blob: d01f8b9e23d5c495cd7edd7d75d9b62c5eafe990 [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512er --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512er --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64
define <16 x float> @test_rsqrt28_ps(<16 x float> %a0) {
; CHECK-LABEL: test_rsqrt28_ps:
; CHECK: # %bb.0:
; CHECK-NEXT: vrsqrt28ps {sae}, %zmm0, %zmm0 # encoding: [0x62,0xf2,0x7d,0x18,0xcc,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
define <16 x float> @test1_rsqrt28_ps(<16 x float> %a0, <16 x float> %a1) {
; CHECK-LABEL: test1_rsqrt28_ps:
; CHECK: # %bb.0:
; CHECK-NEXT: movw $6, %ax # encoding: [0x66,0xb8,0x06,0x00]
; CHECK-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; CHECK-NEXT: vrsqrt28ps {sae}, %zmm0, %zmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x19,0xcc,0xc8]
; CHECK-NEXT: vmovaps %zmm1, %zmm0 # encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc1]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> %a1, i16 6, i32 8)
ret <16 x float> %res
}
define <16 x float> @test2_rsqrt28_ps(<16 x float> %a0) {
; CHECK-LABEL: test2_rsqrt28_ps:
; CHECK: # %bb.0:
; CHECK-NEXT: movw $6, %ax # encoding: [0x66,0xb8,0x06,0x00]
; CHECK-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; CHECK-NEXT: vrsqrt28ps %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcc,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> undef, i16 6, i32 4)
ret <16 x float> %res
}
define <16 x float> @test3_rsqrt28_ps(<16 x float> %a0) {
; CHECK-LABEL: test3_rsqrt28_ps:
; CHECK: # %bb.0:
; CHECK-NEXT: movw $6, %ax # encoding: [0x66,0xb8,0x06,0x00]
; CHECK-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; CHECK-NEXT: vrsqrt28ps %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcc,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> zeroinitializer, i16 6, i32 4)
ret <16 x float> %res
}
define <16 x float> @test4_rsqrt28_ps(<16 x float> %a0) {
; CHECK-LABEL: test4_rsqrt28_ps:
; CHECK: # %bb.0:
; CHECK-NEXT: movw $6, %ax # encoding: [0x66,0xb8,0x06,0x00]
; CHECK-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; CHECK-NEXT: vrsqrt28ps {sae}, %zmm0, %zmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x99,0xcc,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> undef, i16 6, i32 8)
ret <16 x float> %res
}
declare <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float>, <16 x float>, i16, i32) nounwind readnone
define <16 x float> @test_rcp28_ps_512(<16 x float> %a0) {
; CHECK-LABEL: test_rcp28_ps_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vrcp28ps {sae}, %zmm0, %zmm0 # encoding: [0x62,0xf2,0x7d,0x18,0xca,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.rcp28.ps(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
declare <16 x float> @llvm.x86.avx512.rcp28.ps(<16 x float>, <16 x float>, i16, i32) nounwind readnone
define <8 x double> @test_rcp28_pd_512(<8 x double> %a0) {
; CHECK-LABEL: test_rcp28_pd_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vrcp28pd {sae}, %zmm0, %zmm0 # encoding: [0x62,0xf2,0xfd,0x18,0xca,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.rcp28.pd(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1, i32 8)
ret <8 x double> %res
}
declare <8 x double> @llvm.x86.avx512.rcp28.pd(<8 x double>, <8 x double>, i8, i32) nounwind readnone
define <16 x float> @test_exp2_ps_512(<16 x float> %a0) {
; CHECK-LABEL: test_exp2_ps_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vexp2ps {sae}, %zmm0, %zmm0 # encoding: [0x62,0xf2,0x7d,0x18,0xc8,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.exp2.ps(<16 x float> %a0, <16 x float> zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
declare <16 x float> @llvm.x86.avx512.exp2.ps(<16 x float>, <16 x float>, i16, i32) nounwind readnone
define <8 x double> @test_exp2_pd_512(<8 x double> %a0) {
; CHECK-LABEL: test_exp2_pd_512:
; CHECK: # %bb.0:
; CHECK-NEXT: vexp2pd {sae}, %zmm0, %zmm0 # encoding: [0x62,0xf2,0xfd,0x18,0xc8,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.exp2.pd(<8 x double> %a0, <8 x double> zeroinitializer, i8 -1, i32 8)
ret <8 x double> %res
}
declare <8 x double> @llvm.x86.avx512.exp2.pd(<8 x double>, <8 x double>, i8, i32) nounwind readnone
define <4 x float> @test_rsqrt28_ss(<4 x float> %a0) {
