maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AVX512] Add VLX 128/256-bit SET0 operations that encode to 128/256-bit EVEX encoded VPXORD so all 32 registers can be used. 

llvm-svn: 268884
This commit is contained in:
Craig Topper 2016-05-08 21:33:53 +00:00
parent 298b6d7493
commit e5ce84a33c
14 changed files with 114 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -483,6 +483,14 @@ def AVX512_512_SET0 : I<0, Pseudo, (outs VR512:$dst), (ins), "",
[(set VR512:$dst, (v16i32 immAllZerosV))]>;
}
let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
isPseudo = 1, Predicates = [HasVLX] in {
def AVX512_128_SET0 : I<0, Pseudo, (outs VR128X:$dst), (ins), "",
[(set VR128X:$dst, (v4i32 immAllZerosV))]>;
def AVX512_256_SET0 : I<0, Pseudo, (outs VR256X:$dst), (ins), "",
[(set VR256X:$dst, (v8i32 immAllZerosV))]>;
}
//===----------------------------------------------------------------------===//
// AVX-512 - VECTOR INSERT
//

4
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -5512,6 +5512,10 @@ bool X86InstrInfo::expandPostRAPseudo(MachineBasicBlock::iterator MI) const {
case X86::AVX_SET0:
assert(HasAVX && "AVX not supported");
return Expand2AddrUndef(MIB, get(X86::VXORPSYrr));
case X86::AVX512_128_SET0:
return Expand2AddrUndef(MIB, get(X86::VPXORDZ128rr));
case X86::AVX512_256_SET0:
return Expand2AddrUndef(MIB, get(X86::VPXORDZ256rr));
case X86::AVX512_512_SET0:
return Expand2AddrUndef(MIB, get(X86::VPXORDZrr));
case X86::V_SETALLONES:

5
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -472,11 +472,12 @@ let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
// We set canFoldAsLoad because this can be converted to a constant-pool
// load of an all-zeros value if folding it would be beneficial.
let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
isPseudo = 1, SchedRW = [WriteZero] in {
isPseudo = 1, Predicates = [NoVLX], SchedRW = [WriteZero] in {
def V_SET0 : I<0, Pseudo, (outs VR128:$dst), (ins), "",
[(set VR128:$dst, (v4f32 immAllZerosV))]>;
}
let Predicates = [NoVLX] in
def : Pat<(v4i32 immAllZerosV), (V_SET0)>;
@ -485,7 +486,7 @@ def : Pat<(v4i32 immAllZerosV), (V_SET0)>;
// at the rename stage without using any execution unit, so SET0PSY
// and SET0PDY can be used for vector int instructions without penalty
let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1,
isPseudo = 1, Predicates = [HasAVX], SchedRW = [WriteZero] in {
isPseudo = 1, Predicates = [HasAVX, NoVLX], SchedRW = [WriteZero] in {
def AVX_SET0 : I<0, Pseudo, (outs VR256:$dst), (ins), "",
[(set VR256:$dst, (v8i32 immAllZerosV))]>;
}

10
llvm/test/CodeGen/X86/avx512-arith.ll
View File

@ -1,4 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f | FileCheck --check-prefix=CHECK --check-prefix=AVX512F %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512vl | FileCheck --check-prefix=CHECK --check-prefix=AVX512VL %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512bw | FileCheck --check-prefix=CHECK --check-prefix=AVX512BW %s
@ -682,7 +682,7 @@ define <8 x double> @test_mask_vminpd(<8 x double> %dst, <8 x double> %i,
;
; AVX512VL-LABEL: test_mask_vminpd:
; AVX512VL: ## BB#0:
; AVX512VL-NEXT: vpxor %ymm4, %ymm4, %ymm4
; AVX512VL-NEXT: vpxord %ymm4, %ymm4, %ymm4
; AVX512VL-NEXT: vpcmpneqd %ymm4, %ymm3, %k1
; AVX512VL-NEXT: vminpd %zmm2, %zmm1, %zmm0 {%k1}
; AVX512VL-NEXT: retq
@ -703,7 +703,7 @@ define <8 x double> @test_mask_vminpd(<8 x double> %dst, <8 x double> %i,
;
; SKX-LABEL: test_mask_vminpd:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %ymm4, %ymm4, %ymm4
; SKX-NEXT: vpxord %ymm4, %ymm4, %ymm4
; SKX-NEXT: vpcmpneqd %ymm4, %ymm3, %k1
; SKX-NEXT: vminpd %zmm2, %zmm1, %zmm0 {%k1}
; SKX-NEXT: retq
@ -742,7 +742,7 @@ define <8 x double> @test_mask_vmaxpd(<8 x double> %dst, <8 x double> %i,
;
; AVX512VL-LABEL: test_mask_vmaxpd:
; AVX512VL: ## BB#0:
; AVX512VL-NEXT: vpxor %ymm4, %ymm4, %ymm4
; AVX512VL-NEXT: vpxord %ymm4, %ymm4, %ymm4
; AVX512VL-NEXT: vpcmpneqd %ymm4, %ymm3, %k1
; AVX512VL-NEXT: vmaxpd %zmm2, %zmm1, %zmm0 {%k1}
; AVX512VL-NEXT: retq
@ -763,7 +763,7 @@ define <8 x double> @test_mask_vmaxpd(<8 x double> %dst, <8 x double> %i,
;
; SKX-LABEL: test_mask_vmaxpd:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %ymm4, %ymm4, %ymm4
; SKX-NEXT: vpxord %ymm4, %ymm4, %ymm4
; SKX-NEXT: vpcmpneqd %ymm4, %ymm3, %k1
; SKX-NEXT: vmaxpd %zmm2, %zmm1, %zmm0 {%k1}
; SKX-NEXT: retq

