.256(i8*, <4 x i64>, i8)
define <4 x i64> @test_mask_load_aligned_q_256(<4 x i64> %data, i8* %ptr, i8 %mask) {
; CHECK-LABEL: test_mask_load_aligned_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmovdqa64 (%rdi), %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0x07]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vmovdqa64 (%rdi), %ymm0 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x6f,0x07]
; CHECK-NEXT: vmovdqa64 (%rdi), %ymm1 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xa9,0x6f,0x0f]
; CHECK-NEXT: vpaddq %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xf5,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.load.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 -1)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.load.q.256(i8* %ptr, <4 x i64> %res, i8 %mask)
%res2 = call <4 x i64> @llvm.x86.avx512.mask.load.q.256(i8* %ptr, <4 x i64> zeroinitializer, i8 %mask)
%res4 = add <4 x i64> %res2, %res1
ret <4 x i64> %res4
}
[AVX512] Remove maksed pshufd, pshuflw, and phufhw intrinsics and autoupgrade them to selects and shufflevector. llvm-svn: 272527
2016-06-13 10:36:48 +08:00
declare <4 x i32> @llvm.x86.avx512.mask.pshuf.d.128(<4 x i32>, i32, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_pshuf_d_128(<4 x i32> %x0, i32 %x1, <4 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pshuf_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpshufd $3, %xmm0, %xmm2 ## encoding: [0x62,0xf1,0x7d,0x08,0x70,0xd0,0x03]
; CHECK-NEXT: ## xmm2 = xmm0[3,0,0,0]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpshufd $3, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x70,0xc8,0x03]
[X86][AVX512] Add support for VPALIGNR/PSHUFD/PSHUFHW/PSHUFLW masked shuffle comments llvm-svn: 274466
2016-07-03 23:00:51 +08:00
; CHECK-NEXT: ## xmm1 {%k1} = xmm0[3,0,0,0]
[AVX512] Remove maksed pshufd, pshuflw, and phufhw intrinsics and autoupgrade them to selects and shufflevector. llvm-svn: 272527
2016-06-13 10:36:48 +08:00
; CHECK-NEXT: vpshufd $3, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0x70,0xc0,0x03]
[X86][AVX512] Add support for VPALIGNR/PSHUFD/PSHUFHW/PSHUFLW masked shuffle comments llvm-svn: 274466
2016-07-03 23:00:51 +08:00
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[3,0,0,0]
[AVX512] Remove maksed pshufd, pshuflw, and phufhw intrinsics and autoupgrade them to selects and shufflevector. llvm-svn: 272527
2016-06-13 10:36:48 +08:00
; CHECK-NEXT: vpaddd %xmm0, %xmm1, %xmm0 ## encoding: [0x62,0xf1,0x75,0x08,0xfe,0xc0]
; CHECK-NEXT: vpaddd %xmm2, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfe,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pshuf.d.128(<4 x i32> %x0, i32 3, <4 x i32> %x2, i8 %x3)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.pshuf.d.128(<4 x i32> %x0, i32 3, <4 x i32> zeroinitializer, i8 %x3)
%res2 = call <4 x i32> @llvm.x86.avx512.mask.pshuf.d.128(<4 x i32> %x0, i32 3, <4 x i32> %x2, i8 -1)
%res3 = add <4 x i32> %res, %res1
%res4 = add <4 x i32> %res3, %res2
ret <4 x i32> %res4
}
declare <8 x i32> @llvm.x86.avx512.mask.pshuf.d.256(<8 x i32>, i32, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_pshuf_d_256(<8 x i32> %x0, i32 %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pshuf_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpshufd $3, %ymm0, %ymm2 ## encoding: [0x62,0xf1,0x7d,0x28,0x70,0xd0,0x03]
; CHECK-NEXT: ## ymm2 = ymm0[3,0,0,0,7,4,4,4]
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpshufd $3, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x70,0xc8,0x03]
[X86][AVX512] Add support for VPALIGNR/PSHUFD/PSHUFHW/PSHUFLW masked shuffle comments llvm-svn: 274466
2016-07-03 23:00:51 +08:00
; CHECK-NEXT: ## ymm1 {%k1} = ymm0[3,0,0,0,7,4,4,4]
[AVX512] Remove maksed pshufd, pshuflw, and phufhw intrinsics and autoupgrade them to selects and shufflevector. llvm-svn: 272527
2016-06-13 10:36:48 +08:00
; CHECK-NEXT: vpshufd $3, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0x70,0xc0,0x03]
[X86][AVX512] Add support for VPALIGNR/PSHUFD/PSHUFHW/PSHUFLW masked shuffle comments llvm-svn: 274466
2016-07-03 23:00:51 +08:00
; CHECK-NEXT: ## ymm0 {%k1} {z} = ymm0[3,0,0,0,7,4,4,4]
[AVX512] Remove maksed pshufd, pshuflw, and phufhw intrinsics and autoupgrade them to selects and shufflevector. llvm-svn: 272527
2016-06-13 10:36:48 +08:00
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0 ## encoding: [0x62,0xf1,0x75,0x28,0xfe,0xc0]
; CHECK-NEXT: vpaddd %ymm2, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfe,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pshuf.d.256(<8 x i32> %x0, i32 3, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pshuf.d.256(<8 x i32> %x0, i32 3, <8 x i32> zeroinitializer, i8 %x3)
%res2 = call <8 x i32> @llvm.x86.avx512.mask.pshuf.d.256(<8 x i32> %x0, i32 3, <8 x i32> %x2, i8 -1)
%res3 = add <8 x i32> %res, %res1
%res4 = add <8 x i32> %res3, %res2
ret <8 x i32> %res4
}
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
define i8 @test_pcmpeq_d_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_pcmpeq_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpeqd %ymm1, %ymm0, %k0 ## encoding: [0x62,0xf1,0x7d,0x28,0x76,0xc1]
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.d.256(<8 x i32> %a, <8 x i32> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpeq_d_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpeq_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpeqd %ymm1, %ymm0, %k0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x76,0xc1]
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.d.256(<8 x i32> %a, <8 x i32> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpeq.d.256(<8 x i32>, <8 x i32>, i8)
define i8 @test_pcmpeq_q_256(<4 x i64> %a, <4 x i64> %b) {
; CHECK-LABEL: test_pcmpeq_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpeqq %ymm1, %ymm0, %k0 ## encoding: [0x62,0xf2,0xfd,0x28,0x29,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.q.256(<4 x i64> %a, <4 x i64> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpeq_q_256(<4 x i64> %a, <4 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpeq_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpeqq %ymm1, %ymm0, %k0 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x29,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.q.256(<4 x i64> %a, <4 x i64> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpeq.q.256(<4 x i64>, <4 x i64>, i8)
define i8 @test_pcmpgt_d_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_pcmpgt_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpgtd %ymm1, %ymm0, %k0 ## encoding: [0x62,0xf1,0x7d,0x28,0x66,0xc1]
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.d.256(<8 x i32> %a, <8 x i32> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpgt_d_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpgt_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpgtd %ymm1, %ymm0, %k0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x66,0xc1]
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.d.256(<8 x i32> %a, <8 x i32> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpgt.d.256(<8 x i32>, <8 x i32>, i8)
define i8 @test_pcmpgt_q_256(<4 x i64> %a, <4 x i64> %b) {
; CHECK-LABEL: test_pcmpgt_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpgtq %ymm1, %ymm0, %k0 ## encoding: [0x62,0xf2,0xfd,0x28,0x37,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.q.256(<4 x i64> %a, <4 x i64> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpgt_q_256(<4 x i64> %a, <4 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpgt_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpgtq %ymm1, %ymm0, %k0 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x37,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.q.256(<4 x i64> %a, <4 x i64> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpgt.q.256(<4 x i64>, <4 x i64>, i8)
define i8 @test_pcmpeq_d_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_pcmpeq_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm0, %k0 ## encoding: [0x62,0xf1,0x7d,0x08,0x76,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.d.128(<4 x i32> %a, <4 x i32> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpeq_d_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpeq_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpeqd %xmm1, %xmm0, %k0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x76,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.d.128(<4 x i32> %a, <4 x i32> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpeq.d.128(<4 x i32>, <4 x i32>, i8)