; CHECK-LABEL: test_rsqrt28_ss:
; CHECK: # %bb.0:
; CHECK-NEXT: vrsqrt28ss {sae}, %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x18,0xcd,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.rsqrt28.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1, i32 8) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.rsqrt28.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
define <4 x float> @test_rcp28_ss(<4 x float> %a0) {
; CHECK-LABEL: test_rcp28_ss:
; CHECK: # %bb.0:
; CHECK-NEXT: vrcp28ss {sae}, %xmm0, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x18,0xcb,0xc0]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.rcp28.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 -1, i32 8) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.rcp28.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32) nounwind readnone
define <4 x float> @test_rcp28_ss_load(<4 x float> %a0, <4 x float>* %a1ptr) {
; X86-LABEL: test_rcp28_ss_load:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: vrcp28ss (%eax), %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x08,0xcb,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rcp28_ss_load:
; X64: # %bb.0:
; X64-NEXT: vrcp28ss (%rdi), %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x08,0xcb,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%a1 = load <4 x float>, <4 x float>* %a1ptr
%res = call <4 x float> @llvm.x86.avx512.rcp28.ss(<4 x float> %a0, <4 x float> %a1, <4 x float> undef, i8 -1, i32 4) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
define <4 x float> @test_rsqrt28_ss_load(<4 x float> %a0, <4 x float>* %a1ptr) {
; X86-LABEL: test_rsqrt28_ss_load:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: vrsqrt28ss (%eax), %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x08,0xcd,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_ss_load:
; X64: # %bb.0:
; X64-NEXT: vrsqrt28ss (%rdi), %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x08,0xcd,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%a1 = load <4 x float>, <4 x float>* %a1ptr
%res = call <4 x float> @llvm.x86.avx512.rsqrt28.ss(<4 x float> %a0, <4 x float> %a1, <4 x float> undef, i8 -1, i32 4) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
define <4 x float> @test_rsqrt28_ss_maskz(<4 x float> %a0, i8 %mask) {
; X86-LABEL: test_rsqrt28_ss_maskz:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrsqrt28ss {sae}, %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x99,0xcd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_ss_maskz:
; X64: # %bb.0:
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vrsqrt28ss {sae}, %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x99,0xcd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.rsqrt28.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> zeroinitializer, i8 %mask, i32 8) ;
ret <4 x float> %res
}
define <4 x float> @test_rsqrt28_ss_mask(<4 x float> %a0, <4 x float> %b0, <4 x float> %c0, i8 %mask) {
; X86-LABEL: test_rsqrt28_ss_mask:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrsqrt28ss {sae}, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x19,0xcd,0xd1]
; X86-NEXT: vmovaps %xmm2, %xmm0 # encoding: [0xc5,0xf8,0x28,0xc2]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_ss_mask:
; X64: # %bb.0:
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vrsqrt28ss {sae}, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x19,0xcd,0xd1]
; X64-NEXT: vmovaps %xmm2, %xmm0 # encoding: [0xc5,0xf8,0x28,0xc2]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.rsqrt28.ss(<4 x float> %a0, <4 x float> %b0, <4 x float> %c0, i8 %mask, i32 8) ;
ret <4 x float> %res
}
define <2 x double> @test_rcp28_sd_mask_load(<2 x double> %a0, <2 x double>* %a1ptr, <2 x double> %a2, i8 %mask) {
; X86-LABEL: test_rcp28_sd_mask_load:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrcp28sd %xmm0, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0xcb,0xc8]
; X86-NEXT: vmovapd %xmm1, %xmm0 # encoding: [0xc5,0xf9,0x28,0xc1]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rcp28_sd_mask_load:
; X64: # %bb.0:
; X64-NEXT: kmovw %esi, %k1 # encoding: [0xc5,0xf8,0x92,0xce]
; X64-NEXT: vrcp28sd %xmm0, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0xcb,0xc8]
