forked from OSchip/llvm-project
6442 lines
292 KiB
LLVM
6442 lines
292 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
|
|
|
|
declare i32 @llvm.x86.avx512.kortestz.w(i16, i16) nounwind readnone
|
|
define i32 @test_kortestz(i16 %a0, i16 %a1) {
|
|
; CHECK-LABEL: test_kortestz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k0
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: kortestw %k0, %k1
|
|
; CHECK-NEXT: sete %al
|
|
; CHECK-NEXT: kmovw %eax, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: andl $1, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.kortestz.w(i16 %a0, i16 %a1)
|
|
ret i32 %res
|
|
}
|
|
|
|
declare i32 @llvm.x86.avx512.kortestc.w(i16, i16) nounwind readnone
|
|
define i32 @test_kortestc(i16 %a0, i16 %a1) {
|
|
; CHECK-LABEL: test_kortestc:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k0
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: kortestw %k0, %k1
|
|
; CHECK-NEXT: sbbl %eax, %eax
|
|
; CHECK-NEXT: andl $1, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.kortestc.w(i16 %a0, i16 %a1)
|
|
ret i32 %res
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.kand.w(i16, i16) nounwind readnone
|
|
define i16 @test_kand(i16 %a0, i16 %a1) {
|
|
; CHECK-LABEL: test_kand:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: movw $8, %ax
|
|
; CHECK-NEXT: kmovw %eax, %k0
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: kandw %k0, %k1, %k0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: kandw %k1, %k0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%t1 = call i16 @llvm.x86.avx512.kand.w(i16 %a0, i16 8)
|
|
%t2 = call i16 @llvm.x86.avx512.kand.w(i16 %t1, i16 %a1)
|
|
ret i16 %t2
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.knot.w(i16) nounwind readnone
|
|
define i16 @test_knot(i16 %a0) {
|
|
; CHECK-LABEL: test_knot:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k0
|
|
; CHECK-NEXT: knotw %k0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i16 @llvm.x86.avx512.knot.w(i16 %a0)
|
|
ret i16 %res
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.kunpck.bw(i16, i16) nounwind readnone
|
|
|
|
define i16 @unpckbw_test(i16 %a0, i16 %a1) {
|
|
; CHECK-LABEL: unpckbw_test:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: kunpckbw %k1, %k0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i16 @llvm.x86.avx512.kunpck.bw(i16 %a0, i16 %a1)
|
|
ret i16 %res
|
|
}
|
|
|
|
define <16 x float> @test_rcp_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_rcp_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vrcp14ps %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.rcp14.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1) ; <<16 x float>> [#uses=1]
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.rcp14.ps.512(<16 x float>, <16 x float>, i16) nounwind readnone
|
|
|
|
define <8 x double> @test_rcp_pd_512(<8 x double> %a0) {
|
|
; CHECK-LABEL: test_rcp_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vrcp14pd %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.rcp14.pd.512(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1) ; <<8 x double>> [#uses=1]
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.rcp14.pd.512(<8 x double>, <8 x double>, i8) nounwind readnone
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double>, i32, <8 x double>, i8, i32)
|
|
|
|
define <8 x double> @test7(<8 x double> %a) {
|
|
; CHECK-LABEL: test7:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vrndscalepd $11, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %a, i32 11, <8 x double> %a, i8 -1, i32 4)
|
|
ret <8 x double>%res
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float>, i32, <16 x float>, i16, i32)
|
|
|
|
define <16 x float> @test8(<16 x float> %a) {
|
|
; CHECK-LABEL: test8:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vrndscaleps $11, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %a, i32 11, <16 x float> %a, i16 -1, i32 4)
|
|
ret <16 x float>%res
|
|
}
|
|
|
|
define <16 x float> @test_rsqrt_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_rsqrt_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vrsqrt14ps %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.rsqrt14.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1) ; <<16 x float>> [#uses=1]
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.rsqrt14.ps.512(<16 x float>, <16 x float>, i16) nounwind readnone
|
|
|
|
define <8 x double> @test_sqrt_pd_512(<8 x double> %a0) {
|
|
; CHECK-LABEL: test_sqrt_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsqrtpd %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.sqrt.pd.512(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1, i32 4)
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.mask.sqrt.pd.512(<8 x double>, <8 x double>, i8, i32) nounwind readnone
|
|
|
|
define <16 x float> @test_sqrt_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_sqrt_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsqrtps %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sqrt.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_sqrt_round_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_sqrt_round_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsqrtps {rz-sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sqrt.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.sqrt.ps.512(<16 x float>, <16 x float>, i16, i32) nounwind readnone
|
|
|
|
define <8 x double> @test_getexp_pd_512(<8 x double> %a0) {
|
|
; CHECK-LABEL: test_getexp_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vgetexppd %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.getexp.pd.512(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1, i32 4)
|
|
ret <8 x double> %res
|
|
}
|
|
define <8 x double> @test_getexp_round_pd_512(<8 x double> %a0) {
|
|
; CHECK-LABEL: test_getexp_round_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vgetexppd {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.getexp.pd.512(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1, i32 8)
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.mask.getexp.pd.512(<8 x double>, <8 x double>, i8, i32) nounwind readnone
|
|
|
|
define <16 x float> @test_getexp_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_getexp_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vgetexpps %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.getexp.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_getexp_round_ps_512(<16 x float> %a0) {
|
|
; CHECK-LABEL: test_getexp_round_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vgetexpps {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.getexp.ps.512(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.getexp.ps.512(<16 x float>, <16 x float>, i16, i32) nounwind readnone
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_sqrt_ss(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_sqrt_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vsqrtss %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vsqrtss {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vsqrtss {ru-sae}, %xmm1, %xmm0, %xmm4 {%k1} {z}
|
|
; CHECK-NEXT: vsqrtss {rz-sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm2, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 1)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 2)
|
|
%res3 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 3)
|
|
|
|
%res.1 = fadd <4 x float> %res0, %res1
|
|
%res.2 = fadd <4 x float> %res2, %res3
|
|
%res = fadd <4 x float> %res.1, %res.2
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_sqrt_sd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_sqrt_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vsqrtsd %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vsqrtsd {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vsqrtsd {ru-sae}, %xmm1, %xmm0, %xmm4 {%k1} {z}
|
|
; CHECK-NEXT: vsqrtsd {rz-sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm2, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 1)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 2)
|
|
%res3 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 3)
|
|
|
|
%res.1 = fadd <2 x double> %res0, %res1
|
|
%res.2 = fadd <2 x double> %res2, %res3
|
|
%res = fadd <2 x double> %res.1, %res.2
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define i64 @test_x86_sse2_cvtsd2si64(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_sse2_cvtsd2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsd2si %xmm0, %rax
|
|
; CHECK-NEXT: retq
|
|
%res = call i64 @llvm.x86.sse2.cvtsd2si64(<2 x double> %a0) ; <i64> [#uses=1]
|
|
ret i64 %res
|
|
}
|
|
declare i64 @llvm.x86.sse2.cvtsd2si64(<2 x double>) nounwind readnone
|
|
|
|
define <2 x double> @test_x86_sse2_cvtsi642sd(<2 x double> %a0, i64 %a1) {
|
|
; CHECK-LABEL: test_x86_sse2_cvtsi642sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2sdq %rdi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.sse2.cvtsi642sd(<2 x double> %a0, i64 %a1) ; <<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.sse2.cvtsi642sd(<2 x double>, i64) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvttsd2si64(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttsd2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttsd2si %xmm0, %rcx
|
|
; CHECK-NEXT: vcvttsd2si {sae}, %xmm0, %rax
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i64 @llvm.x86.avx512.cvttsd2si64(<2 x double> %a0, i32 4) ;
|
|
%res1 = call i64 @llvm.x86.avx512.cvttsd2si64(<2 x double> %a0, i32 8) ;
|
|
%res2 = add i64 %res0, %res1
|
|
ret i64 %res2
|
|
}
|
|
declare i64 @llvm.x86.avx512.cvttsd2si64(<2 x double>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvttsd2usi(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttsd2usi:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttsd2usi %xmm0, %ecx
|
|
; CHECK-NEXT: vcvttsd2usi {sae}, %xmm0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i32 @llvm.x86.avx512.cvttsd2usi(<2 x double> %a0, i32 4) ;
|
|
%res1 = call i32 @llvm.x86.avx512.cvttsd2usi(<2 x double> %a0, i32 8) ;
|
|
%res2 = add i32 %res0, %res1
|
|
ret i32 %res2
|
|
}
|
|
declare i32 @llvm.x86.avx512.cvttsd2usi(<2 x double>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvttsd2si(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttsd2si:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttsd2si %xmm0, %ecx
|
|
; CHECK-NEXT: vcvttsd2si {sae}, %xmm0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i32 @llvm.x86.avx512.cvttsd2si(<2 x double> %a0, i32 4) ;
|
|
%res1 = call i32 @llvm.x86.avx512.cvttsd2si(<2 x double> %a0, i32 8) ;
|
|
%res2 = add i32 %res0, %res1
|
|
ret i32 %res2
|
|
}
|
|
declare i32 @llvm.x86.avx512.cvttsd2si(<2 x double>, i32) nounwind readnone
|
|
|
|
|
|
|
|
define i64 @test_x86_avx512_cvttsd2usi64(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttsd2usi64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttsd2usi %xmm0, %rcx
|
|
; CHECK-NEXT: vcvttsd2usi {sae}, %xmm0, %rax
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double> %a0, i32 4) ;
|
|
%res1 = call i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double> %a0, i32 8) ;
|
|
%res2 = add i64 %res0, %res1
|
|
ret i64 %res2
|
|
}
|
|
declare i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_sse_cvtss2si64(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_sse_cvtss2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtss2si %xmm0, %rax
|
|
; CHECK-NEXT: retq
|
|
%res = call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %a0) ; <i64> [#uses=1]
|
|
ret i64 %res
|
|
}
|
|
declare i64 @llvm.x86.sse.cvtss2si64(<4 x float>) nounwind readnone
|
|
|
|
|
|
define <4 x float> @test_x86_sse_cvtsi642ss(<4 x float> %a0, i64 %a1) {
|
|
; CHECK-LABEL: test_x86_sse_cvtsi642ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2ssq %rdi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.sse.cvtsi642ss(<4 x float> %a0, i64 %a1) ; <<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.sse.cvtsi642ss(<4 x float>, i64) nounwind readnone
|
|
|
|
|
|
define i32 @test_x86_avx512_cvttss2si(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttss2si:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttss2si {sae}, %xmm0, %ecx
|
|
; CHECK-NEXT: vcvttss2si %xmm0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i32 @llvm.x86.avx512.cvttss2si(<4 x float> %a0, i32 8) ;
|
|
%res1 = call i32 @llvm.x86.avx512.cvttss2si(<4 x float> %a0, i32 4) ;
|
|
%res2 = add i32 %res0, %res1
|
|
ret i32 %res2
|
|
}
|
|
declare i32 @llvm.x86.avx512.cvttss2si(<4 x float>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvttss2si64(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttss2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttss2si %xmm0, %rcx
|
|
; CHECK-NEXT: vcvttss2si {sae}, %xmm0, %rax
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i64 @llvm.x86.avx512.cvttss2si64(<4 x float> %a0, i32 4) ;
|
|
%res1 = call i64 @llvm.x86.avx512.cvttss2si64(<4 x float> %a0, i32 8) ;
|
|
%res2 = add i64 %res0, %res1
|
|
ret i64 %res2
|
|
}
|
|
declare i64 @llvm.x86.avx512.cvttss2si64(<4 x float>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvttss2usi(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttss2usi:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttss2usi {sae}, %xmm0, %ecx
|
|
; CHECK-NEXT: vcvttss2usi %xmm0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i32 @llvm.x86.avx512.cvttss2usi(<4 x float> %a0, i32 8) ;
|
|
%res1 = call i32 @llvm.x86.avx512.cvttss2usi(<4 x float> %a0, i32 4) ;
|
|
%res2 = add i32 %res0, %res1
|
|
ret i32 %res2
|
|
}
|
|
declare i32 @llvm.x86.avx512.cvttss2usi(<4 x float>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvttss2usi64(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvttss2usi64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvttss2usi %xmm0, %rcx
|
|
; CHECK-NEXT: vcvttss2usi {sae}, %xmm0, %rax
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i64 @llvm.x86.avx512.cvttss2usi64(<4 x float> %a0, i32 4) ;
|
|
%res1 = call i64 @llvm.x86.avx512.cvttss2usi64(<4 x float> %a0, i32 8) ;
|
|
%res2 = add i64 %res0, %res1
|
|
ret i64 %res2
|
|
}
|
|
declare i64 @llvm.x86.avx512.cvttss2usi64(<4 x float>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvtsd2usi64(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsd2usi64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsd2usi %xmm0, %rcx
|
|
; CHECK-NEXT: vcvtsd2usi {rz-sae}, %xmm0, %rax
|
|
; CHECK-NEXT: vcvtsd2usi {rd-sae}, %xmm0, %rdx
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: addq %rdx, %rax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 4)
|
|
%res1 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 3)
|
|
%res2 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 1)
|
|
%res3 = add i64 %res, %res1
|
|
%res4 = add i64 %res3, %res2
|
|
ret i64 %res4
|
|
}
|
|
declare i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvtsd2si64(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsd2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsd2si %xmm0, %rcx
|
|
; CHECK-NEXT: vcvtsd2si {rz-sae}, %xmm0, %rax
|
|
; CHECK-NEXT: vcvtsd2si {rd-sae}, %xmm0, %rdx
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: addq %rdx, %rax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 4)
|
|
%res1 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 3)
|
|
%res2 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 1)
|
|
%res3 = add i64 %res, %res1
|
|
%res4 = add i64 %res3, %res2
|
|
ret i64 %res4
|
|
}
|
|
declare i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvtss2usi64(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtss2usi64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtss2usi %xmm0, %rcx
|
|
; CHECK-NEXT: vcvtss2usi {rz-sae}, %xmm0, %rax
|
|
; CHECK-NEXT: vcvtss2usi {rd-sae}, %xmm0, %rdx
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: addq %rdx, %rax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 4)
|
|
%res1 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 3)
|
|
%res2 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 1)
|
|
%res3 = add i64 %res, %res1
|
|
%res4 = add i64 %res3, %res2
|
|
ret i64 %res4
|
|
}
|
|
declare i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float>, i32) nounwind readnone
|
|
|
|
define i64 @test_x86_avx512_cvtss2si64(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtss2si64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtss2si %xmm0, %rcx
|
|
; CHECK-NEXT: vcvtss2si {rz-sae}, %xmm0, %rax
|
|
; CHECK-NEXT: vcvtss2si {rd-sae}, %xmm0, %rdx
|
|
; CHECK-NEXT: addq %rcx, %rax
|
|
; CHECK-NEXT: addq %rdx, %rax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 4)
|
|
%res1 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 3)
|
|
%res2 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 1)
|
|
%res3 = add i64 %res, %res1
|
|
%res4 = add i64 %res3, %res2
|
|
ret i64 %res4
|
|
}
|
|
declare i64 @llvm.x86.avx512.vcvtss2si64(<4 x float>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvtsd2usi32(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsd2usi32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsd2usi %xmm0, %ecx
|
|
; CHECK-NEXT: vcvtsd2usi {rz-sae}, %xmm0, %eax
|
|
; CHECK-NEXT: vcvtsd2usi {rd-sae}, %xmm0, %edx
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: addl %edx, %eax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 4)
|
|
%res1 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 3)
|
|
%res2 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 1)
|
|
%res3 = add i32 %res, %res1
|
|
%res4 = add i32 %res3, %res2
|
|
ret i32 %res4
|
|
}
|
|
declare i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvtsd2si32(<2 x double> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsd2si32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsd2si %xmm0, %ecx
|
|
; CHECK-NEXT: vcvtsd2si {rz-sae}, %xmm0, %eax
|
|
; CHECK-NEXT: vcvtsd2si {rd-sae}, %xmm0, %edx
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: addl %edx, %eax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 4)
|
|
%res1 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 3)
|
|
%res2 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 1)
|
|
%res3 = add i32 %res, %res1
|
|
%res4 = add i32 %res3, %res2
|
|
ret i32 %res4
|
|
}
|
|
declare i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvtss2usi32(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtss2usi32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtss2usi %xmm0, %ecx
|
|
; CHECK-NEXT: vcvtss2usi {rz-sae}, %xmm0, %eax
|
|
; CHECK-NEXT: vcvtss2usi {rd-sae}, %xmm0, %edx
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: addl %edx, %eax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 4)
|
|
%res1 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 3)
|
|
%res2 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 1)
|
|
%res3 = add i32 %res, %res1
|
|
%res4 = add i32 %res3, %res2
|
|
ret i32 %res4
|
|
}
|
|
declare i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float>, i32) nounwind readnone
|
|
|
|
define i32 @test_x86_avx512_cvtss2si32(<4 x float> %a0) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtss2si32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtss2si %xmm0, %ecx
|
|
; CHECK-NEXT: vcvtss2si {rz-sae}, %xmm0, %eax
|
|
; CHECK-NEXT: vcvtss2si {rd-sae}, %xmm0, %edx
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: addl %edx, %eax
|
|
; CHECK-NEXT: retq
|
|
|
|
%res = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 4)
|
|
%res1 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 3)
|
|
%res2 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 1)
|
|
%res3 = add i32 %res, %res1
|
|
%res4 = add i32 %res3, %res2
|
|
ret i32 %res4
|
|
}
|
|
declare i32 @llvm.x86.avx512.vcvtss2si32(<4 x float>, i32) nounwind readnone
|
|
|
|
define <16 x float> @test_x86_vcvtph2ps_512(<16 x i16> %a0) {
|
|
; CHECK-LABEL: test_x86_vcvtph2ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtph2ps %ymm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_x86_vcvtph2ps_512_sae(<16 x i16> %a0) {
|
|
; CHECK-LABEL: test_x86_vcvtph2ps_512_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtph2ps {sae}, %ymm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> zeroinitializer, i16 -1, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_x86_vcvtph2ps_512_rrk(<16 x i16> %a0,<16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_vcvtph2ps_512_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtph2ps %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> %a1, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_x86_vcvtph2ps_512_sae_rrkz(<16 x i16> %a0, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_vcvtph2ps_512_sae_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtph2ps {sae}, %ymm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> zeroinitializer, i16 %mask, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_x86_vcvtph2ps_512_rrkz(<16 x i16> %a0, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_vcvtph2ps_512_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtph2ps %ymm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> zeroinitializer, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16>, <16 x float>, i16, i32) nounwind readonly
|
|
|
|
define <16 x i16> @test_x86_vcvtps2ph_256(<16 x float> %a0, <16 x i16> %src, i16 %mask, <16 x i16> * %dst) {
|
|
; CHECK-LABEL: test_x86_vcvtps2ph_256:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtps2ph $2, %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvtps2ph $2, %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vcvtps2ph $2, %zmm0, (%rsi)
|
|
; CHECK-NEXT: vpaddw %ymm1, %ymm2, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res1 = call <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float> %a0, i32 2, <16 x i16> zeroinitializer, i16 -1)
|
|
%res2 = call <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float> %a0, i32 2, <16 x i16> zeroinitializer, i16 %mask)
|
|
%res3 = call <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float> %a0, i32 2, <16 x i16> %src, i16 %mask)
|
|
store <16 x i16> %res1, <16 x i16> * %dst
|
|
%res = add <16 x i16> %res2, %res3
|
|
ret <16 x i16> %res
|
|
}
|
|
|
|
declare <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float>, i32, <16 x i16>, i16) nounwind readonly
|
|
|
|
define <16 x float> @test_x86_vbroadcast_ss_512(i8* %a0) {
|
|
; CHECK-LABEL: test_x86_vbroadcast_ss_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vbroadcastss (%rdi), %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.vbroadcast.ss.512(i8* %a0) ; <<16 x float>> [#uses=1]
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.vbroadcast.ss.512(i8*) nounwind readonly
|
|
|
|
define <8 x double> @test_x86_vbroadcast_sd_512(i8* %a0) {
|
|
; CHECK-LABEL: test_x86_vbroadcast_sd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vbroadcastsd (%rdi), %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.vbroadcast.sd.512(i8* %a0) ; <<8 x double>> [#uses=1]
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.vbroadcast.sd.512(i8*) nounwind readonly
|
|
|
|
define <16 x i32> @test_conflict_d(<16 x i32> %a) {
|
|
; CHECK-LABEL: test_conflict_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpconflictd %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.conflict.d.512(<16 x i32> %a, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.conflict.d.512(<16 x i32>, <16 x i32>, i16) nounwind readonly
|
|
|
|
define <8 x i64> @test_conflict_q(<8 x i64> %a) {
|
|
; CHECK-LABEL: test_conflict_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpconflictq %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.conflict.q.512(<8 x i64> %a, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.conflict.q.512(<8 x i64>, <8 x i64>, i8) nounwind readonly
|
|
|
|
define <16 x i32> @test_maskz_conflict_d(<16 x i32> %a, i16 %mask) {
|
|