15
llvm/test/CodeGen/X86/avx512-calling-conv.ll
View File

@ -1,13 +1,18 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s --check-prefix=ALL_X64 --check-prefix=KNL
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skx | FileCheck %s --check-prefix=ALL_X64 --check-prefix=SKX
; RUN: llc < %s -mtriple=i686-apple-darwin -mcpu=knl | FileCheck %s --check-prefix=KNL_X32
define <16 x i1> @test1() {
; ALL_X64-LABEL: test1:
; ALL_X64: ## BB#0:
; ALL_X64-NEXT: vxorps %xmm0, %xmm0, %xmm0
; ALL_X64-NEXT: retq
; KNL-LABEL: test1:
; KNL: ## BB#0:
; KNL-NEXT: vxorps %xmm0, %xmm0, %xmm0
; KNL-NEXT: retq
;
; SKX-LABEL: test1:
; SKX: ## BB#0:
; SKX-NEXT: vpxord %xmm0, %xmm0, %xmm0
; SKX-NEXT: retq
;
; KNL_X32-LABEL: test1:
; KNL_X32: ## BB#0:

10
llvm/test/CodeGen/X86/avx512-vec-cmp.ll
View File

@ -1,4 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s --check-prefix=KNL
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=skx | FileCheck %s --check-prefix=SKX
@ -127,7 +127,7 @@ define <4 x float> @test7(<4 x float> %a, <4 x float> %b) {
;
; SKX-LABEL: test7:
; SKX: ## BB#0:
; SKX-NEXT: vxorps %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vcmpltps %xmm2, %xmm0, %k1
; SKX-NEXT: vmovaps %xmm0, %xmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -148,7 +148,7 @@ define <2 x double> @test8(<2 x double> %a, <2 x double> %b) {
;
; SKX-LABEL: test8:
; SKX: ## BB#0:
; SKX-NEXT: vxorpd %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vcmpltpd %xmm2, %xmm0, %k1
; SKX-NEXT: vmovapd %xmm0, %xmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -969,7 +969,7 @@ define <4 x i32> @test44(<4 x i16> %x, <4 x i16> %y) #0 {
;
; SKX-LABEL: test44:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm2[1],xmm1[2],xmm2[3],xmm1[4],xmm2[5],xmm1[6],xmm2[7]
; SKX-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3],xmm0[4],xmm2[5],xmm0[6],xmm2[7]
; SKX-NEXT: vpcmpeqd %xmm1, %xmm0, %k0
@ -992,7 +992,7 @@ define <2 x i64> @test45(<2 x i16> %x, <2 x i16> %y) #0 {
;
; SKX-LABEL: test45:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0],xmm2[1,2,3],xmm1[4],xmm2[5,6,7]
; SKX-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],xmm2[1,2,3],xmm0[4],xmm2[5,6,7]
; SKX-NEXT: vpcmpeqq %xmm1, %xmm0, %k1