define i8 @test_pcmpeq_q_128(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test_pcmpeq_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpeqq %xmm1, %xmm0, %k0 ## encoding: [0x62,0xf2,0xfd,0x08,0x29,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0e]
; CHECK-NEXT: kshiftrw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0e]
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.q.128(<2 x i64> %a, <2 x i64> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpeq_q_128(<2 x i64> %a, <2 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpeq_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpeqq %xmm1, %xmm0, %k0 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x29,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0e]
; CHECK-NEXT: kshiftrw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0e]
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpeq.q.128(<2 x i64> %a, <2 x i64> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpeq.q.128(<2 x i64>, <2 x i64>, i8)
define i8 @test_pcmpgt_d_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_pcmpgt_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpgtd %xmm1, %xmm0, %k0 ## encoding: [0x62,0xf1,0x7d,0x08,0x66,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.d.128(<4 x i32> %a, <4 x i32> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpgt_d_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpgt_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpgtd %xmm1, %xmm0, %k0 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x66,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.d.128(<4 x i32> %a, <4 x i32> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpgt.d.128(<4 x i32>, <4 x i32>, i8)
define i8 @test_pcmpgt_q_128(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test_pcmpgt_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpcmpgtq %xmm1, %xmm0, %k0 ## encoding: [0x62,0xf2,0xfd,0x08,0x37,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0e]
; CHECK-NEXT: kshiftrw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0e]
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.q.128(<2 x i64> %a, <2 x i64> %b, i8 -1)
ret i8 %res
}
define i8 @test_mask_pcmpgt_q_128(<2 x i64> %a, <2 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_pcmpgt_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpcmpgtq %xmm1, %xmm0, %k0 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x37,0xc1]
[AVX512] Zero extend the result of vpcmpeq/vpcmpgt and similar intrinsics in the autoupgrade code. This currently results in worse codegen but is needed for correctness. llvm-svn: 274736
2016-07-07 14:11:07 +08:00
; CHECK-NEXT: kshiftlw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0e]
; CHECK-NEXT: kshiftrw $14, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0e]
; CHECK-NEXT: kshiftlw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x32,0xc0,0x0c]
; CHECK-NEXT: kshiftrw $12, %k0, %k0 ## encoding: [0xc4,0xe3,0xf9,0x30,0xc0,0x0c]
[AVX512] Remove the masked vpcmpeq/vcmpgt intrinsics and autoupgrade them to native icmps. llvm-svn: 273240
2016-06-21 11:53:24 +08:00
; CHECK-NEXT: kmovw %k0, %eax ## encoding: [0xc5,0xf8,0x93,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call i8 @llvm.x86.avx512.mask.pcmpgt.q.128(<2 x i64> %a, <2 x i64> %b, i8 %mask)
ret i8 %res
}
declare i8 @llvm.x86.avx512.mask.pcmpgt.q.128(<2 x i64>, <2 x i64>, i8)
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
declare <2 x double> @llvm.x86.avx512.mask.unpckh.pd.128(<2 x double>, <2 x double>, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_unpckh_pd_128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckh_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpckhpd %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0xfd,0x08,0x15,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[1],xmm1[1]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpckhpd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x15,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[1],xmm1[1]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddpd %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.unpckh.pd.128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3)
%res1 = call <2 x double> @llvm.x86.avx512.mask.unpckh.pd.128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1)
%res2 = fadd <2 x double> %res, %res1
ret <2 x double> %res2
}
declare <4 x double> @llvm.x86.avx512.mask.unpckh.pd.256(<4 x double>, <4 x double>, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_unpckh_pd_256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckh_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpckhpd %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0xfd,0x28,0x15,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpckhpd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x15,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddpd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.unpckh.pd.256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 %x3)
%res1 = call <4 x double> @llvm.x86.avx512.mask.unpckh.pd.256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 -1)
%res2 = fadd <4 x double> %res, %res1
ret <4 x double> %res2
}
declare <4 x float> @llvm.x86.avx512.mask.unpckh.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_unpckh_ps_128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckh_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpckhps %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0x7c,0x08,0x15,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpckhps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x15,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddps %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.unpckh.ps.128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3)
%res1 = call <4 x float> @llvm.x86.avx512.mask.unpckh.ps.128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
}
declare <8 x float> @llvm.x86.avx512.mask.unpckh.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_unpckh_ps_256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckh_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpckhps %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0x7c,0x28,0x15,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpckhps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x15,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddps %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.unpckh.ps.256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 %x3)
%res1 = call <8 x float> @llvm.x86.avx512.mask.unpckh.ps.256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 -1)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
declare <2 x double> @llvm.x86.avx512.mask.unpckl.pd.128(<2 x double>, <2 x double>, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_unpckl_pd_128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckl_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpcklpd %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0xfd,0x08,0x14,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[0],xmm1[0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpcklpd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x14,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[0],xmm1[0]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddpd %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.unpckl.pd.128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3)
%res1 = call <2 x double> @llvm.x86.avx512.mask.unpckl.pd.128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1)
%res2 = fadd <2 x double> %res, %res1
ret <2 x double> %res2
}
declare <4 x double> @llvm.x86.avx512.mask.unpckl.pd.256(<4 x double>, <4 x double>, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_unpckl_pd_256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckl_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpcklpd %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0xfd,0x28,0x14,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpcklpd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x14,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddpd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.unpckl.pd.256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 %x3)