; CHECK-LABEL: test_maskz_conflict_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpconflictd %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.conflict.d.512(<16 x i32> %a, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_conflict_q(<8 x i64> %a, <8 x i64> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_conflict_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpconflictq %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.conflict.q.512(<8 x i64> %a, <8 x i64> %b, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <16 x i32> @test_lzcnt_d(<16 x i32> %a) {
|
|
; CHECK-LABEL: test_lzcnt_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vplzcntd %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.lzcnt.d.512(<16 x i32> %a, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.lzcnt.d.512(<16 x i32>, <16 x i32>, i16) nounwind readonly
|
|
|
|
define <8 x i64> @test_lzcnt_q(<8 x i64> %a) {
|
|
; CHECK-LABEL: test_lzcnt_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vplzcntq %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.lzcnt.q.512(<8 x i64> %a, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.lzcnt.q.512(<8 x i64>, <8 x i64>, i8) nounwind readonly
|
|
|
|
|
|
define <16 x i32> @test_mask_lzcnt_d(<16 x i32> %a, <16 x i32> %b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_lzcnt_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vplzcntd %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.lzcnt.d.512(<16 x i32> %a, <16 x i32> %b, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_lzcnt_q(<8 x i64> %a, <8 x i64> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_lzcnt_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vplzcntq %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.lzcnt.q.512(<8 x i64> %a, <8 x i64> %b, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define i16 @test_cmpps(<16 x float> %a, <16 x float> %b) {
|
|
; CHECK-LABEL: test_cmpps:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpleps {sae}, %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i16 @llvm.x86.avx512.mask.cmp.ps.512(<16 x float> %a, <16 x float> %b, i32 2, i16 -1, i32 8)
|
|
ret i16 %res
|
|
}
|
|
declare i16 @llvm.x86.avx512.mask.cmp.ps.512(<16 x float> , <16 x float> , i32, i16, i32)
|
|
|
|
define i8 @test_cmppd(<8 x double> %a, <8 x double> %b) {
|
|
; CHECK-LABEL: test_cmppd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpneqpd %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i8 @llvm.x86.avx512.mask.cmp.pd.512(<8 x double> %a, <8 x double> %b, i32 4, i8 -1, i32 4)
|
|
ret i8 %res
|
|
}
|
|
declare i8 @llvm.x86.avx512.mask.cmp.pd.512(<8 x double> , <8 x double> , i32, i8, i32)
|
|
|
|
; fp min - max
|
|
define <8 x double> @test_vmaxpd(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: test_vmaxpd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.max.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double>zeroinitializer, i8 -1, i32 4)
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.mask.max.pd.512(<8 x double>, <8 x double>,
|
|
<8 x double>, i8, i32)
|
|
|
|
define <8 x double> @test_vminpd(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: test_vminpd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vminpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.min.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double>zeroinitializer, i8 -1, i32 4)
|
|
ret <8 x double> %res
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.mask.min.pd.512(<8 x double>, <8 x double>,
|
|
<8 x double>, i8, i32)
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pabs.d.512(<16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pabs_d_512(<16 x i32> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pabs_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpabsd %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpabsd %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pabs.d.512(<16 x i32> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pabs.d.512(<16 x i32> %x0, <16 x i32> %x1, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pabs.q.512(<8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pabs_q_512(<8 x i64> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pabs_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpabsq %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpabsq %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pabs.q.512(<8 x i64> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pabs.q.512(<8 x i64> %x0, <8 x i64> %x1, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
define i8 @test_vptestmq(<8 x i64> %a0, <8 x i64> %a1, i8 %m) {
|
|
; CHECK-LABEL: test_vptestmq:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vptestmq %zmm1, %zmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %ecx
|
|
; CHECK-NEXT: vptestmq %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: addb %cl, %al
|
|
; CHECK-NEXT: retq
|
|
%res = call i8 @llvm.x86.avx512.ptestm.q.512(<8 x i64> %a0, <8 x i64> %a1, i8 -1)
|
|
%res1 = call i8 @llvm.x86.avx512.ptestm.q.512(<8 x i64> %a0, <8 x i64> %a1, i8 %m)
|
|
%res2 = add i8 %res1, %res
|
|
ret i8 %res2
|
|
}
|
|
declare i8 @llvm.x86.avx512.ptestm.q.512(<8 x i64>, <8 x i64>, i8)
|
|
|
|
define i16 @test_vptestmd(<16 x i32> %a0, <16 x i32> %a1, i16 %m) {
|
|
; CHECK-LABEL: test_vptestmd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vptestmd %zmm1, %zmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %ecx
|
|
; CHECK-NEXT: vptestmd %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
%res = call i16 @llvm.x86.avx512.ptestm.d.512(<16 x i32> %a0, <16 x i32> %a1, i16 -1)
|
|
%res1 = call i16 @llvm.x86.avx512.ptestm.d.512(<16 x i32> %a0, <16 x i32> %a1, i16 %m)
|
|
%res2 = add i16 %res1, %res
|
|
ret i16 %res2
|
|
}
|
|
declare i16 @llvm.x86.avx512.ptestm.d.512(<16 x i32>, <16 x i32>, i16)
|
|
|
|
define <8 x i64> @test_valign_q(<8 x i64> %a, <8 x i64> %b) {
|
|
; CHECK-LABEL: test_valign_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: valignq $2, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.valign.q.512(<8 x i64> %a, <8 x i64> %b, i32 2, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_valign_q(<8 x i64> %a, <8 x i64> %b, <8 x i64> %src, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_valign_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: valignq $2, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.valign.q.512(<8 x i64> %a, <8 x i64> %b, i32 2, <8 x i64> %src, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.valign.q.512(<8 x i64>, <8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <16 x i32> @test_maskz_valign_d(<16 x i32> %a, <16 x i32> %b, i16 %mask) {
|
|
; CHECK-LABEL: test_maskz_valign_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: valignd $5, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.valign.d.512(<16 x i32> %a, <16 x i32> %b, i32 5, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.valign.d.512(<16 x i32>, <16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define void @test_mask_store_ss(i8* %ptr, <4 x float> %data, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_store_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovss %xmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.store.ss(i8* %ptr, <4 x float> %data, i8 %mask)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.store.ss(i8*, <4 x float>, i8 )
|
|
|
|
define <8 x i16> @test_cmp_d_512(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_cmp_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpcmpeqd %zmm1, %zmm0, %k3
|
|
; CHECK-NEXT: vpcmpltd %zmm1, %zmm0, %k4
|
|
; CHECK-NEXT: vpcmpled %zmm1, %zmm0, %k5
|
|
; CHECK-NEXT: vpcmpunordd %zmm1, %zmm0, %k6
|
|
; CHECK-NEXT: vpcmpneqd %zmm1, %zmm0, %k7
|
|
; CHECK-NEXT: vpcmpnltd %zmm1, %zmm0, %k2
|
|
; CHECK-NEXT: vpcmpnled %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpcmpordd %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: kmovw %k3, %ecx
|
|
; CHECK-NEXT: vmovd %ecx, %xmm0
|
|
; CHECK-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 0, i16 -1)
|
|
%vec0 = insertelement <8 x i16> undef, i16 %res0, i32 0
|
|
%res1 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 1, i16 -1)
|
|
%vec1 = insertelement <8 x i16> %vec0, i16 %res1, i32 1
|
|
%res2 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 2, i16 -1)
|
|
%vec2 = insertelement <8 x i16> %vec1, i16 %res2, i32 2
|
|
%res3 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 3, i16 -1)
|
|
%vec3 = insertelement <8 x i16> %vec2, i16 %res3, i32 3
|
|
%res4 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 4, i16 -1)
|
|
%vec4 = insertelement <8 x i16> %vec3, i16 %res4, i32 4
|
|
%res5 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 5, i16 -1)
|
|
%vec5 = insertelement <8 x i16> %vec4, i16 %res5, i32 5
|
|
%res6 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 6, i16 -1)
|
|
%vec6 = insertelement <8 x i16> %vec5, i16 %res6, i32 6
|
|
%res7 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 7, i16 -1)
|
|
%vec7 = insertelement <8 x i16> %vec6, i16 %res7, i32 7
|
|
ret <8 x i16> %vec7
|
|
}
|
|
|
|
define <8 x i16> @test_mask_cmp_d_512(<16 x i32> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_cmp_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k3
|
|
; CHECK-NEXT: vpcmpeqd %zmm1, %zmm0, %k4 {%k3}
|
|
; CHECK-NEXT: vpcmpltd %zmm1, %zmm0, %k5 {%k3}
|
|
; CHECK-NEXT: vpcmpled %zmm1, %zmm0, %k6 {%k3}
|
|
; CHECK-NEXT: vpcmpunordd %zmm1, %zmm0, %k7 {%k3}
|
|
; CHECK-NEXT: vpcmpneqd %zmm1, %zmm0, %k0 {%k3}
|
|
; CHECK-NEXT: vpcmpnltd %zmm1, %zmm0, %k2 {%k3}
|
|
; CHECK-NEXT: vpcmpnled %zmm1, %zmm0, %k1 {%k3}
|
|
; CHECK-NEXT: vpcmpordd %zmm1, %zmm0, %k3 {%k3}
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: kmovw %k4, %ecx
|
|
; CHECK-NEXT: vmovd %ecx, %xmm0
|
|
; CHECK-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 0, i16 %mask)
|
|
%vec0 = insertelement <8 x i16> undef, i16 %res0, i32 0
|
|
%res1 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 1, i16 %mask)
|
|
%vec1 = insertelement <8 x i16> %vec0, i16 %res1, i32 1
|
|
%res2 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 2, i16 %mask)
|
|
%vec2 = insertelement <8 x i16> %vec1, i16 %res2, i32 2
|
|
%res3 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 3, i16 %mask)
|
|
%vec3 = insertelement <8 x i16> %vec2, i16 %res3, i32 3
|
|
%res4 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 4, i16 %mask)
|
|
%vec4 = insertelement <8 x i16> %vec3, i16 %res4, i32 4
|
|
%res5 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 5, i16 %mask)
|
|
%vec5 = insertelement <8 x i16> %vec4, i16 %res5, i32 5
|
|
%res6 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 6, i16 %mask)
|
|
%vec6 = insertelement <8 x i16> %vec5, i16 %res6, i32 6
|
|
%res7 = call i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 7, i16 %mask)
|
|
%vec7 = insertelement <8 x i16> %vec6, i16 %res7, i32 7
|
|
ret <8 x i16> %vec7
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.mask.cmp.d.512(<16 x i32>, <16 x i32>, i32, i16) nounwind readnone
|
|
|
|
define <8 x i16> @test_ucmp_d_512(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_ucmp_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpcmpequd %zmm1, %zmm0, %k3
|
|
; CHECK-NEXT: vpcmpltud %zmm1, %zmm0, %k4
|
|
; CHECK-NEXT: vpcmpleud %zmm1, %zmm0, %k5
|
|
; CHECK-NEXT: vpcmpunordud %zmm1, %zmm0, %k6
|
|
; CHECK-NEXT: vpcmpnequd %zmm1, %zmm0, %k7
|
|
; CHECK-NEXT: vpcmpnltud %zmm1, %zmm0, %k2
|
|
; CHECK-NEXT: vpcmpnleud %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpcmpordud %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: kmovw %k3, %ecx
|
|
; CHECK-NEXT: vmovd %ecx, %xmm0
|
|
; CHECK-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 0, i16 -1)
|
|
%vec0 = insertelement <8 x i16> undef, i16 %res0, i32 0
|
|
%res1 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 1, i16 -1)
|
|
%vec1 = insertelement <8 x i16> %vec0, i16 %res1, i32 1
|
|
%res2 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 2, i16 -1)
|
|
%vec2 = insertelement <8 x i16> %vec1, i16 %res2, i32 2
|
|
%res3 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 3, i16 -1)
|
|
%vec3 = insertelement <8 x i16> %vec2, i16 %res3, i32 3
|
|
%res4 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 4, i16 -1)
|
|
%vec4 = insertelement <8 x i16> %vec3, i16 %res4, i32 4
|
|
%res5 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 5, i16 -1)
|
|
%vec5 = insertelement <8 x i16> %vec4, i16 %res5, i32 5
|
|
%res6 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 6, i16 -1)
|
|
%vec6 = insertelement <8 x i16> %vec5, i16 %res6, i32 6
|
|
%res7 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 7, i16 -1)
|
|
%vec7 = insertelement <8 x i16> %vec6, i16 %res7, i32 7
|
|
ret <8 x i16> %vec7
|
|
}
|
|
|
|
define <8 x i16> @test_mask_ucmp_d_512(<16 x i32> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_ucmp_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k3
|
|
; CHECK-NEXT: vpcmpequd %zmm1, %zmm0, %k4 {%k3}
|
|
; CHECK-NEXT: vpcmpltud %zmm1, %zmm0, %k5 {%k3}
|
|
; CHECK-NEXT: vpcmpleud %zmm1, %zmm0, %k6 {%k3}
|
|
; CHECK-NEXT: vpcmpunordud %zmm1, %zmm0, %k7 {%k3}
|
|
; CHECK-NEXT: vpcmpnequd %zmm1, %zmm0, %k0 {%k3}
|
|
; CHECK-NEXT: vpcmpnltud %zmm1, %zmm0, %k2 {%k3}
|
|
; CHECK-NEXT: vpcmpnleud %zmm1, %zmm0, %k1 {%k3}
|
|
; CHECK-NEXT: vpcmpordud %zmm1, %zmm0, %k3 {%k3}
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: kmovw %k4, %ecx
|
|
; CHECK-NEXT: vmovd %ecx, %xmm0
|
|
; CHECK-NEXT: vpinsrw $1, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrw $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrw $3, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrw $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrw $5, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrw $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrw $7, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 0, i16 %mask)
|
|
%vec0 = insertelement <8 x i16> undef, i16 %res0, i32 0
|
|
%res1 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 1, i16 %mask)
|
|
%vec1 = insertelement <8 x i16> %vec0, i16 %res1, i32 1
|
|
%res2 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 2, i16 %mask)
|
|
%vec2 = insertelement <8 x i16> %vec1, i16 %res2, i32 2
|
|
%res3 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 3, i16 %mask)
|
|
%vec3 = insertelement <8 x i16> %vec2, i16 %res3, i32 3
|
|
%res4 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 4, i16 %mask)
|
|
%vec4 = insertelement <8 x i16> %vec3, i16 %res4, i32 4
|
|
%res5 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 5, i16 %mask)
|
|
%vec5 = insertelement <8 x i16> %vec4, i16 %res5, i32 5
|
|
%res6 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 6, i16 %mask)
|
|
%vec6 = insertelement <8 x i16> %vec5, i16 %res6, i32 6
|
|
%res7 = call i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32> %a0, <16 x i32> %a1, i32 7, i16 %mask)
|
|
%vec7 = insertelement <8 x i16> %vec6, i16 %res7, i32 7
|
|
ret <8 x i16> %vec7
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.mask.ucmp.d.512(<16 x i32>, <16 x i32>, i32, i16) nounwind readnone
|
|
|
|
define <8 x i8> @test_cmp_q_512(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_cmp_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpcmpeqq %zmm1, %zmm0, %k3
|
|
; CHECK-NEXT: vpcmpltq %zmm1, %zmm0, %k4
|
|
; CHECK-NEXT: vpcmpleq %zmm1, %zmm0, %k5
|
|
; CHECK-NEXT: vpcmpunordq %zmm1, %zmm0, %k6
|
|
; CHECK-NEXT: vpcmpneqq %zmm1, %zmm0, %k7
|
|
; CHECK-NEXT: vpcmpnltq %zmm1, %zmm0, %k2
|
|
; CHECK-NEXT: vpcmpnleq %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpcmpordq %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrb $0, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrb $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrb $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrb $12, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 0, i8 -1)
|
|
%vec0 = insertelement <8 x i8> undef, i8 %res0, i32 0
|
|
%res1 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 1, i8 -1)
|
|
%vec1 = insertelement <8 x i8> %vec0, i8 %res1, i32 1
|
|
%res2 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 2, i8 -1)
|
|
%vec2 = insertelement <8 x i8> %vec1, i8 %res2, i32 2
|
|
%res3 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 3, i8 -1)
|
|
%vec3 = insertelement <8 x i8> %vec2, i8 %res3, i32 3
|
|
%res4 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 4, i8 -1)
|
|
%vec4 = insertelement <8 x i8> %vec3, i8 %res4, i32 4
|
|
%res5 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 5, i8 -1)
|
|
%vec5 = insertelement <8 x i8> %vec4, i8 %res5, i32 5
|
|
%res6 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 6, i8 -1)
|
|
%vec6 = insertelement <8 x i8> %vec5, i8 %res6, i32 6
|
|
%res7 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 7, i8 -1)
|
|
%vec7 = insertelement <8 x i8> %vec6, i8 %res7, i32 7
|
|
ret <8 x i8> %vec7
|
|
}
|
|
|
|
define <8 x i8> @test_mask_cmp_q_512(<8 x i64> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_cmp_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k3
|
|
; CHECK-NEXT: vpcmpeqq %zmm1, %zmm0, %k4 {%k3}
|
|
; CHECK-NEXT: vpcmpltq %zmm1, %zmm0, %k5 {%k3}
|
|
; CHECK-NEXT: vpcmpleq %zmm1, %zmm0, %k6 {%k3}
|
|
; CHECK-NEXT: vpcmpunordq %zmm1, %zmm0, %k7 {%k3}
|
|
; CHECK-NEXT: vpcmpneqq %zmm1, %zmm0, %k0 {%k3}
|
|
; CHECK-NEXT: vpcmpnltq %zmm1, %zmm0, %k2 {%k3}
|
|
; CHECK-NEXT: vpcmpnleq %zmm1, %zmm0, %k1 {%k3}
|
|
; CHECK-NEXT: vpcmpordq %zmm1, %zmm0, %k3 {%k3}
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: vpinsrb $0, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrb $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrb $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrb $12, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 0, i8 %mask)
|
|
%vec0 = insertelement <8 x i8> undef, i8 %res0, i32 0
|
|
%res1 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 1, i8 %mask)
|
|
%vec1 = insertelement <8 x i8> %vec0, i8 %res1, i32 1
|
|
%res2 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 2, i8 %mask)
|
|
%vec2 = insertelement <8 x i8> %vec1, i8 %res2, i32 2
|
|
%res3 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 3, i8 %mask)
|
|
%vec3 = insertelement <8 x i8> %vec2, i8 %res3, i32 3
|
|
%res4 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 4, i8 %mask)
|
|
%vec4 = insertelement <8 x i8> %vec3, i8 %res4, i32 4
|
|
%res5 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 5, i8 %mask)
|
|
%vec5 = insertelement <8 x i8> %vec4, i8 %res5, i32 5
|
|
%res6 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 6, i8 %mask)
|
|
%vec6 = insertelement <8 x i8> %vec5, i8 %res6, i32 6
|
|
%res7 = call i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 7, i8 %mask)
|
|
%vec7 = insertelement <8 x i8> %vec6, i8 %res7, i32 7
|
|
ret <8 x i8> %vec7
|
|
}
|
|
|
|
declare i8 @llvm.x86.avx512.mask.cmp.q.512(<8 x i64>, <8 x i64>, i32, i8) nounwind readnone
|
|
|
|
define <8 x i8> @test_ucmp_q_512(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_ucmp_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpcmpequq %zmm1, %zmm0, %k3
|
|
; CHECK-NEXT: vpcmpltuq %zmm1, %zmm0, %k4
|
|
; CHECK-NEXT: vpcmpleuq %zmm1, %zmm0, %k5
|
|
; CHECK-NEXT: vpcmpunorduq %zmm1, %zmm0, %k6
|
|
; CHECK-NEXT: vpcmpnequq %zmm1, %zmm0, %k7
|
|
; CHECK-NEXT: vpcmpnltuq %zmm1, %zmm0, %k2
|
|
; CHECK-NEXT: vpcmpnleuq %zmm1, %zmm0, %k1
|
|
; CHECK-NEXT: vpcmporduq %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrb $0, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrb $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrb $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrb $12, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 0, i8 -1)
|
|
%vec0 = insertelement <8 x i8> undef, i8 %res0, i32 0
|
|
%res1 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 1, i8 -1)
|
|
%vec1 = insertelement <8 x i8> %vec0, i8 %res1, i32 1
|
|
%res2 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 2, i8 -1)
|
|
%vec2 = insertelement <8 x i8> %vec1, i8 %res2, i32 2
|
|
%res3 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 3, i8 -1)
|
|
%vec3 = insertelement <8 x i8> %vec2, i8 %res3, i32 3
|
|
%res4 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 4, i8 -1)
|
|
%vec4 = insertelement <8 x i8> %vec3, i8 %res4, i32 4
|
|
%res5 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 5, i8 -1)
|
|
%vec5 = insertelement <8 x i8> %vec4, i8 %res5, i32 5
|
|
%res6 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 6, i8 -1)
|
|
%vec6 = insertelement <8 x i8> %vec5, i8 %res6, i32 6
|
|
%res7 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 7, i8 -1)
|
|
%vec7 = insertelement <8 x i8> %vec6, i8 %res7, i32 7
|
|
ret <8 x i8> %vec7
|
|
}
|
|
|
|
define <8 x i8> @test_mask_ucmp_q_512(<8 x i64> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_ucmp_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k3
|
|
; CHECK-NEXT: vpcmpequq %zmm1, %zmm0, %k4 {%k3}
|
|
; CHECK-NEXT: vpcmpltuq %zmm1, %zmm0, %k5 {%k3}
|
|
; CHECK-NEXT: vpcmpleuq %zmm1, %zmm0, %k6 {%k3}
|
|
; CHECK-NEXT: vpcmpunorduq %zmm1, %zmm0, %k7 {%k3}
|
|
; CHECK-NEXT: vpcmpnequq %zmm1, %zmm0, %k0 {%k3}
|
|
; CHECK-NEXT: vpcmpnltuq %zmm1, %zmm0, %k2 {%k3}
|
|
; CHECK-NEXT: vpcmpnleuq %zmm1, %zmm0, %k1 {%k3}
|
|
; CHECK-NEXT: vpcmporduq %zmm1, %zmm0, %k3 {%k3}
|
|
; CHECK-NEXT: kmovw %k4, %eax
|
|
; CHECK-NEXT: vpinsrb $0, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k5, %eax
|
|
; CHECK-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k6, %eax
|
|
; CHECK-NEXT: vpinsrb $4, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k7, %eax
|
|
; CHECK-NEXT: vpinsrb $6, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: vpinsrb $8, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k2, %eax
|
|
; CHECK-NEXT: vpinsrb $10, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k1, %eax
|
|
; CHECK-NEXT: vpinsrb $12, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: kmovw %k3, %eax
|
|
; CHECK-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 0, i8 %mask)
|
|
%vec0 = insertelement <8 x i8> undef, i8 %res0, i32 0
|
|
%res1 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 1, i8 %mask)
|
|
%vec1 = insertelement <8 x i8> %vec0, i8 %res1, i32 1
|
|
%res2 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 2, i8 %mask)
|
|
%vec2 = insertelement <8 x i8> %vec1, i8 %res2, i32 2
|
|
%res3 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 3, i8 %mask)
|
|
%vec3 = insertelement <8 x i8> %vec2, i8 %res3, i32 3
|
|
%res4 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 4, i8 %mask)
|
|
%vec4 = insertelement <8 x i8> %vec3, i8 %res4, i32 4
|
|
%res5 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 5, i8 %mask)
|
|
%vec5 = insertelement <8 x i8> %vec4, i8 %res5, i32 5
|
|
%res6 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 6, i8 %mask)
|
|
%vec6 = insertelement <8 x i8> %vec5, i8 %res6, i32 6
|
|
%res7 = call i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64> %a0, <8 x i64> %a1, i32 7, i8 %mask)
|
|
%vec7 = insertelement <8 x i8> %vec6, i8 %res7, i32 7
|
|
ret <8 x i8> %vec7
|
|
}
|
|
|
|
declare i8 @llvm.x86.avx512.mask.ucmp.q.512(<8 x i64>, <8 x i64>, i32, i8) nounwind readnone
|
|
|
|
define <4 x float> @test_mask_vextractf32x4(<4 x float> %b, <16 x float> %a, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_vextractf32x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vextractf32x4 $2, %zmm1, %xmm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vextractf32x4.512(<16 x float> %a, i32 2, <4 x float> %b, i8 %mask)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.vextractf32x4.512(<16 x float>, i32, <4 x float>, i8)
|
|
|
|
define <4 x i64> @test_mask_vextracti64x4(<4 x i64> %b, <8 x i64> %a, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_vextracti64x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vextracti64x4 $2, %zmm1, %ymm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x i64> @llvm.x86.avx512.mask.vextracti64x4.512(<8 x i64> %a, i32 2, <4 x i64> %b, i8 %mask)