8
llvm/test/CodeGen/X86/avx512vbmivl-intrinsics.ll
View File

@ -89,7 +89,7 @@ define <16 x i8>@test_int_x86_avx512_mask_vpermi2var_qi_128(<16 x i8> %x0, <16 x
; CHECK-NEXT: vmovaps %zmm1, %zmm3 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xd9]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm3 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x7d,0xda]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm1 ## encoding: [0x62,0xf2,0x7d,0x08,0x7d,0xca]
; CHECK-NEXT: vpxor %xmm4, %xmm4, %xmm4 ## encoding: [0xc5,0xd9,0xef,0xe4]
; CHECK-NEXT: vpxord %xmm4, %xmm4, %xmm4 ## encoding: [0x62,0xf1,0x5d,0x08,0xef,0xe4]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm4 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x7d,0xe2]
; CHECK-NEXT: vpaddb %xmm4, %xmm3, %xmm0 ## encoding: [0x62,0xf1,0x65,0x08,0xfc,0xc4]
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfc,0xc1]
@ -111,7 +111,7 @@ define <32 x i8>@test_int_x86_avx512_mask_vpermi2var_qi_256(<32 x i8> %x0, <32 x
; CHECK-NEXT: vmovaps %zmm1, %zmm3 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xd9]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm3 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x7d,0xda]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm1 ## encoding: [0x62,0xf2,0x7d,0x28,0x7d,0xca]
; CHECK-NEXT: vpxor %ymm4, %ymm4, %ymm4 ## encoding: [0xc5,0xdd,0xef,0xe4]
; CHECK-NEXT: vpxord %ymm4, %ymm4, %ymm4 ## encoding: [0x62,0xf1,0x5d,0x28,0xef,0xe4]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm4 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x7d,0xe2]
; CHECK-NEXT: vpaddb %ymm4, %ymm3, %ymm0 ## encoding: [0x62,0xf1,0x65,0x28,0xfc,0xc4]
; CHECK-NEXT: vpaddb %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfc,0xc1]
@ -133,7 +133,7 @@ define <16 x i8>@test_int_x86_avx512_mask_vpermt2var_qi_128(<16 x i8> %x0, <16 x
; CHECK-NEXT: vmovaps %zmm1, %zmm3 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xd9]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm3 {%k1} ## encoding: [0x62,0xf2,0x7d,0x09,0x7d,0xda]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm1 ## encoding: [0x62,0xf2,0x7d,0x08,0x7d,0xca]
; CHECK-NEXT: vpxor %xmm4, %xmm4, %xmm4 ## encoding: [0xc5,0xd9,0xef,0xe4]
; CHECK-NEXT: vpxord %xmm4, %xmm4, %xmm4 ## encoding: [0x62,0xf1,0x5d,0x08,0xef,0xe4]
; CHECK-NEXT: vpermt2b %xmm2, %xmm0, %xmm4 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0x89,0x7d,0xe2]
; CHECK-NEXT: vpaddb %xmm4, %xmm3, %xmm0 ## encoding: [0x62,0xf1,0x65,0x08,0xfc,0xc4]
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0 ## encoding: [0x62,0xf1,0x7d,0x08,0xfc,0xc1]
@ -155,7 +155,7 @@ define <32 x i8>@test_int_x86_avx512_mask_vpermt2var_qi_256(<32 x i8> %x0, <32 x
; CHECK-NEXT: vmovaps %zmm1, %zmm3 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xd9]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm3 {%k1} ## encoding: [0x62,0xf2,0x7d,0x29,0x7d,0xda]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm1 ## encoding: [0x62,0xf2,0x7d,0x28,0x7d,0xca]
; CHECK-NEXT: vpxor %ymm4, %ymm4, %ymm4 ## encoding: [0xc5,0xdd,0xef,0xe4]
; CHECK-NEXT: vpxord %ymm4, %ymm4, %ymm4 ## encoding: [0x62,0xf1,0x5d,0x28,0xef,0xe4]
; CHECK-NEXT: vpermt2b %ymm2, %ymm0, %ymm4 {%k1} {z} ## encoding: [0x62,0xf2,0x7d,0xa9,0x7d,0xe2]
; CHECK-NEXT: vpaddb %ymm4, %ymm3, %ymm0 ## encoding: [0x62,0xf1,0x65,0x28,0xfc,0xc4]
; CHECK-NEXT: vpaddb %ymm1, %ymm0, %ymm0 ## encoding: [0x62,0xf1,0x7d,0x28,0xfc,0xc1]