; X64-NEXT: vmovapd %xmm1, %xmm0 # encoding: [0xc5,0xf9,0x28,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%a1 = load <2 x double>, <2 x double>* %a1ptr
%res = call <2 x double> @llvm.x86.avx512.rcp28.sd(<2 x double> %a0, <2 x double> %a0, <2 x double> %a2, i8 %mask, i32 4) ;
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx512.rcp28.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
define <2 x double> @test_rsqrt28_sd_maskz_load(<2 x double> %a0, <2 x double>* %a1ptr, i8 %mask) {
; X86-LABEL: test_rsqrt28_sd_maskz_load:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrsqrt28sd %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_sd_maskz_load:
; X64: # %bb.0:
; X64-NEXT: kmovw %esi, %k1 # encoding: [0xc5,0xf8,0x92,0xce]
; X64-NEXT: vrsqrt28sd %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%a1 = load <2 x double>, <2 x double>* %a1ptr
%res = call <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double> %a0, <2 x double> %a0, <2 x double> zeroinitializer, i8 %mask, i32 4) ;
ret <2 x double> %res
}
define <2 x double> @test_rsqrt28_sd_maskz(<2 x double> %a0, i8 %mask) {
; X86-LABEL: test_rsqrt28_sd_maskz:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrsqrt28sd {sae}, %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x99,0xcd,0xc0]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_sd_maskz:
; X64: # %bb.0:
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vrsqrt28sd {sae}, %xmm0, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x99,0xcd,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double> %a0, <2 x double> %a0, <2 x double> zeroinitializer, i8 %mask, i32 8) ;
ret <2 x double> %res
}
define <2 x double> @test_rsqrt28_sd_mask(<2 x double> %a0, <2 x double> %b0, <2 x double> %c0, i8 %mask) {
; X86-LABEL: test_rsqrt28_sd_mask:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: vrsqrt28sd {sae}, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x19,0xcd,0xd1]
; X86-NEXT: vmovapd %xmm2, %xmm0 # encoding: [0xc5,0xf9,0x28,0xc2]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_sd_mask:
; X64: # %bb.0:
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vrsqrt28sd {sae}, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x19,0xcd,0xd1]
; X64-NEXT: vmovapd %xmm2, %xmm0 # encoding: [0xc5,0xf9,0x28,0xc2]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double> %a0, <2 x double> %b0, <2 x double> %c0, i8 %mask, i32 8) ;
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32) nounwind readnone
define <2 x double> @test_rsqrt28_sd_maskz_mem(<2 x double> %a0, double* %ptr, i8 %mask) {
; X86-LABEL: test_rsqrt28_sd_maskz_mem:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: vrsqrt28sd (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0x00]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_sd_maskz_mem:
; X64: # %bb.0:
; X64-NEXT: kmovw %esi, %k1 # encoding: [0xc5,0xf8,0x92,0xce]
; X64-NEXT: vrsqrt28sd (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0x07]
; X64-NEXT: retq # encoding: [0xc3]
%mem = load double , double * %ptr, align 8
%mem_v = insertelement <2 x double> undef, double %mem, i32 0
%res = call <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double> %a0, <2 x double> %mem_v, <2 x double> zeroinitializer, i8 %mask, i32 4) ;
ret <2 x double> %res
}
define <2 x double> @test_rsqrt28_sd_maskz_mem_offset(<2 x double> %a0, double* %ptr, i8 %mask) {
; X86-LABEL: test_rsqrt28_sd_maskz_mem_offset:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT: kmovw %eax, %k1 # encoding: [0xc5,0xf8,0x92,0xc8]
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT: vrsqrt28sd 144(%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0x40,0x12]
; X86-NEXT: retl # encoding: [0xc3]
;
; X64-LABEL: test_rsqrt28_sd_maskz_mem_offset:
; X64: # %bb.0:
; X64-NEXT: kmovw %esi, %k1 # encoding: [0xc5,0xf8,0x92,0xce]
; X64-NEXT: vrsqrt28sd 144(%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0xcd,0x47,0x12]
; X64-NEXT: retq # encoding: [0xc3]
%ptr1 = getelementptr double, double* %ptr, i32 18
%mem = load double , double * %ptr1, align 8
%mem_v = insertelement <2 x double> undef, double %mem, i32 0
%res = call <2 x double> @llvm.x86.avx512.rsqrt28.sd(<2 x double> %a0, <2 x double> %mem_v, <2 x double> zeroinitializer, i8 %mask, i32 4) ;
ret <2 x double> %res
}