|
|
ret <4 x i64> %res
|
|
}
|
|
|
|
declare <4 x i64> @llvm.x86.avx512.mask.vextracti64x4.512(<8 x i64>, i32, <4 x i64>, i8)
|
|
|
|
define <4 x i32> @test_maskz_vextracti32x4(<16 x i32> %a, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_vextracti32x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vextracti32x4 $2, %zmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x i32> @llvm.x86.avx512.mask.vextracti32x4.512(<16 x i32> %a, i32 2, <4 x i32> zeroinitializer, i8 %mask)
|
|
ret <4 x i32> %res
|
|
}
|
|
|
|
declare <4 x i32> @llvm.x86.avx512.mask.vextracti32x4.512(<16 x i32>, i32, <4 x i32>, i8)
|
|
|
|
define <4 x double> @test_vextractf64x4(<8 x double> %a) {
|
|
; CHECK-LABEL: test_vextractf64x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vextractf64x4 $2, %zmm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x double> @llvm.x86.avx512.mask.vextractf64x4.512(<8 x double> %a, i32 2, <4 x double> zeroinitializer, i8 -1)
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
declare <4 x double> @llvm.x86.avx512.mask.vextractf64x4.512(<8 x double>, i32, <4 x double>, i8)
|
|
|
|
define <16 x i32> @test_x86_avx512_psll_d(<16 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psll_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpslld %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psll.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psll_d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psll_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpslld %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psll.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psll_d(<16 x i32> %a0, <4 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psll_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpslld %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psll.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psll.d(<16 x i32>, <4 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psll_q(<8 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psll_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsllq %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psll.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psll_q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psll_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllq %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psll.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psll_q(<8 x i64> %a0, <2 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psll_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllq %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psll.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psll.q(<8 x i64>, <2 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <16 x i32> @test_x86_avx512_psrl_d(<16 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrl_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrld %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrl.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psrl_d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrl_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrld %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrl.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psrl_d(<16 x i32> %a0, <4 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrl_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrld %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrl.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psrl.d(<16 x i32>, <4 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psrl_q(<8 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrl_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrlq %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrl.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psrl_q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrl_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlq %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrl.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psrl_q(<8 x i64> %a0, <2 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrl_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlq %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrl.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psrl.q(<8 x i64>, <2 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <16 x i32> @test_x86_avx512_psra_d(<16 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psra_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrad %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psra.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psra_d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psra_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrad %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psra.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psra_d(<16 x i32> %a0, <4 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psra_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrad %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psra.d(<16 x i32> %a0, <4 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psra.d(<16 x i32>, <4 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psra_q(<8 x i64> %a0, <2 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psra_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsraq %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psra.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psra_q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psra_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsraq %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psra.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psra_q(<8 x i64> %a0, <2 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psra_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsraq %xmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psra.q(<8 x i64> %a0, <2 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psra.q(<8 x i64>, <2 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <16 x i32> @test_x86_avx512_psllv_d(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psllv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsllvd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psllv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psllv_d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psllv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllvd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psllv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psllv_d(<16 x i32> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psllv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllvd %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psllv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psllv.d(<16 x i32>, <16 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psllv_q(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psllv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsllvq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psllv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psllv_q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psllv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllvq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psllv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psllv_q(<8 x i64> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psllv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsllvq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psllv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psllv.q(<8 x i64>, <8 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
|
|
define <16 x i32> @test_x86_avx512_psrav_d(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrav_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsravd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrav.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psrav_d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrav_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsravd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrav.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psrav_d(<16 x i32> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrav_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsravd %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrav.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psrav.d(<16 x i32>, <16 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psrav_q(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrav_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsravq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrav.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psrav_q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrav_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsravq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrav.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psrav_q(<8 x i64> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrav_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsravq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrav.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psrav.q(<8 x i64>, <8 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <16 x i32> @test_x86_avx512_psrlv_d(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrlv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrlvd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrlv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_mask_psrlv_d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrlv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlvd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrlv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> %a2, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_x86_avx512_maskz_psrlv_d(<16 x i32> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrlv_d:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlvd %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrlv.d(<16 x i32> %a0, <16 x i32> %a1, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psrlv.d(<16 x i32>, <16 x i32>, <16 x i32>, i16) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psrlv_q(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_psrlv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrlvq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrlv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_mask_psrlv_q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_mask_psrlv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlvq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrlv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_x86_avx512_maskz_psrlv_q(<8 x i64> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_x86_avx512_maskz_psrlv_q:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsrlvq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrlv.q(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psrlv.q(<8 x i64>, <8 x i64>, <8 x i64>, i8) nounwind readnone
|
|
|
|
define <8 x i64> @test_x86_avx512_psrlv_q_memop(<8 x i64> %a0, <8 x i64>* %ptr) {
|
|
; CHECK-LABEL: test_x86_avx512_psrlv_q_memop:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsrlvq (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrlv.q(<8 x i64> %a0, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
declare <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
declare <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)
|
|
|
|
define <16 x float> @test_vsubps_rn(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vsubps_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vsubps_rd(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vsubps_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vsubps_ru(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vsubps_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vsubps_rz(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vsubps_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_rn(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vmulps_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_rd(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vmulps_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_ru(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vmulps_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_rz(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: test_vmulps_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
;; mask float
|
|
define <16 x float> @test_vmulps_mask_rn(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_rd(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_ru(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_rz(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> zeroinitializer, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
;; With Passthru value
|
|
define <16 x float> @test_vmulps_mask_passthru_rn(<16 x float> %a0, <16 x float> %a1, <16 x float> %passthru, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_passthru_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> %passthru, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_passthru_rd(<16 x float> %a0, <16 x float> %a1, <16 x float> %passthru, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_passthru_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> %passthru, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_passthru_ru(<16 x float> %a0, <16 x float> %a1, <16 x float> %passthru, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_passthru_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> %passthru, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_vmulps_mask_passthru_rz(<16 x float> %a0, <16 x float> %a1, <16 x float> %passthru, i16 %mask) {
|
|
; CHECK-LABEL: test_vmulps_mask_passthru_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
|
|
<16 x float> %passthru, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
;; mask double
|
|
define <8 x double> @test_vmulpd_mask_rn(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_vmulpd_mask_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulpd {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double> zeroinitializer, i8 %mask, i32 0)
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @test_vmulpd_mask_rd(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_vmulpd_mask_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulpd {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double> zeroinitializer, i8 %mask, i32 1)
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @test_vmulpd_mask_ru(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_vmulpd_mask_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulpd {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double> zeroinitializer, i8 %mask, i32 2)
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @test_vmulpd_mask_rz(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_vmulpd_mask_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulpd {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
|
|
<8 x double> zeroinitializer, i8 %mask, i32 3)
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rr(<16 x i32> %a, <16 x i32> %b) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rrk(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rrkz(<16 x i32> %a, <16 x i32> %b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rm(<16 x i32> %a, <16 x i32>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddd (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rmk(<16 x i32> %a, <16 x i32>* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddd (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rmkz(<16 x i32> %a, <16 x i32>* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddd (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rmb(<16 x i32> %a, i32* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddd (%rdi){1to16}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rmbk(<16 x i32> %a, i32* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddd (%rdi){1to16}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_add_epi32_rmbkz(<16 x i32> %a, i32* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi32_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddd (%rdi){1to16}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.padd.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rr(<16 x i32> %a, <16 x i32> %b) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rrk(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsubd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rrkz(<16 x i32> %a, <16 x i32> %b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsubd %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rm(<16 x i32> %a, <16 x i32>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubd (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rmk(<16 x i32> %a, <16 x i32>* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubd (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rmkz(<16 x i32> %a, <16 x i32>* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubd (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rmb(<16 x i32> %a, i32* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubd (%rdi){1to16}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rmbk(<16 x i32> %a, i32* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubd (%rdi){1to16}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_sub_epi32_rmbkz(<16 x i32> %a, i32* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi32_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubd (%rdi){1to16}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psub.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rr(<8 x i64> %a, <8 x i64> %b) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rrk(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rrkz(<8 x i64> %a, <8 x i64> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rm(<8 x i64> %a, <8 x i64>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddq (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rmk(<8 x i64> %a, <8 x i64>* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddq (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rmkz(<8 x i64> %a, <8 x i64>* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddq (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rmb(<8 x i64> %a, i64* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpaddq (%rdi){1to8}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rmbk(<8 x i64> %a, i64* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddq (%rdi){1to8}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_add_epi64_rmbkz(<8 x i64> %a, i64* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_epi64_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpaddq (%rdi){1to8}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.padd.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rr(<8 x i64> %a, <8 x i64> %b) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rrk(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsubq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rrkz(<8 x i64> %a, <8 x i64> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpsubq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rm(<8 x i64> %a, <8 x i64>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubq (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rmk(<8 x i64> %a, <8 x i64>* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubq (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rmkz(<8 x i64> %a, <8 x i64>* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubq (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <8 x i64>, <8 x i64>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rmb(<8 x i64> %a, i64* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpsubq (%rdi){1to8}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rmbk(<8 x i64> %a, i64* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubq (%rdi){1to8}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_sub_epi64_rmbkz(<8 x i64> %a, i64* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_sub_epi64_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsubq (%rdi){1to8}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psub.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rr(<16 x i32> %a, <16 x i32> %b) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuldq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rrk(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmuldq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rrkz(<16 x i32> %a, <16 x i32> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmuldq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rm(<16 x i32> %a, <16 x i32>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuldq (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rmk(<16 x i32> %a, <16 x i32>* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuldq (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rmkz(<16 x i32> %a, <16 x i32>* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuldq (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rmb(<16 x i32> %a, i64* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuldq (%rdi){1to8}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rmbk(<16 x i32> %a, i64* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuldq (%rdi){1to8}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epi32_rmbkz(<16 x i32> %a, i64* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epi32_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuldq (%rdi){1to8}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmul.dq.512(<16 x i32>, <16 x i32>, <8 x i64>, i8)
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rr(<16 x i32> %a, <16 x i32> %b) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuludq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rrk(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmuludq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rrkz(<16 x i32> %a, <16 x i32> %b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmuludq %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rm(<16 x i32> %a, <16 x i32>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuludq (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rmk(<16 x i32> %a, <16 x i32>* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rmk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuludq (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rmkz(<16 x i32> %a, <16 x i32>* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rmkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuludq (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rmb(<16 x i32> %a, i64* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rmb:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmuludq (%rdi){1to8}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 -1)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rmbk(<16 x i32> %a, i64* %ptr_b, <8 x i64> %passThru, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rmbk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuludq (%rdi){1to8}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> %passThru, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
define <8 x i64> @test_mask_mul_epu32_rmbkz(<16 x i32> %a, i64* %ptr_b, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_mul_epu32_rmbkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmuludq (%rdi){1to8}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i64, i64* %ptr_b
|
|
%vecinit.i = insertelement <8 x i64> undef, i64 %q, i32 0
|
|
%b64 = shufflevector <8 x i64> %vecinit.i, <8 x i64> undef, <8 x i32> zeroinitializer
|
|