16
llvm/test/CodeGen/X86/avx512vl-intrinsics.ll
View File

@ -7929,7 +7929,7 @@ define <2 x double>@test_int_x86_avx512_mask_fixupimm_pd_128(<2 x double> %x0, <
; CHECK: kmovw %edi, %k1
; CHECK: vmovaps %zmm0, %zmm3
; CHECK: vfixupimmpd $5, %xmm2, %xmm1, %xmm3 {%k1}
; CHECK: vpxor %xmm4, %xmm4, %xmm4
; CHECK: vpxord %xmm4, %xmm4, %xmm4
; CHECK: vfixupimmpd $4, %xmm2, %xmm1, %xmm4 {%k1} {z}
; CHECK: vfixupimmpd $3, %xmm2, %xmm1, %xmm0
; CHECK: vaddpd %xmm4, %xmm3, %xmm1
@ -7950,7 +7950,7 @@ define <2 x double>@test_int_x86_avx512_maskz_fixupimm_pd_128(<2 x double> %x0,
; CHECK: kmovw %edi, %k1
; CHECK: vmovaps %zmm0, %zmm3
; CHECK: vfixupimmpd $5, %xmm2, %xmm1, %xmm3 {%k1} {z}
; CHECK: vpxor %xmm2, %xmm2, %xmm2
; CHECK: vpxord %xmm2, %xmm2, %xmm2
; CHECK: vfixupimmpd $3, %xmm2, %xmm1, %xmm0 {%k1} {z}
; CHECK: vaddpd %xmm0, %xmm3, %xmm0
%res = call <2 x double> @llvm.x86.avx512.maskz.fixupimm.pd.128(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i32 5, i8 %x4)
@ -7968,7 +7968,7 @@ define <4 x double>@test_int_x86_avx512_mask_fixupimm_pd_256(<4 x double> %x0, <
; CHECK: kmovw %edi, %k1
; CHECK: vmovaps %zmm0, %zmm3
; CHECK: vfixupimmpd $4, %ymm2, %ymm1, %ymm3 {%k1}
; CHECK: vpxor %ymm4, %ymm4, %ymm4
; CHECK: vpxord %ymm4, %ymm4, %ymm4
; CHECK: vfixupimmpd $5, %ymm2, %ymm1, %ymm4 {%k1} {z}
; CHECK: vfixupimmpd $3, %ymm2, %ymm1, %ymm0
; CHECK: vaddpd %ymm4, %ymm3, %ymm1
@ -7989,7 +7989,7 @@ define <4 x double>@test_int_x86_avx512_maskz_fixupimm_pd_256(<4 x double> %x0,
; CHECK: kmovw %edi, %k1
; CHECK: vmovaps %zmm0, %zmm3
; CHECK: vfixupimmpd $5, %ymm2, %ymm1, %ymm3 {%k1} {z}
; CHECK: vpxor %ymm4, %ymm4, %ymm4
; CHECK: vpxord %ymm4, %ymm4, %ymm4
; CHECK: vmovaps %zmm0, %zmm5
; CHECK: vfixupimmpd $4, %ymm4, %ymm1, %ymm5 {%k1} {z}
; CHECK: vfixupimmpd $3, %ymm2, %ymm1, %ymm0
@ -8013,7 +8013,7 @@ define <4 x float>@test_int_x86_avx512_mask_fixupimm_ps_128(<4 x float> %x0, <4
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm3 {%k1}
; CHECK: vmovaps %zmm0, %zmm4
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm4
; CHECK: vpxor %xmm2, %xmm2, %xmm2
; CHECK: vpxord %xmm2, %xmm2, %xmm2
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm0 {%k1}
; CHECK: vaddps %xmm0, %xmm3, %xmm0
; CHECK: vaddps %xmm4, %xmm0, %xmm0
@ -8035,7 +8035,7 @@ define <4 x float>@test_int_x86_avx512_maskz_fixupimm_ps_128(<4 x float> %x0, <4
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm3 {%k1} {z}
; CHECK: vmovaps %zmm0, %zmm4
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm4
; CHECK: vpxor %xmm2, %xmm2, %xmm2
; CHECK: vpxord %xmm2, %xmm2, %xmm2
; CHECK: vfixupimmps $5, %xmm2, %xmm1, %xmm0 {%k1} {z}
; CHECK: vaddps %xmm0, %xmm3, %xmm0
; CHECK: vaddps %xmm4, %xmm0, %xmm0
@ -8057,7 +8057,7 @@ define <8 x float>@test_int_x86_avx512_mask_fixupimm_ps_256(<8 x float> %x0, <8
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm3 {%k1}
; CHECK: vmovaps %zmm0, %zmm4
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm4
; CHECK: vpxor %ymm2, %ymm2, %ymm2
; CHECK: vpxord %ymm2, %ymm2, %ymm2
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm0 {%k1}
; CHECK: vaddps %ymm0, %ymm3, %ymm0
; CHECK: vaddps %ymm4, %ymm0, %ymm0
@ -8079,7 +8079,7 @@ define <8 x float>@test_int_x86_avx512_maskz_fixupimm_ps_256(<8 x float> %x0, <8
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm3 {%k1} {z}
; CHECK: vmovaps %zmm0, %zmm4
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm4
; CHECK: vpxor %ymm2, %ymm2, %ymm2
; CHECK: vpxord %ymm2, %ymm2, %ymm2
; CHECK: vfixupimmps $5, %ymm2, %ymm1, %ymm0 {%k1} {z}
; CHECK: vaddps %ymm0, %ymm3, %ymm0
; CHECK: vaddps %ymm4, %ymm0, %ymm0