%res1 = call <4 x double> @llvm.x86.avx512.mask.unpckl.pd.256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x2, i8 -1)
%res2 = fadd <4 x double> %res, %res1
ret <4 x double> %res2
}
declare <4 x float> @llvm.x86.avx512.mask.unpckl.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_unpckl_ps_128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckl_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpcklps %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0x7c,0x08,0x14,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpcklps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x14,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddps %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.unpckl.ps.128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3)
%res1 = call <4 x float> @llvm.x86.avx512.mask.unpckl.ps.128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
}
declare <8 x float> @llvm.x86.avx512.mask.unpckl.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_unpckl_ps_256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_unpckl_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vunpcklps %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0x7c,0x28,0x14,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vunpcklps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x14,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vaddps %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.unpckl.ps.256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 %x3)
%res1 = call <8 x float> @llvm.x86.avx512.mask.unpckl.ps.256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x2, i8 -1)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
declare <4 x i32> @llvm.x86.avx512.mask.punpckhd.q.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_punpckhd_q_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckhd_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckhdq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0x7d,0x08,0x6a,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckhdq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x6a,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.punpckhd.q.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.punpckhd.q.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <4 x i32> @llvm.x86.avx512.mask.punpckld.q.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_punpckld_q_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckld_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckldq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0x7d,0x08,0x62,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckldq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0x62,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.punpckld.q.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %x3)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.punpckld.q.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 -1)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.punpckhd.q.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_punpckhd_q_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckhd_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckhdq %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0x7d,0x28,0x6a,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckhdq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x6a,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.punpckhd.q.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.punpckhd.q.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.punpckld.q.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_punpckld_q_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckld_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckldq %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0x7d,0x28,0x62,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckldq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0x62,0xd1]
[X86][AVX512] Add support for UNPCK masked shuffle comments llvm-svn: 274464
2016-07-03 22:26:21 +08:00
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
[AVX512] Remove masked unpack intrinsics and autoupgrade to vectorshuffle and selects. llvm-svn: 273543
2016-06-23 15:37:33 +08:00
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.punpckld.q.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.punpckld.q.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.punpckhqd.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_punpckhqd_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckhqd_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckhqdq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0xfd,0x08,0x6d,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[1],xmm1[1]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckhqdq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x6d,0xd1]
; CHECK-NEXT: ## xmm2 = xmm0[1],xmm1[1]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.punpckhqd.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.punpckhqd.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.punpcklqd.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_punpcklqd_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpcklqd_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpcklqdq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0xfd,0x08,0x6c,0xd9]
; CHECK-NEXT: ## xmm3 = xmm0[0],xmm1[0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpcklqdq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0x6c,0xd1]
; CHECK-NEXT: ## xmm2 = xmm0[0],xmm1[0]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.punpcklqd.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.punpcklqd.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.punpcklqd.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_punpcklqd_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpcklqd_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpcklqdq %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0xfd,0x28,0x6c,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpcklqdq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x6c,0xd1]
; CHECK-NEXT: ## ymm2 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
; CHECK-NEXT: vpaddq %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.punpcklqd.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.punpcklqd.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 -1)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.punpckhqd.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_punpckhqd_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_punpckhqd_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpunpckhqdq %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0xfd,0x28,0x6d,0xd9]
; CHECK-NEXT: ## ymm3 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpunpckhqdq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0x6d,0xd1]
; CHECK-NEXT: ## ymm2 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
; CHECK-NEXT: vpaddq %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.punpckhqd.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %x3)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.punpckhqd.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 -1)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