%b = bitcast <8 x i64> %b64 to <16 x i32>
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32> %a, <16 x i32> %b, <8 x i64> zeroinitializer, i8 %mask)
|
|
ret < 8 x i64> %res
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmulu.dq.512(<16 x i32>, <16 x i32>, <8 x i64>, i8)
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rr_512(<16 x i32> %a, <16 x i32> %b) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rr_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmulld %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rrk_512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rrk_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmulld %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rrkz_512(<16 x i32> %a, <16 x i32> %b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rrkz_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmulld %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rm_512(<16 x i32> %a, <16 x i32>* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rm_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmulld (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rmk_512(<16 x i32> %a, <16 x i32>* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rmk_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmulld (%rdi), %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rmkz_512(<16 x i32> %a, <16 x i32>* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rmkz_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmulld (%rdi), %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%b = load <16 x i32>, <16 x i32>* %ptr_b
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rmb_512(<16 x i32> %a, i32* %ptr_b) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rmb_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmulld (%rdi){1to16}, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 -1)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rmbk_512(<16 x i32> %a, i32* %ptr_b, <16 x i32> %passThru, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rmbk_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmulld (%rdi){1to16}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> %passThru, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
define <16 x i32> @test_mask_mullo_epi32_rmbkz_512(<16 x i32> %a, i32* %ptr_b, i16 %mask) {
|
|
; CHECK-LABEL: test_mask_mullo_epi32_rmbkz_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmulld (%rdi){1to16}, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%q = load i32, i32* %ptr_b
|
|
%vecinit.i = insertelement <16 x i32> undef, i32 %q, i32 0
|
|
%b = shufflevector <16 x i32> %vecinit.i, <16 x i32> undef, <16 x i32> zeroinitializer
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32> %a, <16 x i32> %b, <16 x i32> zeroinitializer, i16 %mask)
|
|
ret < 16 x i32> %res
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmull.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x float> @test_mm512_maskz_add_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_add_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_maskz_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_add_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_maskz_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_add_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_maskz_add_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_add_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_maskz_add_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_add_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_add_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_add_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_add_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_add_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_add_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_add_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_mask_add_round_ps_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_add_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_add_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_add_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_add_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_add_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_add_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_add_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_add_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_add_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
|
|
define <16 x float> @test_mm512_mask_sub_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_sub_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_sub_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_sub_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_sub_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_sub_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_sub_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_sub_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_mask_sub_round_ps_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_sub_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vsubps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_sub_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_sub_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_sub_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_sub_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_sub_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_sub_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_sub_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_sub_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_sub_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_sub_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vsubps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_maskz_div_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_div_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_maskz_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_div_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_maskz_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_div_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_maskz_div_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_div_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_maskz_div_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_div_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_div_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_div_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_div_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_mask_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_div_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_div_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_div_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_mask_div_round_ps_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_div_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vdivps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
|
|
define <16 x float> @test_mm512_div_round_ps_rn_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_div_round_ps_rn_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_div_round_ps_rd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
|
|
ret <16 x float> %res
|
|
}
|
|
define <16 x float> @test_mm512_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_div_round_ps_ru_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_div_round_ps_rz_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_div_round_ps_rz_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_div_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_div_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vdivps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
|
|
define <16 x float> @test_mm512_maskz_min_round_ps_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_min_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminps {sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_maskz_min_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_min_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminps %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_min_round_ps_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_min_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminps {sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_min_round_ps_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_min_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_min_round_ps_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_min_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vminps {sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_min_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_min_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vminps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.min.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
|
|
define <16 x float> @test_mm512_maskz_max_round_ps_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_max_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxps {sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_maskz_max_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_maskz_max_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxps %zmm1, %zmm0, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_max_round_ps_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_max_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxps {sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_mask_max_round_ps_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_mask_max_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_max_round_ps_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_max_round_ps_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxps {sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 8)
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @test_mm512_max_round_ps_current(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: test_mm512_max_round_ps_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 4)
|
|
ret <16 x float> %res
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.max.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_mask_add_ss_rn(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_ss_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 0)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_mask_add_ss_rd(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_ss_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 1)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_mask_add_ss_ru(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_ss_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss {ru-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 2)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_mask_add_ss_rz(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_ss_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss {rz-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 3)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_mask_add_ss_current(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_ss_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 4)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_maskz_add_ss_rn(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_add_ss_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 0)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_add_ss_rn(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: test_add_ss_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 0)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_mask_add_sd_rn(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_sd_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 0)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_mask_add_sd_rd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_sd_rd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 1)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_mask_add_sd_ru(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_sd_ru:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd {ru-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 2)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_mask_add_sd_rz(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_sd_rz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd {rz-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 3)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_mask_add_sd_current(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_add_sd_current:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 4)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_maskz_add_sd_rn(<2 x double> %a0, <2 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_add_sd_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 0)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_add_sd_rn(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_add_sd_rn:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 0)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_mask_max_ss_sae(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_max_ss_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxss {sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 8)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_maskz_max_ss_sae(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_max_ss_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxss {sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 8)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_max_ss_sae(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: test_max_ss_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxss {sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 8)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_mask_max_ss(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_max_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxss %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 4)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_maskz_max_ss(<4 x float> %a0, <4 x float> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_max_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxss %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 4)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_max_ss(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: test_max_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxss %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 4)
|
|
ret <4 x float> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_mask_max_sd_sae(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_max_sd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxsd {sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 8)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_maskz_max_sd_sae(<2 x double> %a0, <2 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_max_sd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxsd {sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 8)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_max_sd_sae(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_max_sd_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxsd {sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 8)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_mask_max_sd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_mask_max_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxsd %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 4)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_maskz_max_sd(<2 x double> %a0, <2 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: test_maskz_max_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxsd %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 4)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_max_sd(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_max_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmaxsd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 4)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_x86_avx512_cvtsi2sd32(<2 x double> %a, i32 %b) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsi2sd32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2sdl %edi, {rz-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.cvtsi2sd32(<2 x double> %a, i32 %b, i32 3) ; <<<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.cvtsi2sd32(<2 x double>, i32, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_x86_avx512_cvtsi2sd64(<2 x double> %a, i64 %b) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsi2sd64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2sdq %rdi, {rz-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.cvtsi2sd64(<2 x double> %a, i64 %b, i32 3) ; <<<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.cvtsi2sd64(<2 x double>, i64, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_x86_avx512_cvtsi2ss32(<4 x float> %a, i32 %b) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsi2ss32:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2ssl %edi, {rz-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss32(<4 x float> %a, i32 %b, i32 3) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.avx512.cvtsi2ss32(<4 x float>, i32, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_x86_avx512_cvtsi2ss64(<4 x float> %a, i64 %b) {
|
|
; CHECK-LABEL: test_x86_avx512_cvtsi2ss64:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtsi2ssq %rdi, {rz-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss64(<4 x float> %a, i64 %b, i32 3) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.avx512.cvtsi2ss64(<4 x float>, i64, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_x86_avx512__mm_cvt_roundu32_ss (<4 x float> %a, i32 %b)
|
|
; CHECK-LABEL: test_x86_avx512__mm_cvt_roundu32_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2ssl %edi, {rd-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 1) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_x86_avx512__mm_cvt_roundu32_ss_mem(<4 x float> %a, i32* %ptr)
|
|
; CHECK-LABEL: test_x86_avx512__mm_cvt_roundu32_ss_mem:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: movl (%rdi), %eax
|
|
; CHECK-NEXT: vcvtusi2ssl %eax, {rd-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%b = load i32, i32* %ptr
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 1) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_x86_avx512__mm_cvtu32_ss(<4 x float> %a, i32 %b)
|
|
; CHECK-LABEL: test_x86_avx512__mm_cvtu32_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2ssl %edi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 4) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_x86_avx512__mm_cvtu32_ss_mem(<4 x float> %a, i32* %ptr)
|
|
; CHECK-LABEL: test_x86_avx512__mm_cvtu32_ss_mem:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2ssl (%rdi), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%b = load i32, i32* %ptr
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 4) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float>, i32, i32) nounwind readnone
|
|
|
|
define <4 x float> @_mm_cvt_roundu64_ss (<4 x float> %a, i64 %b)
|
|
; CHECK-LABEL: _mm_cvt_roundu64_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2ssq %rdi, {rd-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi642ss(<4 x float> %a, i64 %b, i32 1) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @_mm_cvtu64_ss(<4 x float> %a, i64 %b)
|
|
; CHECK-LABEL: _mm_cvtu64_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2ssq %rdi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <4 x float> @llvm.x86.avx512.cvtusi642ss(<4 x float> %a, i64 %b, i32 4) ; <<<4 x float>> [#uses=1]
|
|
ret <4 x float> %res
|
|
}
|
|
declare <4 x float> @llvm.x86.avx512.cvtusi642ss(<4 x float>, i64, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_x86_avx512_mm_cvtu32_sd(<2 x double> %a, i32 %b)
|
|
; CHECK-LABEL: test_x86_avx512_mm_cvtu32_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2sdl %edi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <2 x double> @llvm.x86.avx512.cvtusi2sd(<2 x double> %a, i32 %b) ; <<<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.cvtusi2sd(<2 x double>, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_x86_avx512_mm_cvtu64_sd(<2 x double> %a, i64 %b)
|
|
; CHECK-LABEL: test_x86_avx512_mm_cvtu64_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2sdq %rdi, {rd-sae}, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <2 x double> @llvm.x86.avx512.cvtusi642sd(<2 x double> %a, i64 %b, i32 1) ; <<<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @test_x86_avx512__mm_cvt_roundu64_sd(<2 x double> %a, i64 %b)
|
|
; CHECK-LABEL: test_x86_avx512__mm_cvt_roundu64_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcvtusi2sdq %rdi, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
{
|
|
%res = call <2 x double> @llvm.x86.avx512.cvtusi642sd(<2 x double> %a, i64 %b, i32 4) ; <<<2 x double>> [#uses=1]
|
|
ret <2 x double> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.cvtusi642sd(<2 x double>, i64, i32) nounwind readnone
|
|
|
|
define <8 x i64> @test_vpmaxq(<8 x i64> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: test_vpmaxq:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmaxs.q.512(<8 x i64> %a0, <8 x i64> %a1,
|
|
<8 x i64>zeroinitializer, i8 -1)
|
|
ret <8 x i64> %res
|
|
}
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmaxs.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <16 x i32> @test_vpminud(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_vpminud:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pminu.d.512(<16 x i32> %a0, <16 x i32> %a1,
|
|
<16 x i32>zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pminu.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32> @test_vpmaxsd(<16 x i32> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: test_vpmaxsd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmaxsd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmaxs.d.512(<16 x i32> %a0, <16 x i32> %a1,
|
|
<16 x i32>zeroinitializer, i16 -1)
|
|
ret <16 x i32> %res
|
|
}
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmaxs.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmaxs_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmaxsd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpmaxsd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmaxs.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmaxs.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmaxs_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxs_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmaxsq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmaxs.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmaxs.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmaxu.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmaxu_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmaxud %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpmaxud %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmaxu.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmaxu.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmaxu.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmaxu_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmaxu_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmaxuq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpmaxuq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmaxu.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmaxu.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmins.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmins_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpminsd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpminsd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmins.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmins.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmins.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmins_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmins_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpminsq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpminsq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmins.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmins.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pminu_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpminud %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpminud %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pminu.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pminu.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pminu.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pminu_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pminu_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpminuq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpminuq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pminu.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pminu.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.vpermi2var.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_vpermi2var_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32>* %x2p, <16 x i32> %x4, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermi2var_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermi2d (%rdi), %zmm0, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpermi2d %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%x2 = load <16 x i32>, <16 x i32>* %x2p