12
llvm/test/CodeGen/X86/avx512vl-vbroadcast.ll
View File

@ -73,7 +73,7 @@ define <8 x float> @_inreg8xfloat(float %a) {
define <8 x float> @_ss8xfloat_mask(<8 x float> %i, float %a, <8 x i32> %mask1) {
; CHECK-LABEL: _ss8xfloat_mask:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %ymm3, %ymm3, %ymm3
; CHECK-NEXT: vpxord %ymm3, %ymm3, %ymm3
; CHECK-NEXT: vpcmpneqd %ymm3, %ymm2, %k1
; CHECK-NEXT: vbroadcastss %xmm1, %ymm0 {%k1}
; CHECK-NEXT: retq
@ -87,7 +87,7 @@ define <8 x float> @_ss8xfloat_mask(<8 x float> %i, float %a, <8 x i32> %mask1
define <8 x float> @_ss8xfloat_maskz(float %a, <8 x i32> %mask1) {
; CHECK-LABEL: _ss8xfloat_maskz:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %ymm2, %ymm2, %ymm2
; CHECK-NEXT: vpxord %ymm2, %ymm2, %ymm2
; CHECK-NEXT: vpcmpneqd %ymm2, %ymm1, %k1
; CHECK-NEXT: vbroadcastss %xmm0, %ymm0 {%k1} {z}
; CHECK-NEXT: retq
@ -111,7 +111,7 @@ define <4 x float> @_inreg4xfloat(float %a) {
define <4 x float> @_ss4xfloat_mask(<4 x float> %i, float %a, <4 x i32> %mask1) {
; CHECK-LABEL: _ss4xfloat_mask:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vpxord %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vpcmpneqd %xmm3, %xmm2, %k1
; CHECK-NEXT: vbroadcastss %xmm1, %xmm0 {%k1}
; CHECK-NEXT: retq
@ -125,7 +125,7 @@ define <4 x float> @_ss4xfloat_mask(<4 x float> %i, float %a, <4 x i32> %mask1
define <4 x float> @_ss4xfloat_maskz(float %a, <4 x i32> %mask1) {
; CHECK-LABEL: _ss4xfloat_maskz:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vpxord %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vpcmpneqd %xmm2, %xmm1, %k1
; CHECK-NEXT: vbroadcastss %xmm0, %xmm0 {%k1} {z}
; CHECK-NEXT: retq
@ -149,7 +149,7 @@ define <4 x double> @_inreg4xdouble(double %a) {
define <4 x double> @_ss4xdouble_mask(<4 x double> %i, double %a, <4 x i32> %mask1) {
; CHECK-LABEL: _ss4xdouble_mask:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vpxord %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vpcmpneqd %xmm3, %xmm2, %k1
; CHECK-NEXT: vbroadcastsd %xmm1, %ymm0 {%k1}
; CHECK-NEXT: retq
@ -163,7 +163,7 @@ define <4 x double> @_ss4xdouble_mask(<4 x double> %i, double %a, <4 x i32> %m
define <4 x double> @_ss4xdouble_maskz(double %a, <4 x i32> %mask1) {
; CHECK-LABEL: _ss4xdouble_maskz:
; CHECK: # BB#0:
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vpxord %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vpcmpneqd %xmm2, %xmm1, %k1
; CHECK-NEXT: vbroadcastsd %xmm0, %ymm0 {%k1} {z}
; CHECK-NEXT: retq

5
llvm/test/CodeGen/X86/fma_patterns.ll
View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma4,+fma -fp-contract=fast | FileCheck %s --check-prefix=ALL --check-prefix=FMA4
@ -1150,7 +1151,7 @@ define <4 x float> @test_v4f32_fneg_fmul(<4 x float> %x, <4 x float> %y) #0 {
;
; AVX512-LABEL: test_v4f32_fneg_fmul:
; AVX512: # BB#0:
; AVX512-NEXT: vxorps %xmm2, %xmm2, %xmm2
; AVX512-NEXT: vpxord %xmm2, %xmm2, %xmm2
; AVX512-NEXT: vfnmsub213ps %xmm2, %xmm1, %xmm0
; AVX512-NEXT: retq
%m = fmul nsz <4 x float> %x, %y
@ -1173,7 +1174,7 @@ define <4 x double> @test_v4f64_fneg_fmul(<4 x double> %x, <4 x double> %y) #0 {
;
; AVX512-LABEL: test_v4f64_fneg_fmul:
; AVX512: # BB#0:
; AVX512-NEXT: vxorps %ymm2, %ymm2, %ymm2
; AVX512-NEXT: vpxord %ymm2, %ymm2, %ymm2
; AVX512-NEXT: vfnmsub213pd %ymm2, %ymm1, %ymm0
; AVX512-NEXT: retq
%m = fmul nsz <4 x double> %x, %y