define <4 x i32> @test_mask_and_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_and_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xdb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xdb,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xdb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_and_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xdb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_and_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xdb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_and_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.pand.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <8 x i32> @test_mask_and_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_and_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xdb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xdb,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandd %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xdb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_and_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xdb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_and_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandd (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xdb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_and_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_and_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandd (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xdb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.pand.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <4 x i32> @test_mask_or_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_or_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xeb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpord %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xeb,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpord %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xeb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_or_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xeb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_or_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xeb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_or_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.por.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <8 x i32> @test_mask_or_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_or_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xeb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpord %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xeb,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpord %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xeb,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_or_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xeb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_or_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpord (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xeb,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_or_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_or_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpord (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xeb,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.por.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <4 x i32> @test_mask_xor_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_xor_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xef,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpxord %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xef,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpxord %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xef,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_xor_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xef,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_xor_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xef,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_xor_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.pxor.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <8 x i32> @test_mask_xor_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_xor_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xef,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpxord %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xef,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpxord %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xef,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_xor_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xef,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_xor_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpxord (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xef,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_xor_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_xor_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpxord (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xef,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.pxor.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <4 x i32> @test_mask_andnot_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_andnot_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xdf,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_andnot_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.pandn.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <8 x i32> @test_mask_andnot_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_andnot_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xdf,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnd %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnd (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_andnot_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnd (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.pandn.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <2 x i64> @test_mask_andnot_epi64_rr_128(<2 x i64> %a, <2 x i64> %b) {
; CHECK-LABEL: test_mask_andnot_epi64_rr_128:
; CHECK: ## BB#0:
[AVX-512] Don't let ExeDependencyFix pass convert VPANDD/Q to VPANDPS/PD unless DQI instructions are supported. Same for ANDN, OR, and XOR. Thanks to Igor Breger for pointing out my mistake. llvm-svn: 277292
2016-08-01 01:15:07 +08:00
; CHECK-NEXT: vpandnq %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0xdf,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 -1)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rrk_128(<2 x i64> %a, <2 x i64> %b, <2 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0xdf,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> %passThru, i8 %mask)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rrkz_128(<2 x i64> %a, <2 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnq %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 %mask)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rm_128(<2 x i64> %a, <2 x i64>* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi64_rm_128:
; CHECK: ## BB#0:
[AVX-512] Don't let ExeDependencyFix pass convert VPANDD/Q to VPANDPS/PD unless DQI instructions are supported. Same for ANDN, OR, and XOR. Thanks to Igor Breger for pointing out my mistake. llvm-svn: 277292
2016-08-01 01:15:07 +08:00
; CHECK-NEXT: vpandnq (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0xdf,0x07]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <2 x i64>, <2 x i64>* %ptr_b
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 -1)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rmk_128(<2 x i64> %a, <2 x i64>* %ptr_b, <2 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <2 x i64>, <2 x i64>* %ptr_b
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> %passThru, i8 %mask)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rmkz_128(<2 x i64> %a, <2 x i64>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <2 x i64>, <2 x i64>* %ptr_b
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 %mask)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rmb_128(<2 x i64> %a, i64* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi64_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnq (%rdi){1to2}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x18,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <2 x i64> undef, i64 %q, i32 0
%b = shufflevector <2 x i64> %vecinit.i, <2 x i64> undef, <2 x i32> zeroinitializer
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 -1)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rmbk_128(<2 x i64> %a, i64* %ptr_b, <2 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi){1to2}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0xfd,0x19,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <2 x i64> undef, i64 %q, i32 0
%b = shufflevector <2 x i64> %vecinit.i, <2 x i64> undef, <2 x i32> zeroinitializer
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> %passThru, i8 %mask)
ret <2 x i64> %res
}
define <2 x i64> @test_mask_andnot_epi64_rmbkz_128(<2 x i64> %a, i64* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi){1to2}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x99,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <2 x i64> undef, i64 %q, i32 0
%b = shufflevector <2 x i64> %vecinit.i, <2 x i64> undef, <2 x i32> zeroinitializer
%res = call <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64> %a, <2 x i64> %b, <2 x i64> zeroinitializer, i8 %mask)
ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.avx512.mask.pandn.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <4 x i64> @test_mask_andnot_epi64_rr_256(<4 x i64> %a, <4 x i64> %b) {
; CHECK-LABEL: test_mask_andnot_epi64_rr_256:
; CHECK: ## BB#0:
[AVX-512] Don't let ExeDependencyFix pass convert VPANDD/Q to VPANDPS/PD unless DQI instructions are supported. Same for ANDN, OR, and XOR. Thanks to Igor Breger for pointing out my mistake. llvm-svn: 277292
2016-08-01 01:15:07 +08:00
; CHECK-NEXT: vpandnq %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0xdf,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 -1)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rrk_256(<4 x i64> %a, <4 x i64> %b, <4 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0xdf,0xd1]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> %passThru, i8 %mask)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rrkz_256(<4 x i64> %a, <4 x i64> %b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpandnq %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xa9,0xdf,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 %mask)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rm_256(<4 x i64> %a, <4 x i64>* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi64_rm_256:
; CHECK: ## BB#0:
[AVX-512] Don't let ExeDependencyFix pass convert VPANDD/Q to VPANDPS/PD unless DQI instructions are supported. Same for ANDN, OR, and XOR. Thanks to Igor Breger for pointing out my mistake. llvm-svn: 277292
2016-08-01 01:15:07 +08:00
; CHECK-NEXT: vpandnq (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0xdf,0x07]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i64>, <4 x i64>* %ptr_b
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 -1)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rmk_256(<4 x i64> %a, <4 x i64>* %ptr_b, <4 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i64>, <4 x i64>* %ptr_b
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> %passThru, i8 %mask)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rmkz_256(<4 x i64> %a, <4 x i64>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xa9,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i64>, <4 x i64>* %ptr_b
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 %mask)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rmb_256(<4 x i64> %a, i64* %ptr_b) {
; CHECK-LABEL: test_mask_andnot_epi64_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpandnq (%rdi){1to4}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x38,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <4 x i64> undef, i64 %q, i32 0
%b = shufflevector <4 x i64> %vecinit.i, <4 x i64> undef, <4 x i32> zeroinitializer
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 -1)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rmbk_256(<4 x i64> %a, i64* %ptr_b, <4 x i64> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi){1to4}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0xfd,0x39,0xdf,0x0f]
[AVX512] Add VLX packed move instructions to the execution dependency fix pass and update tests. llvm-svn: 277304
2016-08-01 04:20:01 +08:00
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
[AVX512] Remove masked logic op intrinsics and autoupgrade them to native IR. llvm-svn: 275155
2016-07-12 13:27:53 +08:00
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <4 x i64> undef, i64 %q, i32 0
%b = shufflevector <4 x i64> %vecinit.i, <4 x i64> undef, <4 x i32> zeroinitializer
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> %passThru, i8 %mask)
ret <4 x i64> %res
}
define <4 x i64> @test_mask_andnot_epi64_rmbkz_256(<4 x i64> %a, i64* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_andnot_epi64_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpandnq (%rdi){1to4}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xb9,0xdf,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i64, i64* %ptr_b
%vecinit.i = insertelement <4 x i64> undef, i64 %q, i32 0
%b = shufflevector <4 x i64> %vecinit.i, <4 x i64> undef, <4 x i32> zeroinitializer
%res = call <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64> %a, <4 x i64> %b, <4 x i64> zeroinitializer, i8 %mask)
ret <4 x i64> %res
}
declare <4 x i64> @llvm.x86.avx512.mask.pandn.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
[AVX-512] Remove masked integer add/sub/mull intrinsics and upgrade to native IR. llvm-svn: 280611
2016-09-04 10:09:53 +08:00
define <4 x i32> @test_mask_add_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_add_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xfe,0xd1]
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpaddd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_add_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xfe,0x0f]
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_add_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xfe,0x0f]
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_add_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.padd.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32> @test_mask_sub_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_sub_epi32_rr_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfa,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rrk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xfa,0xd1]
; CHECK-NEXT: vmovdqa64 %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rrkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpsubd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xfa,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_sub_epi32_rm_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd (%rdi), %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi), %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x09,0xfa,0x0f]
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi), %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x89,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <4 x i32>, <4 x i32>* %ptr_b
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_sub_epi32_rmb_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd (%rdi){1to4}, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x18,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 -1)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <4 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmbk_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi){1to4}, %xmm0, %xmm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x19,0xfa,0x0f]
; CHECK-NEXT: vmovdqa64 %xmm1, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> %passThru, i8 %mask)
ret <4 x i32> %res
}
define <4 x i32> @test_mask_sub_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmbkz_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0x99,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
%b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
%res = call <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32> %a, <4 x i32> %b, <4 x i32> zeroinitializer, i8 %mask)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx512.mask.psub.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <8 x i32> @test_mask_sub_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_sub_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfa,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpsubd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xfa,0xd1]
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpsubd %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xfa,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_sub_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xfa,0x0f]
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_sub_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpsubd (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xfa,0x0f]
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_sub_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_sub_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpsubd (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xfa,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.psub.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32> @test_mask_add_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_add_epi32_rr_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rrk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xfe,0xd1]