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.vpermi2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.vpermi2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x4, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.vpermi2var.pd.512(<8 x double>, <8 x i64>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_vpermi2var_pd_512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermi2var_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermi2pd %zmm2, %zmm0, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpermi2pd %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.vpermi2var.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.vpermi2var.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 -1)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.vpermi2var.ps.512(<16 x float>, <16 x i32>, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_vpermi2var_ps_512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermi2var_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermi2ps %zmm2, %zmm0, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpermi2ps %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vpermi2var.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.vpermi2var.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 -1)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.vpermi2var.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_vpermi2var_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermi2var_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermi2q %zmm2, %zmm0, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpermi2q %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.vpermi2var.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.vpermi2var.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.maskz.vpermt2var.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_maskz_vpermt2var_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32>* %x2p, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vpermt2var_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm2
|
|
; CHECK-NEXT: vpermt2d (%rdi), %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpermt2d %zmm1, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%x2 = load <16 x i32>, <16 x i32>* %x2p
|
|
%res = call <16 x i32> @llvm.x86.avx512.maskz.vpermt2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.maskz.vpermt2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x1, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.maskz.vpermt2var.pd.512(<8 x i64>, <8 x double>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_maskz_vpermt2var_pd_512(<8 x i64> %x0, <8 x double> %x1, double* %x2ptr, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vpermt2var_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm2
|
|
; CHECK-NEXT: vpermt2pd (%rdi){1to8}, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpermt2pd %zmm1, %zmm0, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%x2s = load double, double* %x2ptr
|
|
%x2ins = insertelement <8 x double> undef, double %x2s, i32 0
|
|
%x2 = shufflevector <8 x double> %x2ins, <8 x double> undef, <8 x i32> zeroinitializer
|
|
%res = call <8 x double> @llvm.x86.avx512.maskz.vpermt2var.pd.512(<8 x i64> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.maskz.vpermt2var.pd.512(<8 x i64> %x0, <8 x double> %x1, <8 x double> %x1, i8 -1)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32>, <16 x float>, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_maskz_vpermt2var_ps_512(<16 x i32> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vpermt2var_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermt2ps %zmm2, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermt2ps %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32> %x0, <16 x float> %x1, <16 x float> %x2, i16 -1)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.maskz.vpermt2var.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_maskz_vpermt2var_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vpermt2var_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermt2q %zmm2, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermt2q %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.maskz.vpermt2var.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.maskz.vpermt2var.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.vpermt2var.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_vpermt2var_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermt2var_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm3
|
|
; CHECK-NEXT: vpermt2d %zmm2, %zmm0, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpermt2d %zmm2, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.vpermt2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.vpermt2var.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)
|
|
define <8 x double>@test_int_x86_avx512_mask_scalef_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_scalef_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vscalefpd {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vscalefpd {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 3)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 -1, i32 0)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
|
|
define <16 x float>@test_int_x86_avx512_mask_scalef_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_scalef_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vscalefps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vscalefps {rn-sae}, %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 2)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 -1, i32 0)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64>, <16 x i8>, i8)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmov_qb_512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qb_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovqb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovqb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovqb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmov.qb.512(<8 x i64> %x0, <16 x i8> zeroinitializer, i8 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmov.qb.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmov_qb_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qb_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovqb %zmm0, (%rdi)
|
|
; CHECK-NEXT: vpmovqb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmov.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmov.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64>, <16 x i8>, i8)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmovs_qb_512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qb_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsqb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsqb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsqb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.qb.512(<8 x i64> %x0, <16 x i8> zeroinitializer, i8 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovs.qb.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovs_qb_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qb_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovsqb %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovsqb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovs.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovs.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64>, <16 x i8>, i8)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmovus_qb_512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qb_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovusqb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovusqb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovusqb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> %x0, <16 x i8> %x1, i8 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.qb.512(<8 x i64> %x0, <16 x i8> zeroinitializer, i8 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovus.qb.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovus_qb_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qb_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovusqb %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovusqb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovus.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovus.qb.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64>, <8 x i16>, i8)
|
|
|
|
define <8 x i16>@test_int_x86_avx512_mask_pmov_qw_512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovqw %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovqw %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovqw %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
|
|
%res1 = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2)
|
|
%res2 = call <8 x i16> @llvm.x86.avx512.mask.pmov.qw.512(<8 x i64> %x0, <8 x i16> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i16> %res0, %res1
|
|
%res4 = add <8 x i16> %res3, %res2
|
|
ret <8 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmov.qw.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmov_qw_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovqw %zmm0, (%rdi)
|
|
; CHECK-NEXT: vpmovqw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmov.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmov.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64>, <8 x i16>, i8)
|
|
|
|
define <8 x i16>@test_int_x86_avx512_mask_pmovs_qw_512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsqw %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsqw %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsqw %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
|
|
%res1 = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2)
|
|
%res2 = call <8 x i16> @llvm.x86.avx512.mask.pmovs.qw.512(<8 x i64> %x0, <8 x i16> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i16> %res0, %res1
|
|
%res4 = add <8 x i16> %res3, %res2
|
|
ret <8 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovs.qw.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovs_qw_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovsqw %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovsqw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovs.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovs.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64>, <8 x i16>, i8)
|
|
|
|
define <8 x i16>@test_int_x86_avx512_mask_pmovus_qw_512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovusqw %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovusqw %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovusqw %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddw %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 -1)
|
|
%res1 = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> %x0, <8 x i16> %x1, i8 %x2)
|
|
%res2 = call <8 x i16> @llvm.x86.avx512.mask.pmovus.qw.512(<8 x i64> %x0, <8 x i16> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i16> %res0, %res1
|
|
%res4 = add <8 x i16> %res3, %res2
|
|
ret <8 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovus.qw.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovus_qw_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovusqw %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovusqw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovus.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovus.qw.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.pmov.qd.512(<8 x i64>, <8 x i32>, i8)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_pmov_qd_512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovqd %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovqd %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovqd %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i32> @llvm.x86.avx512.mask.pmov.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 -1)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmov.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2)
|
|
%res2 = call <8 x i32> @llvm.x86.avx512.mask.pmov.qd.512(<8 x i64> %x0, <8 x i32> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i32> %res0, %res1
|
|
%res4 = add <8 x i32> %res3, %res2
|
|
ret <8 x i32> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmov.qd.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmov_qd_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_qd_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovqd %zmm0, (%rdi)
|
|
; CHECK-NEXT: vpmovqd %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmov.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmov.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64>, <8 x i32>, i8)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_pmovs_qd_512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsqd %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovsqd %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsqd %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 -1)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2)
|
|
%res2 = call <8 x i32> @llvm.x86.avx512.mask.pmovs.qd.512(<8 x i64> %x0, <8 x i32> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i32> %res0, %res1
|
|
%res4 = add <8 x i32> %res3, %res2
|
|
ret <8 x i32> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovs.qd.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovs_qd_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_qd_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovsqd %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovsqd %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovs.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovs.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64>, <8 x i32>, i8)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_pmovus_qd_512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovusqd %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovusqd %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovusqd %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 -1)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> %x1, i8 %x2)
|
|
%res2 = call <8 x i32> @llvm.x86.avx512.mask.pmovus.qd.512(<8 x i64> %x0, <8 x i32> zeroinitializer, i8 %x2)
|
|
%res3 = add <8 x i32> %res0, %res1
|
|
%res4 = add <8 x i32> %res3, %res2
|
|
ret <8 x i32> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovus.qd.mem.512(i8* %ptr, <8 x i64>, i8)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovus_qd_mem_512(i8* %ptr, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_qd_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovusqd %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovusqd %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovus.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 -1)
|
|
call void @llvm.x86.avx512.mask.pmovus.qd.mem.512(i8* %ptr, <8 x i64> %x1, i8 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32>, <16 x i8>, i16)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmov_db_512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_db_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovdb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovdb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovdb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmov.db.512(<16 x i32> %x0, <16 x i8> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmov.db.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmov_db_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_db_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovdb %zmm0, (%rdi)
|
|
; CHECK-NEXT: vpmovdb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmov.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmov.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32>, <16 x i8>, i16)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmovs_db_512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_db_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsdb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsdb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsdb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.db.512(<16 x i32> %x0, <16 x i8> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovs.db.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovs_db_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_db_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovsdb %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovsdb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovs.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmovs.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32>, <16 x i8>, i16)
|
|
|
|
define <16 x i8>@test_int_x86_avx512_mask_pmovus_db_512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_db_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovusdb %zmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vpmovusdb %zmm0, %xmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovusdb %zmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vpaddb %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 -1)
|
|
%res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> %x0, <16 x i8> %x1, i16 %x2)
|
|
%res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.db.512(<16 x i32> %x0, <16 x i8> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i8> %res0, %res1
|
|
%res4 = add <16 x i8> %res3, %res2
|
|
ret <16 x i8> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovus.db.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovus_db_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_db_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovusdb %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovusdb %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovus.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmovus.db.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32>, <16 x i16>, i16)
|
|
|
|
define <16 x i16>@test_int_x86_avx512_mask_pmov_dw_512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_dw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovdw %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovdw %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovdw %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
|
|
%res1 = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2)
|
|
%res2 = call <16 x i16> @llvm.x86.avx512.mask.pmov.dw.512(<16 x i32> %x0, <16 x i16> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i16> %res0, %res1
|
|
%res4 = add <16 x i16> %res3, %res2
|
|
ret <16 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmov.dw.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmov_dw_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmov_dw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovdw %zmm0, (%rdi)
|
|
; CHECK-NEXT: vpmovdw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmov.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmov.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32>, <16 x i16>, i16)
|
|
|
|
define <16 x i16>@test_int_x86_avx512_mask_pmovs_dw_512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_dw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsdw %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovsdw %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsdw %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
|
|
%res1 = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2)
|
|
%res2 = call <16 x i16> @llvm.x86.avx512.mask.pmovs.dw.512(<16 x i32> %x0, <16 x i16> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i16> %res0, %res1
|
|
%res4 = add <16 x i16> %res3, %res2
|
|
ret <16 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovs.dw.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovs_dw_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovs_dw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovsdw %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovsdw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovs.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmovs.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32>, <16 x i16>, i16)
|
|
|
|
define <16 x i16>@test_int_x86_avx512_mask_pmovus_dw_512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_dw_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovusdw %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vpmovusdw %zmm0, %ymm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovusdw %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: vpaddw %ymm2, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 -1)
|
|
%res1 = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> %x0, <16 x i16> %x1, i16 %x2)
|
|
%res2 = call <16 x i16> @llvm.x86.avx512.mask.pmovus.dw.512(<16 x i32> %x0, <16 x i16> zeroinitializer, i16 %x2)
|
|
%res3 = add <16 x i16> %res0, %res1
|
|
%res4 = add <16 x i16> %res3, %res2
|
|
ret <16 x i16> %res4
|
|
}
|
|
|
|
declare void @llvm.x86.avx512.mask.pmovus.dw.mem.512(i8* %ptr, <16 x i32>, i16)
|
|
|
|
define void @test_int_x86_avx512_mask_pmovus_dw_mem_512(i8* %ptr, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovus_dw_mem_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vpmovusdw %zmm0, (%rdi)
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpmovusdw %zmm0, (%rdi) {%k1}
|
|
; CHECK-NEXT: retq
|
|
call void @llvm.x86.avx512.mask.pmovus.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 -1)
|
|
call void @llvm.x86.avx512.mask.pmovus.dw.mem.512(i8* %ptr, <16 x i32> %x1, i16 %x2)
|
|
ret void
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.cvtdq2pd.512(<8 x i32>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_cvt_dq2pd_512(<8 x i32> %x0, <8 x double> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_dq2pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtdq2pd %ymm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.cvtdq2pd.512(<8 x i32> %x0, <8 x double> %x1, i8 %x2)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtdq2pd.512(<8 x i32> %x0, <8 x double> %x1, i8 -1)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32>, <16 x float>, i16, i32)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_cvt_dq2ps_512(<16 x i32> %x0, <16 x float> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_dq2ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtdq2ps %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtdq2ps {rn-sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 %x2, i32 4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 0)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double>, <8 x i32>, i8, i32)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_cvt_pd2dq_512(<8 x double> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_pd2dq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtpd2dq %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvtpd2dq {rn-sae}, %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 4)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 0)