40
llvm/test/CodeGen/X86/masked_memop.ll
View File

@ -1,4 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx < %s | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx2 < %s | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx512f < %s | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
@ -204,7 +204,7 @@ define <8 x double> @test5(<8 x i32> %trigger, <8 x double>* %addr, <8 x double>
;
; SKX-LABEL: test5:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpxord %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpcmpeqd %ymm2, %ymm0, %k1
; SKX-NEXT: vmovupd (%rdi), %zmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -233,7 +233,7 @@ define <2 x double> @test6(<2 x i64> %trigger, <2 x double>* %addr, <2 x double>
;
; SKX-LABEL: test6:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT: vmovupd (%rdi), %xmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -262,7 +262,7 @@ define <4 x float> @test7(<4 x i32> %trigger, <4 x float>* %addr, <4 x float> %d
;
; SKX-LABEL: test7:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT: vmovups (%rdi), %xmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -299,7 +299,7 @@ define <4 x i32> @test8(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
;
; SKX-LABEL: test8:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT: vmovdqu32 (%rdi), %xmm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -333,7 +333,7 @@ define void @test9(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
;
; SKX-LABEL: test9:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT: vmovdqu32 %xmm1, (%rdi) {%k1}
; SKX-NEXT: retq
@ -375,7 +375,7 @@ define <4 x double> @test10(<4 x i32> %trigger, <4 x double>* %addr, <4 x double
;
; SKX-LABEL: test10:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT: vmovapd (%rdi), %ymm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -415,7 +415,7 @@ define <4 x double> @test10b(<4 x i32> %trigger, <4 x double>* %addr, <4 x doubl
;
; SKX-LABEL: test10b:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpxord %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpcmpeqd %xmm1, %xmm0, %k1
; SKX-NEXT: vmovapd (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT: retq
@ -456,7 +456,7 @@ define <8 x float> @test11a(<8 x i32> %trigger, <8 x float>* %addr, <8 x float>
;
; SKX-LABEL: test11a:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpxord %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpcmpeqd %ymm2, %ymm0, %k1
; SKX-NEXT: vmovaps (%rdi), %ymm1 {%k1}
; SKX-NEXT: vmovaps %zmm1, %zmm0
@ -624,7 +624,7 @@ define void @test12(<8 x i32> %trigger, <8 x i32>* %addr, <8 x i32> %val) {
;
; SKX-LABEL: test12:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpxord %ymm2, %ymm2, %ymm2
; SKX-NEXT: vpcmpeqd %ymm2, %ymm0, %k1
; SKX-NEXT: vmovdqu32 %ymm1, (%rdi) {%k1}
; SKX-NEXT: retq
@ -704,7 +704,7 @@ define void @test14(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
;
; SKX-LABEL: test14:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT: vpcmpeqq %xmm2, %xmm0, %k0
; SKX-NEXT: kshiftlw $14, %k0, %k0
@ -752,7 +752,7 @@ define void @test15(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
;
; SKX-LABEL: test15:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT: vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT: vpmovqd %xmm1, (%rdi) {%k1}
@ -798,7 +798,7 @@ define <2 x float> @test16(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %
;
; SKX-LABEL: test16:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT: vpcmpeqq %xmm2, %xmm0, %k0
; SKX-NEXT: kshiftlw $14, %k0, %k0
@ -853,7 +853,7 @@ define <2 x i32> @test17(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
;
; SKX-LABEL: test17:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpxord %xmm2, %xmm2, %xmm2
; SKX-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT: vpcmpeqq %xmm2, %xmm0, %k0
; SKX-NEXT: kshiftlw $14, %k0, %k0
@ -900,7 +900,7 @@ define <2 x float> @test18(<2 x i32> %trigger, <2 x float>* %addr) {
;
; SKX-LABEL: test18:
; SKX: ## BB#0:
; SKX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpxord %xmm1, %xmm1, %xmm1
; SKX-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; SKX-NEXT: vpcmpeqq %xmm1, %xmm0, %k0
; SKX-NEXT: kshiftlw $14, %k0, %k0
@ -1317,12 +1317,12 @@ define <4 x i32> @load_one_mask_bit_set1(<4 x i32>* %addr, <4 x i32> %val) {
define <4 x float> @load_one_mask_bit_set2(<4 x float>* %addr, <4 x float> %val) {
; AVX-LABEL: load_one_mask_bit_set2:
; AVX: ## BB#0:
; AVX-NEXT: vinsertps $32, 8(%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT: retq
;
; AVX512-LABEL: load_one_mask_bit_set2:
; AVX512: ## BB#0:
; AVX512-NEXT: vinsertps $32, 8(%rdi), %xmm0, %xmm0 ## xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX512-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX512-NEXT: retq
%res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x float> %val)
ret <4 x float> %res
@ -1368,21 +1368,21 @@ define <4 x double> @load_one_mask_bit_set4(<4 x double>* %addr, <4 x double> %v
; AVX-LABEL: load_one_mask_bit_set4:
; AVX: ## BB#0:
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX-NEXT: vmovhpd 24(%rdi), %xmm1, %xmm1 ## xmm1 = xmm1[0],mem[0]
; AVX-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX-NEXT: retq
;
; AVX512F-LABEL: load_one_mask_bit_set4:
; AVX512F: ## BB#0:
; AVX512F-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovhpd 24(%rdi), %xmm1, %xmm1 ## xmm1 = xmm1[0],mem[0]
; AVX512F-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; AVX512F-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; SKX-LABEL: load_one_mask_bit_set4:
; SKX: ## BB#0:
; SKX-NEXT: vextractf128 $1, %ymm0, %xmm1
; SKX-NEXT: vmovhpd 24(%rdi), %xmm1, %xmm1 ## xmm1 = xmm1[0],mem[0]
; SKX-NEXT: vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; SKX-NEXT: vinsertf32x4 $1, %xmm1, %ymm0, %ymm0
; SKX-NEXT: retq
%res = call <4 x double> @llvm.masked.load.v4f64(<4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>, <4 x double> %val)