; CHECK-NEXT: vmovdqa64 %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rrkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xfe,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; CHECK-LABEL: test_mask_add_epi32_rm_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd (%rdi), %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi), %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x29,0xfe,0x0f]
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi), %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xa9,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%b = load <8 x i32>, <8 x i32>* %ptr_b
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; CHECK-LABEL: test_mask_add_epi32_rmb_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpaddd (%rdi){1to8}, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x38,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 -1)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <8 x i32> %passThru, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmbk_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi){1to8}, %ymm0, %ymm1 {%k1} ## encoding: [0x62,0xf1,0x7d,0x39,0xfe,0x0f]
; CHECK-NEXT: vmovdqa64 %ymm1, %ymm0 ## encoding: [0x62,0xf1,0xfd,0x28,0x6f,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> %passThru, i8 %mask)
ret <8 x i32> %res
}
define <8 x i32> @test_mask_add_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i8 %mask) {
; CHECK-LABEL: test_mask_add_epi32_rmbkz_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1 ## encoding: [0xc5,0xf8,0x92,0xce]
; CHECK-NEXT: vpaddd (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7d,0xb9,0xfe,0x07]
; CHECK-NEXT: retq ## encoding: [0xc3]
%q = load i32, i32* %ptr_b
%vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
%b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
%res = call <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32> %a, <8 x i32> %b, <8 x i32> zeroinitializer, i8 %mask)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx512.mask.padd.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
[AVX-512] Remove 128-bit and 256-bit masked floating point add/sub/mul/div intrinsics and upgrade to native IR. llvm-svn: 280633
2016-09-05 02:13:33 +08:00
define <8 x float> @test_mm512_maskz_add_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_add_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.add.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_mask_add_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_add_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x58,0xd1]
; CHECK-NEXT: vmovaps %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.add.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_add_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_add_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.add.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 -1)
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx512.mask.add.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <4 x float> @test_mm512_maskz_add_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_add_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.add.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_mask_add_ps_128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_add_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x58,0xd1]
; CHECK-NEXT: vmovaps %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.add.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_add_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_add_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.add.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 -1)
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.mask.add.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
define <8 x float> @test_mm512_maskz_sub_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_sub_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vsubps %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x5c,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.sub.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_mask_sub_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_sub_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vsubps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x5c,0xd1]
; CHECK-NEXT: vmovaps %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.sub.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_sub_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_sub_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vsubps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x5c,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.sub.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 -1)
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx512.mask.sub.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <4 x float> @test_mm512_maskz_sub_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_sub_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vsubps %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x5c,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.sub.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_mask_sub_ps_128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_sub_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vsubps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x5c,0xd1]
; CHECK-NEXT: vmovaps %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.sub.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_sub_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_sub_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vsubps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x5c,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.sub.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 -1)
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.mask.sub.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
define <8 x float> @test_mm512_maskz_mul_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_mul_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmulps %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x59,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.mul.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_mask_mul_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_mul_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmulps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x59,0xd1]
; CHECK-NEXT: vmovaps %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.mul.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_mul_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_mul_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vmulps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x59,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.mul.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 -1)
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx512.mask.mul.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <4 x float> @test_mm512_maskz_mul_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_mul_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmulps %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x59,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.mul.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_mask_mul_ps_128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_mul_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vmulps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x59,0xd1]
; CHECK-NEXT: vmovaps %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.mul.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_mul_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_mul_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vmulps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x59,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.mul.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 -1)
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.mask.mul.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
define <8 x float> @test_mm512_maskz_div_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_div_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vdivps %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xa9,0x5e,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.div.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_mask_div_ps_256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_div_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vdivps %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0x5e,0xd1]