|
|
%res2 = add <8 x i32> %res, %res1
|
|
ret <8 x i32> %res2
|
|
}
|
|
|
|
declare <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double>, <8 x float>, i8, i32)
|
|
|
|
define <8 x float>@test_int_x86_avx512_mask_cvt_pd2ps_512(<8 x double> %x0, <8 x float> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_pd2ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtpd2ps %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvtpd2ps {ru-sae}, %zmm0, %ymm0
|
|
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double> %x0, <8 x float> %x1, i8 %x2, i32 4)
|
|
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double> %x0, <8 x float> %x1, i8 -1, i32 2)
|
|
%res2 = fadd <8 x float> %res, %res1
|
|
ret <8 x float> %res2
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double>, <8 x i32>, i8, i32)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_cvt_pd2udq_512(<8 x double> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_pd2udq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtpd2udq {ru-sae}, %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvtpd2udq {rn-sae}, %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 2)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 0)
|
|
%res2 = add <8 x i32> %res, %res1
|
|
ret <8 x i32> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float>, <16 x i32>, i16, i32)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_cvt_ps2dq_512(<16 x float> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ps2dq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtps2dq {ru-sae}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtps2dq {rn-sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 0)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.cvtps2pd.512(<8 x float>, <8 x double>, i8, i32)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_cvt_ps2pd_512(<8 x float> %x0, <8 x double> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ps2pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtps2pd %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtps2pd {sae}, %ymm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.cvtps2pd.512(<8 x float> %x0, <8 x double> %x1, i8 %x2, i32 4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtps2pd.512(<8 x float> %x0, <8 x double> %x1, i8 -1, i32 8)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float>, <16 x i32>, i16, i32)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_cvt_ps2udq_512(<16 x float> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ps2udq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtps2udq {ru-sae}, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtps2udq {rn-sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 0)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.cvttpd2dq.512(<8 x double>, <8 x i32>, i8, i32)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_cvtt_pd2dq_512(<8 x double> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_pd2dq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvttpd2dq %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvttpd2dq {sae}, %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i32> @llvm.x86.avx512.mask.cvttpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 4)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvttpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 8)
|
|
%res2 = add <8 x i32> %res, %res1
|
|
ret <8 x i32> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.cvtudq2pd.512(<8 x i32>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_cvt_udq2pd_512(<8 x i32> %x0, <8 x double> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_udq2pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtudq2pd %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtudq2pd %ymm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.cvtudq2pd.512(<8 x i32> %x0, <8 x double> %x1, i8 %x2)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtudq2pd.512(<8 x i32> %x0, <8 x double> %x1, i8 -1)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32>, <16 x float>, i16, i32)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_cvt_udq2ps_512(<16 x i32> %x0, <16 x float> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_udq2ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtudq2ps %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvtudq2ps {rn-sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 %x2, i32 4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 0)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <8 x i32> @llvm.x86.avx512.mask.cvttpd2udq.512(<8 x double>, <8 x i32>, i8, i32)
|
|
|
|
define <8 x i32>@test_int_x86_avx512_mask_cvtt_pd2udq_512(<8 x double> %x0, <8 x i32> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_pd2udq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvttpd2udq %zmm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vcvttpd2udq {sae}, %zmm0, %ymm0
|
|
; CHECK-NEXT: vpaddd %ymm0, %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i32> @llvm.x86.avx512.mask.cvttpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 4)
|
|
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvttpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 8)
|
|
%res2 = add <8 x i32> %res, %res1
|
|
ret <8 x i32> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.cvttps2dq.512(<16 x float>, <16 x i32>, i16, i32)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_cvtt_ps2dq_512(<16 x float> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_ps2dq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvttps2dq %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvttps2dq {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.cvttps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvttps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 8)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.cvttps2udq.512(<16 x float>, <16 x i32>, i16, i32)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_cvtt_ps2udq_512(<16 x float> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_ps2udq_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvttps2udq %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vcvttps2udq {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.cvttps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvttps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 8)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.getexp.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
|
|
|
|
define <4 x float> @test_getexp_ss(<4 x float> %a0, <4 x float> %a1, <4 x float> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_getexp_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vgetexpss %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vgetexpss {sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vgetexpss {sae}, %xmm1, %xmm0, %xmm4 {%k1} {z}
|
|
; CHECK-NEXT: vgetexpss {sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm2, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <4 x float> @llvm.x86.avx512.mask.getexp.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.getexp.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 8)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask.getexp.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 8)
|
|
%res3 = call <4 x float> @llvm.x86.avx512.mask.getexp.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 8)
|
|
|
|
%res.1 = fadd <4 x float> %res0, %res1
|
|
%res.2 = fadd <4 x float> %res2, %res3
|
|
%res = fadd <4 x float> %res.1, %res.2
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.getexp.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
|
|
|
|
define <2 x double> @test_getexp_sd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2, i8 %mask) {
|
|
; CHECK-LABEL: test_getexp_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vgetexpsd %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vgetexpsd %xmm1, %xmm0, %xmm4
|
|
; CHECK-NEXT: vgetexpsd {sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vgetexpsd {sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: vaddpd %xmm2, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm4, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res0 = call <2 x double> @llvm.x86.avx512.mask.getexp.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.getexp.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 8)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask.getexp.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 8)
|
|
%res3 = call <2 x double> @llvm.x86.avx512.mask.getexp.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 4)
|
|
|
|
%res.1 = fadd <2 x double> %res0, %res1
|
|
%res.2 = fadd <2 x double> %res2, %res3
|
|
%res = fadd <2 x double> %res.1, %res.2
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double>, <2 x double>, i32, i8, i32)
|
|
|
|
define i8@test_int_x86_avx512_mask_cmp_sd(<2 x double> %x0, <2 x double> %x1, i8 %x3, i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cmp_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcmpnltsd {sae}, %xmm1, %xmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: andl $1, %eax
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
|
|
%res4 = call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %x0, <2 x double> %x1, i32 5, i8 %x3, i32 8)
|
|
ret i8 %res4
|
|
}
|
|
|
|
define i8@test_int_x86_avx512_mask_cmp_sd_all(<2 x double> %x0, <2 x double> %x1, i8 %x3, i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cmp_sd_all:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpunordsd {sae}, %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: vcmplesd %xmm1, %xmm0, %k1
|
|
; CHECK-NEXT: korw %k0, %k1, %k0
|
|
; CHECK-NEXT: vcmpnltsd {sae}, %xmm1, %xmm0, %k1
|
|
; CHECK-NEXT: vcmpneqsd %xmm1, %xmm0, %k2
|
|
; CHECK-NEXT: korw %k1, %k2, %k1
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k2
|
|
; CHECK-NEXT: kandw %k2, %k1, %k1
|
|
; CHECK-NEXT: korw %k1, %k0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: andl $1, %eax
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
|
|
%res1 = call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %x0, <2 x double> %x1, i32 2, i8 -1, i32 4)
|
|
%res2 = call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %x0, <2 x double> %x1, i32 3, i8 -1, i32 8)
|
|
%res3 = call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %x0, <2 x double> %x1, i32 4, i8 %x3, i32 4)
|
|
%res4 = call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %x0, <2 x double> %x1, i32 5, i8 %x3, i32 8)
|
|
|
|
%res11 = or i8 %res1, %res2
|
|
%res12 = or i8 %res3, %res4
|
|
%res13 = or i8 %res11, %res12
|
|
ret i8 %res13
|
|
}
|
|
|
|
declare i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float>, <4 x float>, i32, i8, i32)
|
|
|
|
define i8@test_int_x86_avx512_mask_cmp_ss(<4 x float> %x0, <4 x float> %x1, i8 %x3, i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cmp_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcmpunordss %xmm1, %xmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: andl $1, %eax
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
|
|
%res2 = call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %x0, <4 x float> %x1, i32 3, i8 %x3, i32 4)
|
|
ret i8 %res2
|
|
}
|
|
|
|
|
|
define i8@test_int_x86_avx512_mask_cmp_ss_all(<4 x float> %x0, <4 x float> %x1, i8 %x3, i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cmp_ss_all:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpless %xmm1, %xmm0, %k1
|
|
; CHECK-NEXT: vcmpunordss {sae}, %xmm1, %xmm0, %k0 {%k1}
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcmpneqss %xmm1, %xmm0, %k2 {%k1}
|
|
; CHECK-NEXT: kmovw %k2, %ecx
|
|
; CHECK-NEXT: vcmpnltss {sae}, %xmm1, %xmm0, %k1 {%k1}
|
|
; CHECK-NEXT: kmovw %k1, %edx
|
|
; CHECK-NEXT: andl $1, %edx
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: andb %cl, %al
|
|
; CHECK-NEXT: andb %dl, %al
|
|
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
%res1 = call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %x0, <4 x float> %x1, i32 2, i8 -1, i32 4)
|
|
%res2 = call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %x0, <4 x float> %x1, i32 3, i8 -1, i32 8)
|
|
%res3 = call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %x0, <4 x float> %x1, i32 4, i8 %x3, i32 4)
|
|
%res4 = call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %x0, <4 x float> %x1, i32 5, i8 %x3, i32 8)
|
|
|
|
%res11 = and i8 %res1, %res2
|
|
%res12 = and i8 %res3, %res4
|
|
%res13 = and i8 %res11, %res12
|
|
ret i8 %res13
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.shuf.f32x4(<16 x float>, <16 x float>, i32, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_shuf_f32x4(<16 x float> %x0, <16 x float> %x1, <16 x float> %x3, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_f32x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm2 {%k1} = zmm0[8,9,10,11,4,5,6,7],zmm1[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm0 = zmm0[8,9,10,11,4,5,6,7],zmm1[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.shuf.f32x4(<16 x float> %x0, <16 x float> %x1, i32 22, <16 x float> %x3, i16 %x4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.shuf.f32x4(<16 x float> %x0, <16 x float> %x1, i32 22, <16 x float> %x3, i16 -1)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.shuf.f64x2(<8 x double>, <8 x double>, i32, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_shuf_f64x2(<8 x double> %x0, <8 x double> %x1, <8 x double> %x3, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_f64x2:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm2 {%k1} = zmm0[4,5,2,3],zmm1[2,3,0,1]
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm3 {%k1} {z} = zmm0[4,5,2,3],zmm1[2,3,0,1]
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[4,5,2,3],zmm1[2,3,0,1]
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm3, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.shuf.f64x2(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> %x3, i8 %x4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.shuf.f64x2(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> %x3, i8 -1)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.shuf.f64x2(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> zeroinitializer, i8 %x4)
|
|
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res3, %res2
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.shuf.i32x4(<16 x i32>, <16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_shuf_i32x4(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x3, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_i32x4:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm2 {%k1} = zmm0[8,9,10,11,4,5,6,7],zmm1[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm0 = zmm0[8,9,10,11,4,5,6,7],zmm1[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.shuf.i32x4(<16 x i32> %x0, <16 x i32> %x1, i32 22, <16 x i32> %x3, i16 %x4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.shuf.i32x4(<16 x i32> %x0, <16 x i32> %x1, i32 22, <16 x i32> %x3, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.shuf.i64x2(<8 x i64>, <8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_shuf_i64x2(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x3, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_i64x2:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm2 {%k1} = zmm0[4,5,2,3],zmm1[2,3,0,1]
|
|
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[4,5,2,3],zmm1[2,3,0,1]
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.shuf.i64x2(<8 x i64> %x0, <8 x i64> %x1, i32 22, <8 x i64> %x3, i8 %x4)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.shuf.i64x2(<8 x i64> %x0, <8 x i64> %x1, i32 22, <8 x i64> %x3, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double>, i32, <8 x double>, i8, i32)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_getmant_pd_512(<8 x double> %x0, <8 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_getmant_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vgetmantpd $11, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vgetmantpd $11, {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double> %x0, i32 11, <8 x double> %x2, i8 %x3, i32 4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.getmant.pd.512(<8 x double> %x0, i32 11, <8 x double> %x2, i8 -1, i32 8)
|
|
%res2 = fadd <8 x double> %res, %res1
|
|
ret <8 x double> %res2
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float>, i32, <16 x float>, i16, i32)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_getmant_ps_512(<16 x float> %x0, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_getmant_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vgetmantps $11, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vgetmantps $11, {sae}, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float> %x0, i32 11, <16 x float> %x2, i16 %x3, i32 4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.getmant.ps.512(<16 x float> %x0, i32 11, <16 x float> %x2, i16 -1, i32 8)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double>, <2 x double>, i32, <2 x double>, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_getmant_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_getmant_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm3
|
|
; CHECK-NEXT: vgetmantsd $11, %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vgetmantsd $11, %xmm1, %xmm0, %xmm4 {%k1} {z}
|
|
; CHECK-NEXT: vgetmantsd $11, %xmm1, %xmm0, %xmm5
|
|
; CHECK-NEXT: vgetmantsd $11, {sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vaddpd %xmm4, %xmm3, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm5, %xmm2, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %x0, <2 x double> %x1, i32 11, <2 x double> %x2, i8 %x3, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %x0, <2 x double> %x1, i32 11, <2 x double> zeroinitializer, i8 %x3, i32 4)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %x0, <2 x double> %x1, i32 11, <2 x double> %x2, i8 %x3, i32 8)
|
|
%res3 = call <2 x double> @llvm.x86.avx512.mask.getmant.sd(<2 x double> %x0, <2 x double> %x1, i32 11, <2 x double> %x2, i8 -1, i32 4)
|
|
%res11 = fadd <2 x double> %res, %res1
|
|
%res12 = fadd <2 x double> %res2, %res3
|
|
%res13 = fadd <2 x double> %res11, %res12
|
|
ret <2 x double> %res13
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float>, <4 x float>, i32, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_getmant_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_getmant_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vgetmantss $11, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vgetmantss $11, %xmm1, %xmm0, %xmm3 {%k1} {z}
|
|
; CHECK-NEXT: vgetmantss $11, %xmm1, %xmm0, %xmm4
|
|
; CHECK-NEXT: vgetmantss $11, {sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm3, %xmm2, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm4, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %x0, <4 x float> %x1, i32 11, <4 x float> %x2, i8 %x3, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %x0, <4 x float> %x1, i32 11, <4 x float> zeroinitializer, i8 %x3, i32 4)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %x0, <4 x float> %x1, i32 11, <4 x float> %x2, i8 -1, i32 8)
|
|
%res3 = call <4 x float> @llvm.x86.avx512.mask.getmant.ss(<4 x float> %x0, <4 x float> %x1, i32 11, <4 x float> %x2, i8 -1, i32 4)
|
|
%res11 = fadd <4 x float> %res, %res1
|
|
%res12 = fadd <4 x float> %res2, %res3
|
|
%res13 = fadd <4 x float> %res11, %res12
|
|
ret <4 x float> %res13
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.shuf.pd.512(<8 x double>, <8 x double>, i32, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_shuf_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x3, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufpd {{.*#+}} zmm2 {%k1} = zmm0[0],zmm1[1],zmm0[3],zmm1[2],zmm0[5],zmm1[4],zmm0[6],zmm1[6]
|
|
; CHECK-NEXT: vshufpd {{.*#+}} zmm3 {%k1} {z} = zmm0[0],zmm1[1],zmm0[3],zmm1[2],zmm0[5],zmm1[4],zmm0[6],zmm1[6]
|
|
; CHECK-NEXT: vshufpd {{.*#+}} zmm0 = zmm0[0],zmm1[1],zmm0[3],zmm1[2],zmm0[5],zmm1[4],zmm0[6],zmm1[6]
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm3, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.shuf.pd.512(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> %x3, i8 %x4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.shuf.pd.512(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> %x3, i8 -1)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.shuf.pd.512(<8 x double> %x0, <8 x double> %x1, i32 22, <8 x double> zeroinitializer, i8 %x4)
|
|
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res3, %res2
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.shuf.ps.512(<16 x float>, <16 x float>, i32, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_shuf_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x3, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_shuf_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufps {{.*#+}} zmm2 {%k1} = zmm0[2,1],zmm1[1,0],zmm0[6,5],zmm1[5,4],zmm0[10,9],zmm1[9,8],zmm0[14,13],zmm1[13,12]
|
|
; CHECK-NEXT: vshufps {{.*#+}} zmm0 = zmm0[2,1],zmm1[1,0],zmm0[6,5],zmm1[5,4],zmm0[10,9],zmm1[9,8],zmm0[14,13],zmm1[13,12]
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.shuf.ps.512(<16 x float> %x0, <16 x float> %x1, i32 22, <16 x float> %x3, i16 %x4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.shuf.ps.512(<16 x float> %x0, <16 x float> %x1, i32 22, <16 x float> %x3, i16 -1)
|
|
%res2 = fadd <16 x float> %res, %res1
|
|
ret <16 x float> %res2
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.vpermilvar.pd.512(<8 x double>, <8 x i64>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_vpermilvar_pd_512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermilvar_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilpd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermilpd %zmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermilpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.vpermilvar.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.vpermilvar.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.vpermilvar.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 -1)
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res2, %res3
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.vpermilvar.ps.512(<16 x float>, <16 x i32>, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_vpermilvar_ps_512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vpermilvar_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilps %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermilps %zmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermilps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.vpermilvar.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.vpermilvar.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.mask.vpermilvar.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 -1)
|
|
%res3 = fadd <16 x float> %res, %res1
|
|
%res4 = fadd <16 x float> %res2, %res3
|
|