33
llvm/test/CodeGen/X86/vector-shuffle-128-v2.ll
View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by update_llc_test_checks.py
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3
@ -762,7 +763,7 @@ define <2 x i64> @shuffle_v2i64_z1(<2 x i64> %a) {
;
; AVX512VL-LABEL: shuffle_v2i64_z1:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512VL-NEXT: retq
%shuffle = shufflevector <2 x i64> %a, <2 x i64> zeroinitializer, <2 x i32> <i32 2, i32 1>
@ -804,7 +805,7 @@ define <2 x double> @shuffle_v2f64_1z(<2 x double> %a) {
;
; AVX512VL-LABEL: shuffle_v2f64_1z:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
; AVX512VL-NEXT: retq
%shuffle = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <2 x i32> <i32 1, i32 3>
@ -833,7 +834,7 @@ define <2 x double> @shuffle_v2f64_z0(<2 x double> %a) {
;
; AVX512VL-LABEL: shuffle_v2f64_z0:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512VL-NEXT: retq
%shuffle = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <2 x i32> <i32 2, i32 0>
@ -865,11 +866,23 @@ define <2 x double> @shuffle_v2f64_z1(<2 x double> %a) {
; SSE41-NEXT: blendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE41-NEXT: retq
;
; AVX-LABEL: shuffle_v2f64_z1:
; AVX: # BB#0:
; AVX-NEXT: vxorpd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vblendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; AVX-NEXT: retq
; AVX1-LABEL: shuffle_v2f64_z1:
; AVX1: # BB#0:
; AVX1-NEXT: vxorpd %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vblendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v2f64_z1:
; AVX2: # BB#0:
; AVX2-NEXT: vxorpd %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vblendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; AVX2-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v2f64_z1:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vblendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; AVX512VL-NEXT: retq
%shuffle = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <2 x i32> <i32 2, i32 1>
ret <2 x double> %shuffle
}
@ -895,7 +908,7 @@ define <2 x double> @shuffle_v2f64_bitcast_1z(<2 x double> %a) {
;
; AVX512VL-LABEL: shuffle_v2f64_bitcast_1z:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vshufpd {{.*#+}} xmm0 = xmm0[1],xmm1[0]
; AVX512VL-NEXT: retq
%shuffle64 = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <2 x i32> <i32 2, i32 1>
@ -947,7 +960,7 @@ define <2 x i64> @shuffle_v2i64_bitcast_z123(<2 x i64> %x) {
;
; AVX512VL-LABEL: shuffle_v2i64_bitcast_z123:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
; AVX512VL-NEXT: retq
%bitcast32 = bitcast <2 x i64> %x to <4 x float>