; CHECK-NEXT: vmovaps %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.div.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float> %src, i8 %mask)
ret <8 x float> %res
}
define <8 x float> @test_mm512_div_ps_256(<8 x float> %a0, <8 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_div_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vdivps %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7c,0x28,0x5e,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.div.ps.256(<8 x float> %a0, <8 x float> %a1, <8 x float>zeroinitializer, i8 -1)
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx512.mask.div.ps.256(<8 x float>, <8 x float>, <8 x float>, i8)
define <4 x float> @test_mm512_maskz_div_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_maskz_div_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vdivps %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x89,0x5e,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.div.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_mask_div_ps_128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask) {
; CHECK-LABEL: test_mm512_mask_div_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vdivps %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0x5e,0xd1]
; CHECK-NEXT: vmovaps %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x28,0xc2]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.div.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float> %src, i8 %mask)
ret <4 x float> %res
}
define <4 x float> @test_mm512_div_ps_128(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
; CHECK-LABEL: test_mm512_div_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vdivps %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7c,0x08,0x5e,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.div.ps.128(<4 x float> %a0, <4 x float> %a1, <4 x float>zeroinitializer, i8 -1)
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.mask.div.ps.128(<4 x float>, <4 x float>, <4 x float>, i8)
[X86] Remove masked shufpd/shufps intrinsics and autoupgrade to native vector shuffles. They were removed from clang previously but accidentally left in the backend. llvm-svn: 281300
2016-09-13 15:40:53 +08:00
declare <2 x double> @llvm.x86.avx512.mask.shuf.pd.128(<2 x double>, <2 x double>, i32, <2 x double>, i8)
define <2 x double>@test_int_x86_avx512_mask_shuf_pd_128(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_pd_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vshufpd $1, %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0xfd,0x08,0xc6,0xd9,0x01]
; CHECK-NEXT: ## xmm3 = xmm0[1],xmm1[0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vshufpd $1, %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x09,0xc6,0xd1,0x01]
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[1],xmm1[0]
; CHECK-NEXT: vshufpd $1, %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x89,0xc6,0xc1,0x01]
; CHECK-NEXT: ## xmm0 {%k1} {z} = xmm0[1],xmm1[0]
; CHECK-NEXT: vaddpd %xmm3, %xmm2, %xmm1 ## encoding: [0x62,0xf1,0xed,0x08,0x58,0xcb]
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0xfd,0x08,0x58,0xc1]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.shuf.pd.128(<2 x double> %x0, <2 x double> %x1, i32 1, <2 x double> %x3, i8 %x4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.shuf.pd.128(<2 x double> %x0, <2 x double> %x1, i32 1, <2 x double> %x3, i8 -1)
%res2 = call <2 x double> @llvm.x86.avx512.mask.shuf.pd.128(<2 x double> %x0, <2 x double> %x1, i32 1, <2 x double> zeroinitializer, i8 %x4)
%res3 = fadd <2 x double> %res, %res1
%res4 = fadd <2 x double> %res2, %res3
ret <2 x double> %res4
}
declare <4 x double> @llvm.x86.avx512.mask.shuf.pd.256(<4 x double>, <4 x double>, i32, <4 x double>, i8)
define <4 x double>@test_int_x86_avx512_mask_shuf_pd_256(<4 x double> %x0, <4 x double> %x1, <4 x double> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_pd_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vshufpd $6, %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0xfd,0x28,0xc6,0xd9,0x06]
; CHECK-NEXT: ## ymm3 = ymm0[0],ymm1[1],ymm0[3],ymm1[2]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vshufpd $6, %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0xfd,0x29,0xc6,0xd1,0x06]
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[0],ymm1[1],ymm0[3],ymm1[2]
; CHECK-NEXT: vaddpd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x double> @llvm.x86.avx512.mask.shuf.pd.256(<4 x double> %x0, <4 x double> %x1, i32 6, <4 x double> %x3, i8 %x4)
%res1 = call <4 x double> @llvm.x86.avx512.mask.shuf.pd.256(<4 x double> %x0, <4 x double> %x1, i32 6, <4 x double> %x3, i8 -1)
%res2 = fadd <4 x double> %res, %res1
ret <4 x double> %res2
}
declare <4 x float> @llvm.x86.avx512.mask.shuf.ps.128(<4 x float>, <4 x float>, i32, <4 x float>, i8)
define <4 x float>@test_int_x86_avx512_mask_shuf_ps_128(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_ps_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vshufps $22, %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf1,0x7c,0x08,0xc6,0xd9,0x16]
; CHECK-NEXT: ## xmm3 = xmm0[2,1],xmm1[1,0]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vshufps $22, %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x09,0xc6,0xd1,0x16]
; CHECK-NEXT: ## xmm2 {%k1} = xmm0[2,1],xmm1[1,0]
; CHECK-NEXT: vaddps %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6c,0x08,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.shuf.ps.128(<4 x float> %x0, <4 x float> %x1, i32 22, <4 x float> %x3, i8 %x4)
%res1 = call <4 x float> @llvm.x86.avx512.mask.shuf.ps.128(<4 x float> %x0, <4 x float> %x1, i32 22, <4 x float> %x3, i8 -1)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
}
declare <8 x float> @llvm.x86.avx512.mask.shuf.ps.256(<8 x float>, <8 x float>, i32, <8 x float>, i8)
define <8 x float>@test_int_x86_avx512_mask_shuf_ps_256(<8 x float> %x0, <8 x float> %x1, <8 x float> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_ps_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vshufps $22, %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf1,0x7c,0x28,0xc6,0xd9,0x16]
; CHECK-NEXT: ## ymm3 = ymm0[2,1],ymm1[1,0],ymm0[6,5],ymm1[5,4]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vshufps $22, %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x29,0xc6,0xd1,0x16]
; CHECK-NEXT: ## ymm2 {%k1} = ymm0[2,1],ymm1[1,0],ymm0[6,5],ymm1[5,4]
; CHECK-NEXT: vaddps %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6c,0x28,0x58,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.shuf.ps.256(<8 x float> %x0, <8 x float> %x1, i32 22, <8 x float> %x3, i8 %x4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.shuf.ps.256(<8 x float> %x0, <8 x float> %x1, i32 22, <8 x float> %x3, i8 -1)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
[AVX-512] Remove masked pmin/pmax intrinsics and autoupgrade to native IR. Clang patch to replace 512-bit vector and 64-bit element versions with native IR will follow. llvm-svn: 284955
2016-10-24 12:04:16 +08:00
declare <4 x i32> @llvm.x86.avx512.mask.pmaxs.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_pmaxs_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x3d,0xd1]
; CHECK-NEXT: vpmaxsd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x3d,0xc1]
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pmaxs.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2 ,i8 %mask)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.pmaxs.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %mask)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.pmaxs.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_pmaxs_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmaxsd %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf2,0x7d,0x28,0x3d,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxsd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x3d,0xd1]