ret <16 x float> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.insertf32x4.512(<16 x float>, <4 x float>, i32, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_insertf32x4_512(<16 x float> %x0, <4 x float> %x1, <16 x float> %x3, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_insertf32x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vinsertf32x4 $1, %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vinsertf32x4 $1, %xmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vinsertf32x4 $1, %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.insertf32x4.512(<16 x float> %x0, <4 x float> %x1, i32 1, <16 x float> %x3, i16 %x4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.insertf32x4.512(<16 x float> %x0, <4 x float> %x1, i32 1, <16 x float> %x3, i16 -1)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.mask.insertf32x4.512(<16 x float> %x0, <4 x float> %x1, i32 1, <16 x float> zeroinitializer, i16 %x4)
|
|
%res3 = fadd <16 x float> %res, %res1
|
|
%res4 = fadd <16 x float> %res2, %res3
|
|
ret <16 x float> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.inserti32x4.512(<16 x i32>, <4 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_inserti32x4_512(<16 x i32> %x0, <4 x i32> %x1, <16 x i32> %x3, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_inserti32x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vinserti32x4 $1, %xmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vinserti32x4 $1, %xmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vinserti32x4 $1, %xmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.inserti32x4.512(<16 x i32> %x0, <4 x i32> %x1, i32 1, <16 x i32> %x3, i16 %x4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.inserti32x4.512(<16 x i32> %x0, <4 x i32> %x1, i32 1, <16 x i32> %x3, i16 -1)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.inserti32x4.512(<16 x i32> %x0, <4 x i32> %x1, i32 1, <16 x i32> zeroinitializer, i16 %x4)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res2, %res3
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.insertf64x4.512(<8 x double>, <4 x double>, i32, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_insertf64x4_512(<8 x double> %x0, <4 x double> %x1, <8 x double> %x3, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_insertf64x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.insertf64x4.512(<8 x double> %x0, <4 x double> %x1, i32 1, <8 x double> %x3, i8 %x4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.insertf64x4.512(<8 x double> %x0, <4 x double> %x1, i32 1, <8 x double> %x3, i8 -1)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.insertf64x4.512(<8 x double> %x0, <4 x double> %x1, i32 1, <8 x double> zeroinitializer, i8 %x4)
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res2, %res3
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.inserti64x4.512(<8 x i64>, <4 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_inserti64x4_512(<8 x i64> %x0, <4 x i64> %x1, <8 x i64> %x3, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_inserti64x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.inserti64x4.512(<8 x i64> %x0, <4 x i64> %x1, i32 1, <8 x i64> %x3, i8 %x4)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.inserti64x4.512(<8 x i64> %x0, <4 x i64> %x1, i32 1, <8 x i64> %x3, i8 -1)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.inserti64x4.512(<8 x i64> %x0, <4 x i64> %x1, i32 1, <8 x i64> zeroinitializer, i8 %x4)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res2, %res3
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.cvtss2sd.round(<2 x double>, <4 x float>, <2 x double>, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_cvt_ss2sd_round(<2 x double> %x0,<4 x float> %x1, <2 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ss2sd_round:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtss2sd %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vcvtss2sd {sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.cvtss2sd.round(<2 x double> %x0, <4 x float> %x1, <2 x double> %x2, i8 %x3, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.cvtss2sd.round(<2 x double> %x0, <4 x float> %x1, <2 x double> %x2, i8 -1, i32 8)
|
|
%res2 = fadd <2 x double> %res, %res1
|
|
ret <2 x double> %res2
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float>, <2 x double>, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_cvt_sd2ss_round(<4 x float> %x0,<2 x double> %x1, <4 x float> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_sd2ss_round:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vcvtsd2ss {rz-sae}, %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vcvtsd2ss {rn-sae}, %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float> %x0, <2 x double> %x1, <4 x float> %x2, i8 %x3, i32 3)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float> %x0, <2 x double> %x1, <4 x float> %x2, i8 -1, i32 8)
|
|
%res2 = fadd <4 x float> %res, %res1
|
|
ret <4 x float> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pternlog.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i32, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pternlog_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pternlog_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm0, %zmm3
|
|
; CHECK-NEXT: vpternlogd $33, %zmm2, %zmm1, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpternlogd $33, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pternlog.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i32 33, i16 %x4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pternlog.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i32 33, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.maskz.pternlog.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i32, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_maskz_pternlog_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_pternlog_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm0, %zmm3
|
|
; CHECK-NEXT: vpternlogd $33, %zmm2, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpternlogd $33, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.maskz.pternlog.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i32 33, i16 %x4)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.maskz.pternlog.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i32 33, i16 -1)
|
|
%res2 = add <16 x i32> %res, %res1
|
|
ret <16 x i32> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pternlog.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i32, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pternlog_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pternlog_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm0, %zmm3
|
|
; CHECK-NEXT: vpternlogq $33, %zmm2, %zmm1, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpternlogq $33, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pternlog.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i32 33, i8 %x4)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pternlog.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i32 33, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.maskz.pternlog.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i32, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_maskz_pternlog_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_pternlog_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovdqa64 %zmm0, %zmm3
|
|
; CHECK-NEXT: vpternlogq $33, %zmm2, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpternlogq $33, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.maskz.pternlog.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i32 33, i8 %x4)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.maskz.pternlog.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i32 33, i8 -1)
|
|
%res2 = add <8 x i64> %res, %res1
|
|
ret <8 x i64> %res2
|
|
}
|
|
|
|
define i32 @test_x86_avx512_comi_sd_eq_sae(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_comi_sd_eq_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpeqsd {sae}, %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 0, i32 8)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_ucomi_sd_eq_sae(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_ucomi_sd_eq_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpeq_uqsd {sae}, %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 8, i32 8)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_comi_sd_eq(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_comi_sd_eq:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpeqsd %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 0, i32 4)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_ucomi_sd_eq(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_ucomi_sd_eq:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpeq_uqsd %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 8, i32 4)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_comi_sd_lt_sae(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_comi_sd_lt_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpltsd {sae}, %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 1, i32 8)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_ucomi_sd_lt_sae(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_ucomi_sd_lt_sae:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpngesd {sae}, %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 9, i32 8)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_comi_sd_lt(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_comi_sd_lt:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpltsd %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 1, i32 4)
|
|
ret i32 %res
|
|
}
|
|
|
|
define i32 @test_x86_avx512_ucomi_sd_lt(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_ucomi_sd_lt:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpngesd %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %a0, <2 x double> %a1, i32 9, i32 4)
|
|
ret i32 %res
|
|
}
|
|
|
|
declare i32 @llvm.x86.avx512.vcomi.sd(<2 x double>, <2 x double>, i32, i32)
|
|
|
|
define i32 @test_x86_avx512_ucomi_ss_lt(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: test_x86_avx512_ucomi_ss_lt:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vcmpngess %xmm1, %xmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: retq
|
|
%res = call i32 @llvm.x86.avx512.vcomi.ss(<4 x float> %a0, <4 x float> %a1, i32 9, i32 4)
|
|
ret i32 %res
|
|
}
|
|
|
|
declare i32 @llvm.x86.avx512.vcomi.ss(<4 x float>, <4 x float>, i32, i32)
|
|
declare <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float>, <4 x float>, <4 x float>, i8)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_move_ss_rrk(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_ss_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovss %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_move_ss_rrkz(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_ss_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovss %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> zeroinitializer, i8 %x2)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_move_ss_rr(<4 x float> %x0, <4 x float> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_ss_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.move.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> zeroinitializer, i8 -1)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double>, <2 x double>, <2 x double>, i8)
|
|
define <2 x double>@test_int_x86_avx512_mask_move_sd_rr(<2 x double> %x0, <2 x double> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_sd_rr:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> zeroinitializer, i8 -1)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_move_sd_rrkz(<2 x double> %x0, <2 x double> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_sd_rrkz:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovsd %xmm1, %xmm0, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> zeroinitializer, i8 %x2)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_move_sd_rrk(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_move_sd_rrk:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovsd %xmm1, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.move.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3)
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.broadcastf32x4.512(<4 x float>, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_broadcastf32x4_512(<4 x float> %x0, <16 x float> %x2, i16 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf32x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm0 = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x4.512(<4 x float> %x0, <16 x float> %x2, i16 -1)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x4.512(<4 x float> %x0, <16 x float> %x2, i16 %mask)
|
|
%res3 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x4.512(<4 x float> %x0, <16 x float> zeroinitializer, i16 %mask)
|
|
%res4 = fadd <16 x float> %res1, %res2
|
|
%res5 = fadd <16 x float> %res3, %res4
|
|
ret <16 x float> %res5
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.broadcastf64x4.512(<4 x double>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_broadcastf64x4_512(<4 x double> %x0, <8 x double> %x2, i8 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf64x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: ## kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x4.512(<4 x double> %x0, <8 x double> %x2, i8 -1)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x4.512(<4 x double> %x0, <8 x double> %x2, i8 %mask)
|
|
%res3 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x4.512(<4 x double> %x0, <8 x double> zeroinitializer, i8 %mask)
|
|
%res4 = fadd <8 x double> %res1, %res2
|
|
%res5 = fadd <8 x double> %res3, %res4
|
|
ret <8 x double> %res5
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.broadcasti32x4.512(<4 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_broadcasti32x4_512(<4 x i32> %x0, <16 x i32> %x2, i16 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti32x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm0 = zmm0[0,1,2,3,0,1,2,3,0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x4.512(<4 x i32> %x0, <16 x i32> %x2, i16 -1)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x4.512(<4 x i32> %x0, <16 x i32> %x2, i16 %mask)
|
|
%res3 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x4.512(<4 x i32> %x0, <16 x i32> zeroinitializer, i16 %mask)
|
|
%res4 = add <16 x i32> %res1, %res2
|
|
%res5 = add <16 x i32> %res3, %res4
|
|
ret <16 x i32> %res5
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.broadcasti64x4.512(<4 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_broadcasti64x4_512(<4 x i64> %x0, <8 x i64> %x2, i8 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti64x4_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: ## kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,2,3,0,1,2,3]
|
|
; CHECK-NEXT: vpaddq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x4.512(<4 x i64> %x0, <8 x i64> %x2, i8 -1)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x4.512(<4 x i64> %x0, <8 x i64> %x2, i8 %mask)
|
|
%res3 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x4.512(<4 x i64> %x0, <8 x i64> zeroinitializer, i8 %mask)
|
|
%res4 = add <8 x i64> %res1, %res2
|
|
%res5 = add <8 x i64> %res3, %res4
|
|
ret <8 x i64> %res5
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_psrl_qi_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psrl_qi_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpsrlq $255, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i32 255, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i32 255, <8 x i64> %x2, i8 -1)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.psrl.qi.512(<8 x i64> %x0, i32 255, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_psrl_di_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psrl_di_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsrld $255, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpsrld $255, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpsrld $255, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> %x2, i16 -1)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.psrl.di.512(<16 x i32> %x0, i32 255, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_psra_di_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psra_di_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsrad $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpsrad $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpsrad $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i32 3, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.psra.di.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_psra_qi_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psra_qi_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsraq $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpsraq $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpsraq $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i32 3, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.psra.qi.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_psll_di_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psll_di_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpslld $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpslld $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpslld $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i32 3, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.psll.di.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_psll_qi_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_psll_qi_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpsllq $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpsllq $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpsllq $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i32 3, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.psll.qi.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.prorv.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_prorv_d_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_prorv_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vprorvd %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vprorvd %zmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vprorvd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.prorv.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.prorv.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.prorv.d.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.prorv.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_prorv_q_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_prorv_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vprorvq %zmm1, %zmm0, %zmm2 {%k1}
|
|
; CHECK-NEXT: vprorvq %zmm1, %zmm0, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vprorvq %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.prorv.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.prorv.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.prorv.q.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32>, i32, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_prol_d_512(<16 x i32> %x0, i32 %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_prol_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vprold $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vprold $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vprold $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.prol.d.512(<16 x i32> %x0, i32 3, <16 x i32> %x2, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64>, i32, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_prol_q_512(<8 x i64> %x0, i32 %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_prol_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vprolq $3, %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vprolq $3, %zmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vprolq $3, %zmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.prol.q.512(<8 x i64> %x0, i32 3, <8 x i64> %x2, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmovzxb.d.512(<16 x i8>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmovzxb_d_512(<16 x i8> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovzxb_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovzxbd {{.*#+}} zmm1 {%k1} = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxbd {{.*#+}} zmm2 {%k1} {z} = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmovzxb.d.512(<16 x i8> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmovzxb.d.512(<16 x i8> %x0, <16 x i32> zeroinitializer, i16 %x2)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.pmovzxb.d.512(<16 x i8> %x0, <16 x i32> %x1, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovzxb.q.512(<16 x i8>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovzxb_q_512(<16 x i8> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovzxb_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovzxbq {{.*#+}} zmm1 {%k1} = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,xmm0[4],zero,zero,zero,zero,zero,zero,zero,xmm0[5],zero,zero,zero,zero,zero,zero,zero,xmm0[6],zero,zero,zero,zero,zero,zero,zero,xmm0[7],zero,zero,zero,zero,zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxbq {{.*#+}} zmm2 {%k1} {z} = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,xmm0[4],zero,zero,zero,zero,zero,zero,zero,xmm0[5],zero,zero,zero,zero,zero,zero,zero,xmm0[6],zero,zero,zero,zero,zero,zero,zero,xmm0[7],zero,zero,zero,zero,zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxbq {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,xmm0[4],zero,zero,zero,zero,zero,zero,zero,xmm0[5],zero,zero,zero,zero,zero,zero,zero,xmm0[6],zero,zero,zero,zero,zero,zero,zero,xmm0[7],zero,zero,zero,zero,zero,zero,zero
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovzxb.q.512(<16 x i8> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxb.q.512(<16 x i8> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxb.q.512(<16 x i8> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovzxd.q.512(<8 x i32>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovzxd_q_512(<8 x i32> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovzxd_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovzxdq {{.*#+}} zmm1 {%k1} = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
|
|
; CHECK-NEXT: vpmovzxdq {{.*#+}} zmm2 {%k1} {z} = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
|
|
; CHECK-NEXT: vpmovzxdq {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovzxd.q.512(<8 x i32> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxd.q.512(<8 x i32> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxd.q.512(<8 x i32> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmovzxw.d.512(<16 x i16>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmovzxw_d_512(<16 x i16> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovzxw_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovzxwd {{.*#+}} zmm1 {%k1} = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; CHECK-NEXT: vpmovzxwd {{.*#+}} zmm2 {%k1} {z} = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; CHECK-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmovzxw.d.512(<16 x i16> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmovzxw.d.512(<16 x i16> %x0, <16 x i32> zeroinitializer, i16 %x2)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.pmovzxw.d.512(<16 x i16> %x0, <16 x i32> %x1, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovzxw.q.512(<8 x i16>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovzxw_q_512(<8 x i16> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovzxw_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovzxwq {{.*#+}} zmm1 {%k1} = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxwq {{.*#+}} zmm2 {%k1} {z} = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
|
|