14
llvm/test/CodeGen/X86/vector-tzcnt-128.ll
View File

@ -192,7 +192,7 @@ define <2 x i64> @testv2i64u(<2 x i64> %in) nounwind {
;
; AVX512CDVL-LABEL: testv2i64u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubq %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandq %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vplzcntq %xmm0, %xmm0
@ -388,7 +388,7 @@ define <4 x i32> @testv4i32(<4 x i32> %in) nounwind {
;
; AVX512CDVL-LABEL: testv4i32:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubd %xmm0, %xmm1, %xmm2
; AVX512CDVL-NEXT: vpandd %xmm2, %xmm0, %xmm0
; AVX512CDVL-NEXT: vpsubd {{.*}}(%rip){1to4}, %xmm0, %xmm0
@ -611,7 +611,7 @@ define <4 x i32> @testv4i32u(<4 x i32> %in) nounwind {
;
; AVX512CDVL-LABEL: testv4i32u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubd %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandd %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vplzcntd %xmm0, %xmm0
@ -794,7 +794,7 @@ define <8 x i16> @testv8i16(<8 x i16> %in) nounwind {
;
; AVX512CDVL-LABEL: testv8i16:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubw %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandq %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vpsubw {{.*}}(%rip), %xmm0, %xmm0
@ -992,7 +992,7 @@ define <8 x i16> @testv8i16u(<8 x i16> %in) nounwind {
;
; AVX512CDVL-LABEL: testv8i16u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubw %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandq %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vpsubw {{.*}}(%rip), %xmm0, %xmm0
@ -1168,7 +1168,7 @@ define <16 x i8> @testv16i8(<16 x i8> %in) nounwind {
;
; AVX512CDVL-LABEL: testv16i8:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubb %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandq %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0
@ -1334,7 +1334,7 @@ define <16 x i8> @testv16i8u(<16 x i8> %in) nounwind {
;
; AVX512CDVL-LABEL: testv16i8u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpxord %xmm1, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpsubb %xmm0, %xmm1, %xmm1
; AVX512CDVL-NEXT: vpandq %xmm1, %xmm0, %xmm0
; AVX512CDVL-NEXT: vpsubb {{.*}}(%rip), %xmm0, %xmm0

16
llvm/test/CodeGen/X86/vector-tzcnt-256.ll
View File

@ -56,7 +56,7 @@ define <4 x i64> @testv4i64(<4 x i64> %in) nounwind {
;
; AVX512CDVL-LABEL: testv4i64:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubq %ymm0, %ymm1, %ymm2
; AVX512CDVL-NEXT: vpandq %ymm2, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubq {{.*}}(%rip){1to4}, %ymm0, %ymm0
@ -144,7 +144,7 @@ define <4 x i64> @testv4i64u(<4 x i64> %in) nounwind {
;
; AVX512CDVL-LABEL: testv4i64u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubq %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandq %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vplzcntq %ymm0, %ymm0
@ -229,7 +229,7 @@ define <8 x i32> @testv8i32(<8 x i32> %in) nounwind {
;
; AVX512CDVL-LABEL: testv8i32:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubd %ymm0, %ymm1, %ymm2
; AVX512CDVL-NEXT: vpandd %ymm2, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubd {{.*}}(%rip){1to8}, %ymm0, %ymm0
@ -337,7 +337,7 @@ define <8 x i32> @testv8i32u(<8 x i32> %in) nounwind {
;
; AVX512CDVL-LABEL: testv8i32u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubd %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandd %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vplzcntd %ymm0, %ymm0
@ -415,7 +415,7 @@ define <16 x i16> @testv16i16(<16 x i16> %in) nounwind {
;
; AVX512CDVL-LABEL: testv16i16:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubw %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandq %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubw {{.*}}(%rip), %ymm0, %ymm0
@ -511,7 +511,7 @@ define <16 x i16> @testv16i16u(<16 x i16> %in) nounwind {
;
; AVX512CDVL-LABEL: testv16i16u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubw %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandq %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubw {{.*}}(%rip), %ymm0, %ymm0
@ -598,7 +598,7 @@ define <32 x i8> @testv32i8(<32 x i8> %in) nounwind {
;
; AVX512CDVL-LABEL: testv32i8:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubb %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandq %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubb {{.*}}(%rip), %ymm0, %ymm0
@ -679,7 +679,7 @@ define <32 x i8> @testv32i8u(<32 x i8> %in) nounwind {
;
; AVX512CDVL-LABEL: testv32i8u:
; AVX512CDVL: # BB#0:
; AVX512CDVL-NEXT: vpxor %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpxord %ymm1, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpsubb %ymm0, %ymm1, %ymm1
; AVX512CDVL-NEXT: vpandq %ymm1, %ymm0, %ymm0
; AVX512CDVL-NEXT: vpsubb {{.*}}(%rip), %ymm0, %ymm0