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pmaxs.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmaxs.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.pmaxs.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_pmaxs_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmaxsq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf2,0xfd,0x08,0x3d,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxsq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x3d,0xd1]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pmaxs.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.pmaxs.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.pmaxs.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_pmaxs_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxsq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x3d,0xd1]
; CHECK-NEXT: vpmaxsq %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x3d,0xc1]
; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pmaxs.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.pmaxs.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> zeroinitializer, i8 %mask)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i32> @llvm.x86.avx512.mask.pmaxu.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_pmaxu_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2,i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxud %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x3f,0xd1]
; CHECK-NEXT: vpmaxud %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x3f,0xc1]
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pmaxu.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.pmaxu.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %mask)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.pmaxu.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_pmaxu_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmaxud %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf2,0x7d,0x28,0x3f,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxud %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x3f,0xd1]
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pmaxu.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmaxu.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.pmaxu.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_pmaxu_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmaxuq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf2,0xfd,0x08,0x3f,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxuq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x3f,0xd1]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pmaxu.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.pmaxu.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.pmaxu.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_pmaxu_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpmaxuq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x3f,0xd1]
; CHECK-NEXT: vpmaxuq %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x3f,0xc1]
; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pmaxu.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.pmaxu.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> zeroinitializer, i8 %mask)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i32> @llvm.x86.avx512.mask.pmins.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_pmins_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x39,0xd1]
; CHECK-NEXT: vpminsd %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x39,0xc1]
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pmins.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.pmins.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %mask)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.pmins.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_pmins_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpminsd %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf2,0x7d,0x28,0x39,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminsd %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x39,0xd1]
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pmins.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmins.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.pmins.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_pmins_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpminsq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf2,0xfd,0x08,0x39,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminsq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x39,0xd1]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pmins.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.pmins.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.pmins.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_pmins_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminsq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x39,0xd1]
; CHECK-NEXT: vpminsq %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x39,0xc1]
; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pmins.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.pmins.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> zeroinitializer, i8 %mask)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}
declare <4 x i32> @llvm.x86.avx512.mask.pminu.d.128(<4 x i32>, <4 x i32>, <4 x i32>, i8)
define <4 x i32>@test_int_x86_avx512_mask_pminu_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_d_128:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminud %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x3b,0xd1]
; CHECK-NEXT: vpminud %xmm1, %xmm0, %xmm0 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x3b,0xc1]
; CHECK-NEXT: vpaddd %xmm0, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0x6d,0x08,0xfe,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i32> @llvm.x86.avx512.mask.pminu.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2, i8 %mask)
%res1 = call <4 x i32> @llvm.x86.avx512.mask.pminu.d.128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> zeroinitializer, i8 %mask)
%res2 = add <4 x i32> %res, %res1
ret <4 x i32> %res2
}
declare <8 x i32> @llvm.x86.avx512.mask.pminu.d.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)
define <8 x i32>@test_int_x86_avx512_mask_pminu_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_d_256:
; CHECK: ## BB#0:
; CHECK-NEXT: vpminud %ymm1, %ymm0, %ymm3 ## encoding: [0x62,0xf2,0x7d,0x28,0x3b,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminud %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x3b,0xd1]
; CHECK-NEXT: vpaddd %ymm3, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0x6d,0x28,0xfe,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <8 x i32> @llvm.x86.avx512.mask.pminu.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 %x3)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pminu.d.256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2, i8 -1)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
declare <2 x i64> @llvm.x86.avx512.mask.pminu.q.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
define <2 x i64>@test_int_x86_avx512_mask_pminu_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_q_128:
; CHECK: ## BB#0:
; CHECK-NEXT: vpminuq %xmm1, %xmm0, %xmm3 ## encoding: [0x62,0xf2,0xfd,0x08,0x3b,0xd9]
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminuq %xmm1, %xmm0, %xmm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x09,0x3b,0xd1]
; CHECK-NEXT: vpaddq %xmm3, %xmm2, %xmm0 ## encoding: [0x62,0xf1,0xed,0x08,0xd4,0xc3]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <2 x i64> @llvm.x86.avx512.mask.pminu.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 %x3)
%res1 = call <2 x i64> @llvm.x86.avx512.mask.pminu.q.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2, i8 -1)
%res2 = add <2 x i64> %res, %res1
ret <2 x i64> %res2
}
declare <4 x i64> @llvm.x86.avx512.mask.pminu.q.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
define <4 x i64>@test_int_x86_avx512_mask_pminu_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_q_256:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; CHECK-NEXT: vpminuq %ymm1, %ymm0, %ymm2 {%k1} ## encoding: [0x62,0xf2,0xfd,0x29,0x3b,0xd1]
; CHECK-NEXT: vpminuq %ymm1, %ymm0, %ymm0 {%k1} {z} ## encoding: [0x62,0xf2,0xfd,0xa9,0x3b,0xc1]
; CHECK-NEXT: vpaddq %ymm0, %ymm2, %ymm0 ## encoding: [0x62,0xf1,0xed,0x28,0xd4,0xc0]
; CHECK-NEXT: retq ## encoding: [0xc3]
%res = call <4 x i64> @llvm.x86.avx512.mask.pminu.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2, i8 %mask)
%res1 = call <4 x i64> @llvm.x86.avx512.mask.pminu.q.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> zeroinitializer, i8 %mask)
%res2 = add <4 x i64> %res, %res1
ret <4 x i64> %res2
}