; CHECK-NEXT: vpmovzxwq {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovzxw.q.512(<8 x i16> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxw.q.512(<8 x i16> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovzxw.q.512(<8 x i16> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmovsxb.d.512(<16 x i8>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmovsxb_d_512(<16 x i8> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovsxb_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsxbd %xmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsxbd %xmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsxbd %xmm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmovsxb.d.512(<16 x i8> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmovsxb.d.512(<16 x i8> %x0, <16 x i32> zeroinitializer, i16 %x2)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.pmovsxb.d.512(<16 x i8> %x0, <16 x i32> %x1, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovsxb.q.512(<16 x i8>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovsxb_q_512(<16 x i8> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovsxb_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsxbq %xmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsxbq %xmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsxbq %xmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovsxb.q.512(<16 x i8> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxb.q.512(<16 x i8> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxb.q.512(<16 x i8> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovsxd.q.512(<8 x i32>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovsxd_q_512(<8 x i32> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovsxd_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsxdq %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsxdq %ymm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsxdq %ymm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovsxd.q.512(<8 x i32> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxd.q.512(<8 x i32> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxd.q.512(<8 x i32> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pmovsxw.d.512(<16 x i16>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pmovsxw_d_512(<16 x i16> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovsxw_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsxwd %ymm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsxwd %ymm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsxwd %ymm0, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pmovsxw.d.512(<16 x i16> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pmovsxw.d.512(<16 x i16> %x0, <16 x i32> zeroinitializer, i16 %x2)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.pmovsxw.d.512(<16 x i16> %x0, <16 x i32> %x1, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pmovsxw.q.512(<8 x i16>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pmovsxw_q_512(<8 x i16> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pmovsxw_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpmovsxwq %xmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vpmovsxwq %xmm0, %zmm2 {%k1} {z}
|
|
; CHECK-NEXT: vpmovsxwq %xmm0, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm2, %zmm1, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pmovsxw.q.512(<8 x i16> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxw.q.512(<8 x i16> %x0, <8 x i64> zeroinitializer, i8 %x2)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pmovsxw.q.512(<8 x i16> %x0, <8 x i64> %x1, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double>, <8 x i64>, <8 x double>, i8)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_permvar_df_512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_df_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermpd %zmm0, %zmm1, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermpd %zmm0, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 %x3)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2, i8 -1)
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res3, %res2
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_permvar_di_512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_di_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermq %zmm0, %zmm1, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermq %zmm0, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 %x3)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> zeroinitializer, i8 %x3)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i64> %x2, i8 -1)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res3, %res2
|
|
ret <8 x i64> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float>, <16 x i32>, <16 x float>, i16)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_permvar_sf_512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_sf_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 %x3)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2, i16 -1)
|
|
%res3 = fadd <16 x float> %res, %res1
|
|
%res4 = fadd <16 x float> %res3, %res2
|
|
ret <16 x float> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_permvar_si_512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_permvar_si_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermd %zmm0, %zmm1, %zmm2 {%k1}
|
|
; CHECK-NEXT: vpermd %zmm0, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpermd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm3, %zmm2, %zmm1
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 %x3)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> zeroinitializer, i16 %x3)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %x0, <16 x i32> %x1, <16 x i32> %x2, i16 -1)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res3, %res2
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.fixupimm.pd.512(<8 x double>, <8 x double>, <8 x i64>, i32, i8, i32)
|
|
|
|
define <8 x double>@test_int_x86_avx512_mask_fixupimm_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_fixupimm_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmpd $4, %zmm2, %zmm1, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpxord %zmm4, %zmm4, %zmm4
|
|
; CHECK-NEXT: vfixupimmpd $5, %zmm2, %zmm1, %zmm4 {%k1} {z}
|
|
; CHECK-NEXT: vfixupimmpd $3, {sae}, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm4, %zmm3, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.mask.fixupimm.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i32 4, i8 %x4, i32 4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.mask.fixupimm.pd.512(<8 x double> zeroinitializer, <8 x double> %x1, <8 x i64> %x2, i32 5, i8 %x4, i32 4)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.mask.fixupimm.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i32 3, i8 -1, i32 8)
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res3, %res2
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.maskz.fixupimm.pd.512(<8 x double>, <8 x double>, <8 x i64>, i32, i8, i32)
|
|
|
|
define <8 x double>@test_int_x86_avx512_maskz_fixupimm_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_fixupimm_pd_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmpd $3, %zmm2, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vpxord %zmm4, %zmm4, %zmm4
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm5
|
|
; CHECK-NEXT: vfixupimmpd $5, %zmm4, %zmm1, %zmm5 {%k1} {z}
|
|
; CHECK-NEXT: vfixupimmpd $2, {sae}, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vaddpd %zmm5, %zmm3, %zmm1
|
|
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x double> @llvm.x86.avx512.maskz.fixupimm.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i32 3, i8 %x4, i32 4)
|
|
%res1 = call <8 x double> @llvm.x86.avx512.maskz.fixupimm.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x i64> zeroinitializer, i32 5, i8 %x4, i32 4)
|
|
%res2 = call <8 x double> @llvm.x86.avx512.maskz.fixupimm.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x i64> %x2, i32 2, i8 -1, i32 8)
|
|
%res3 = fadd <8 x double> %res, %res1
|
|
%res4 = fadd <8 x double> %res3, %res2
|
|
ret <8 x double> %res4
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.fixupimm.ss(<4 x float>, <4 x float>, <4 x i32>, i32, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_fixupimm_ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_fixupimm_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmss $5, %xmm2, %xmm1, %xmm3 {%k1}
|
|
; CHECK-NEXT: vxorps %xmm4, %xmm4, %xmm4
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm5
|
|
; CHECK-NEXT: vfixupimmss $5, %xmm4, %xmm1, %xmm5 {%k1}
|
|
; CHECK-NEXT: vfixupimmss $5, {sae}, %xmm2, %xmm1, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm5, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i32 5, i8 %x4, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> zeroinitializer, i32 5, i8 %x4, i32 4)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i32 5, i8 -1, i32 8)
|
|
%res3 = fadd <4 x float> %res, %res1
|
|
%res4 = fadd <4 x float> %res3, %res2
|
|
ret <4 x float> %res4
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.maskz.fixupimm.ss(<4 x float>, <4 x float>, <4 x i32>, i32, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_maskz_fixupimm_ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_fixupimm_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmss $5, %xmm2, %xmm1, %xmm3 {%k1} {z}
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm4
|
|
; CHECK-NEXT: vfixupimmss $5, %xmm2, %xmm1, %xmm4
|
|
; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
|
; CHECK-NEXT: vfixupimmss $5, {sae}, %xmm2, %xmm1, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: vaddps %xmm0, %xmm3, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm4, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i32 5, i8 %x4, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.maskz.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> zeroinitializer, i32 5, i8 %x4, i32 8)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.maskz.fixupimm.ss(<4 x float> %x0, <4 x float> %x1, <4 x i32> %x2, i32 5, i8 -1, i32 4)
|
|
%res3 = fadd <4 x float> %res, %res1
|
|
%res4 = fadd <4 x float> %res3, %res2
|
|
ret <4 x float> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.fixupimm.ps.512(<16 x float>, <16 x float>, <16 x i32>, i32, i16, i32)
|
|
|
|
define <16 x float>@test_int_x86_avx512_mask_fixupimm_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_fixupimm_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmps $5, %zmm2, %zmm1, %zmm3 {%k1}
|
|
; CHECK-NEXT: vpxord %zmm4, %zmm4, %zmm4
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm5
|
|
; CHECK-NEXT: vfixupimmps $5, %zmm4, %zmm1, %zmm5 {%k1}
|
|
; CHECK-NEXT: vfixupimmps $5, {sae}, %zmm2, %zmm1, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm5, %zmm3, %zmm1
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.mask.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i32 5, i16 %x4, i32 4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.mask.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> zeroinitializer, i32 5, i16 %x4, i32 4)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.mask.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i32 5, i16 -1, i32 8)
|
|
%res3 = fadd <16 x float> %res, %res1
|
|
%res4 = fadd <16 x float> %res3, %res2
|
|
ret <16 x float> %res4
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.maskz.fixupimm.ps.512(<16 x float>, <16 x float>, <16 x i32>, i32, i16, i32)
|
|
|
|
define <16 x float>@test_int_x86_avx512_maskz_fixupimm_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i16 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_fixupimm_ps_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmps $5, %zmm2, %zmm1, %zmm3 {%k1} {z}
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm4
|
|
; CHECK-NEXT: vfixupimmps $5, %zmm2, %zmm1, %zmm4
|
|
; CHECK-NEXT: vpxord %zmm2, %zmm2, %zmm2
|
|
; CHECK-NEXT: vfixupimmps $5, {sae}, %zmm2, %zmm1, %zmm0 {%k1} {z}
|
|
; CHECK-NEXT: vaddps %zmm0, %zmm3, %zmm0
|
|
; CHECK-NEXT: vaddps %zmm4, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x float> @llvm.x86.avx512.maskz.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i32 5, i16 %x4, i32 4)
|
|
%res1 = call <16 x float> @llvm.x86.avx512.maskz.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> zeroinitializer, i32 5, i16 %x4, i32 8)
|
|
%res2 = call <16 x float> @llvm.x86.avx512.maskz.fixupimm.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x i32> %x2, i32 5, i16 -1, i32 4)
|
|
%res3 = fadd <16 x float> %res, %res1
|
|
%res4 = fadd <16 x float> %res3, %res2
|
|
ret <16 x float> %res4
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.fixupimm.sd(<2 x double>, <2 x double>, <2 x i64>, i32, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_fixupimm_sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_fixupimm_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmsd $5, %xmm2, %xmm1, %xmm3 {%k1}
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm4
|
|
; CHECK-NEXT: vfixupimmsd $5, %xmm2, %xmm1, %xmm4
|
|
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
|
|
; CHECK-NEXT: vfixupimmsd $5, {sae}, %xmm2, %xmm1, %xmm0 {%k1}
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm3, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm4, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i32 5, i8 %x4, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> zeroinitializer, i32 5, i8 %x4, i32 8)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i32 5, i8 -1, i32 4)
|
|
%res3 = fadd <2 x double> %res, %res1
|
|
%res4 = fadd <2 x double> %res3, %res2
|
|
ret <2 x double> %res4
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.maskz.fixupimm.sd(<2 x double>, <2 x double>, <2 x i64>, i32, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_maskz_fixupimm_sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i8 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_fixupimm_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm3
|
|
; CHECK-NEXT: vfixupimmsd $5, %xmm2, %xmm1, %xmm3 {%k1} {z}
|
|
; CHECK-NEXT: vxorpd %xmm4, %xmm4, %xmm4
|
|
; CHECK-NEXT: vmovapd %zmm0, %zmm5
|
|
; CHECK-NEXT: vfixupimmsd $5, {sae}, %xmm4, %xmm1, %xmm5 {%k1} {z}
|
|
; CHECK-NEXT: vfixupimmsd $5, {sae}, %xmm2, %xmm1, %xmm0 {%k1} {z}
|
|
; CHECK-NEXT: vaddpd %xmm5, %xmm3, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.maskz.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i32 5, i8 %x4, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.maskz.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> zeroinitializer, i32 5, i8 %x4, i32 8)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.maskz.fixupimm.sd(<2 x double> %x0, <2 x double> %x1, <2 x i64> %x2, i32 5, i8 %x4, i32 8)
|
|
%res3 = fadd <2 x double> %res, %res1
|
|
%res4 = fadd <2 x double> %res3, %res2
|
|
ret <2 x double> %res4
|
|
}
|
|
|
|
declare i16 @llvm.x86.avx512.ptestnm.d.512(<16 x i32>, <16 x i32>, i16 %x2)
|
|
|
|
define i16@test_int_x86_avx512_ptestnm_d_512(<16 x i32> %x0, <16 x i32> %x1, i16 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_ptestnm_d_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vptestnmd %zmm1, %zmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %ecx
|
|
; CHECK-NEXT: vptestnmd %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: addl %ecx, %eax
|
|
; CHECK-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
|
|
; CHECK-NEXT: retq
|
|
%res = call i16 @llvm.x86.avx512.ptestnm.d.512(<16 x i32> %x0, <16 x i32> %x1, i16 %x2)
|
|
%res1 = call i16 @llvm.x86.avx512.ptestnm.d.512(<16 x i32> %x0, <16 x i32> %x1, i16-1)
|
|
%res2 = add i16 %res, %res1
|
|
ret i16 %res2
|
|
}
|
|
|
|
declare i8 @llvm.x86.avx512.ptestnm.q.512(<8 x i64>, <8 x i64>, i8 %x2)
|
|
|
|
define i8@test_int_x86_avx512_ptestnm_q_512(<8 x i64> %x0, <8 x i64> %x1, i8 %x2) {
|
|
; CHECK-LABEL: test_int_x86_avx512_ptestnm_q_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vptestnmq %zmm1, %zmm0, %k0 {%k1}
|
|
; CHECK-NEXT: kmovw %k0, %ecx
|
|
; CHECK-NEXT: vptestnmq %zmm1, %zmm0, %k0
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: addb %cl, %al
|
|
; CHECK-NEXT: retq
|
|
%res = call i8 @llvm.x86.avx512.ptestnm.q.512(<8 x i64> %x0, <8 x i64> %x1, i8 %x2)
|
|
%res1 = call i8 @llvm.x86.avx512.ptestnm.q.512(<8 x i64> %x0, <8 x i64> %x1, i8-1)
|
|
%res2 = add i8 %res, %res1
|
|
ret i8 %res2
|
|
}
|
|
|
|
define <16 x i32>@test_int_x86_avx512_mask_pbroadcastd_gpr_512(i32 %x0, <16 x i32> %x1, i16 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pbroadcastd_gpr_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpbroadcastd %edi, %zmm0 {%k1}
|
|
; CHECK-NEXT: vpbroadcastd %edi, %zmm1 {%k1} {z}
|
|
; CHECK-NEXT: vpbroadcastd %edi, %zmm2
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <16 x i32> @llvm.x86.avx512.mask.pbroadcast.d.gpr.512(i32 %x0, <16 x i32> %x1, i16 -1)
|
|
%res1 = call <16 x i32> @llvm.x86.avx512.mask.pbroadcast.d.gpr.512(i32 %x0, <16 x i32> %x1, i16 %mask)
|
|
%res2 = call <16 x i32> @llvm.x86.avx512.mask.pbroadcast.d.gpr.512(i32 %x0, <16 x i32> zeroinitializer, i16 %mask)
|
|
%res3 = add <16 x i32> %res, %res1
|
|
%res4 = add <16 x i32> %res2, %res3
|
|
ret <16 x i32> %res4
|
|
}
|
|
|
|
declare <16 x i32> @llvm.x86.avx512.mask.pbroadcast.d.gpr.512(i32, <16 x i32>, i16)
|
|
|
|
define <8 x i64>@test_int_x86_avx512_mask_pbroadcastq_gpr_512(i64 %x0, <8 x i64> %x1, i8 %mask) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_pbroadcastq_gpr_512:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpbroadcastq %rdi, %zmm0 {%k1}
|
|
; CHECK-NEXT: vpbroadcastq %rdi, %zmm1 {%k1} {z}
|
|
; CHECK-NEXT: vpbroadcastq %rdi, %zmm2
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
|
|
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <8 x i64> @llvm.x86.avx512.mask.pbroadcast.q.gpr.512(i64 %x0, <8 x i64> %x1,i8 -1)
|
|
%res1 = call <8 x i64> @llvm.x86.avx512.mask.pbroadcast.q.gpr.512(i64 %x0, <8 x i64> %x1,i8 %mask)
|
|
%res2 = call <8 x i64> @llvm.x86.avx512.mask.pbroadcast.q.gpr.512(i64 %x0, <8 x i64> zeroinitializer,i8 %mask)
|
|
%res3 = add <8 x i64> %res, %res1
|
|
%res4 = add <8 x i64> %res2, %res3
|
|
ret <8 x i64> %res4
|
|
}
|
|
declare <8 x i64> @llvm.x86.avx512.mask.pbroadcast.q.gpr.512(i64, <8 x i64>, i8)
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask_vfmadd_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vfmadd_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfmadd132sd %xmm1, %xmm2, %xmm3 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm4
|
|
; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm4
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm5
|
|
; CHECK-NEXT: vfmadd132sd {rz-sae}, %xmm1, %xmm2, %xmm5 {%k1}
|
|
; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
|
|
%res3 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
|
|
%res4 = fadd <2 x double> %res, %res1
|
|
%res5 = fadd <2 x double> %res2, %res3
|
|
%res6 = fadd <2 x double> %res4, %res5
|
|
ret <2 x double> %res6
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_vfmadd_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vfmadd_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm3
|
|
; CHECK-NEXT: vfmadd132ss %xmm1, %xmm2, %xmm3 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm4
|
|
; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm4
|
|
; CHECK-NEXT: vmovaps %zmm0, %zmm5
|
|
; CHECK-NEXT: vfmadd132ss {rz-sae}, %xmm1, %xmm2, %xmm5 {%k1}
|
|
; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm0, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
|
|
%res3 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
|
|
%res4 = fadd <4 x float> %res, %res1
|
|
%res5 = fadd <4 x float> %res2, %res3
|
|
%res6 = fadd <4 x float> %res4, %res5
|
|
ret <4 x float> %res6
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_maskz_vfmadd_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm3
|
|
; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm3 {%k1} {z}
|
|
; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; CHECK-NEXT: vaddpd %xmm1, %xmm3, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
|
|
%res2 = fadd <2 x double> %res, %res1
|
|
ret <2 x double> %res2
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
|
|
%res2 = fadd <4 x float> %res, %res1
|
|
ret <4 x float> %res
|
|
}
|
|
declare <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)
|
|
|
|
define <2 x double>@test_int_x86_avx512_mask3_vfmadd_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_sd:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vfmadd231sd %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm4
|
|
; CHECK-NEXT: vfmadd213sd %xmm2, %xmm0, %xmm4
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm5
|
|
; CHECK-NEXT: vfmadd231sd {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
|
|
; CHECK-NEXT: vfmadd213sd {rz-sae}, %xmm2, %xmm0, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm3, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddpd %xmm5, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
|
|
%res1 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
|
|
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
|
|
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
|
|
%res4 = fadd <2 x double> %res, %res1
|
|
%res5 = fadd <2 x double> %res2, %res3
|
|
%res6 = fadd <2 x double> %res4, %res5
|
|
ret <2 x double> %res6
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3,i32 %x4 ){
|
|
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ss:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %edi
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm3
|
|
; CHECK-NEXT: vfmadd231ss %xmm1, %xmm0, %xmm3 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm4
|
|
; CHECK-NEXT: vfmadd213ss %xmm2, %xmm0, %xmm4
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm5
|
|
; CHECK-NEXT: vfmadd231ss {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
|
|
; CHECK-NEXT: vfmadd213ss {rz-sae}, %xmm2, %xmm0, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm3, %xmm4, %xmm0
|
|
; CHECK-NEXT: vaddps %xmm5, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
|
|
%res1 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
|
|
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
|
|
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
|
|
%res4 = fadd <4 x float> %res, %res1
|
|
%res5 = fadd <4 x float> %res2, %res3
|
|
%res6 = fadd <4 x float> %res4, %res5
|
|
ret <4 x float> %res6
|
|
}
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss_rm(<4 x float> %x0, <4 x float> %x1, float *%ptr_b ,i8 %x3,i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ss_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %esi
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vfmadd231ss (%rdi), %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load float, float* %ptr_b
|
|
%vecinit.i = insertelement <4 x float> undef, float %q, i32 0
|
|
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %vecinit.i, <4 x float> %x1, i8 %x3, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_int_x86_avx512_mask_vfmadd_ss_rm(<4 x float> %x0, <4 x float> %x1,float *%ptr_b ,i8 %x3,i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_mask_vfmadd_ss_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: andl $1, %esi
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vfmadd132ss (%rdi), %xmm1, %xmm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%q = load float, float* %ptr_b
|
|
%vecinit.i = insertelement <4 x float> undef, float %q, i32 0
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0,<4 x float> %vecinit.i, <4 x float> %x1, i8 %x3, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
|
|
define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss_rm(<4 x float> %x0, <4 x float> %x1,float *%ptr_b ,i8 %x3,i32 %x4) {
|
|
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_ss_rm:
|
|
; CHECK: ## BB#0:
|
|
; CHECK-NEXT: kxorw %k0, %k0, %k1
|
|
; CHECK-NEXT: vfmadd213ss (%rdi), %xmm0, %xmm1 {%k1} {z}
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%q = load float, float* %ptr_b
|
|
%vecinit.i = insertelement <4 x float> undef, float %q, i32 0
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %vecinit.i, i8 0, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|