maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/vec-strict-inttofp-128.ll

1390 lines
56 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 -O3 | FileCheck %s --check-prefixes=SSE,SSE-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 -O3 | FileCheck %s --check-prefixes=SSE,SSE-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 -O3 | FileCheck %s --check-prefixes=SSE41,SSE41-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 -O3 | FileCheck %s --check-prefixes=SSE41,SSE41-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx -O3 | FileCheck %s --check-prefixes=AVX,AVX1,AVX-32,AVX1-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -O3 | FileCheck %s --check-prefixes=AVX,AVX1,AVX-64,AVX1-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512f -O3 | FileCheck %s --check-prefixes=AVX,AVX512F,AVX-32,AVX512F-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f -O3 | FileCheck %s --check-prefixes=AVX,AVX512F,AVX-64,AVX512F-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx512vl -O3 | FileCheck %s --check-prefixes=AVX,AVX512VL,AVX-32,AVX512VL-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512vl -O3 | FileCheck %s --check-prefixes=AVX,AVX512VL,AVX-64,AVX512VL-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx512f,avx512dq -O3 | FileCheck %s --check-prefixes=AVX,AVX512DQ,AVX512DQ-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f,avx512dq -O3 | FileCheck %s --check-prefixes=AVX,AVX512DQ,AVX512DQ-64
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx512dq,avx512vl -O3 | FileCheck %s --check-prefixes=AVX,AVX512DQVL,AVX512DQVL-32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512dq,avx512vl -O3 | FileCheck %s --check-prefixes=AVX,AVX512DQVL,AVX512DQVL-64
declare <2 x float> @llvm.experimental.constrained.sitofp.v2f32.v2i32(<2 x i32>, metadata, metadata)
declare <2 x float> @llvm.experimental.constrained.uitofp.v2f32.v2i32(<2 x i32>, metadata, metadata)
declare <2 x float> @llvm.experimental.constrained.sitofp.v2f32.v2i64(<2 x i64>, metadata, metadata)
declare <2 x float> @llvm.experimental.constrained.uitofp.v2f32.v2i64(<2 x i64>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i1(<4 x i1>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i1(<4 x i1>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i8(<4 x i8>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i8(<4 x i8>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i16(<4 x i16>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i16(<4 x i16>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i32(<4 x i32>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i32(<4 x i32>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i1(<2 x i1>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i1(<2 x i1>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i8(<2 x i8>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i8(<2 x i8>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i16(<2 x i16>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i16(<2 x i16>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i32(<2 x i32>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i32(<2 x i32>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i64(<2 x i64>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i64(<2 x i64>, metadata, metadata)
define <2 x float> @sitofp_v2i32_v2f32(<2 x i32> %x) #0 {
; SSE-LABEL: sitofp_v2i32_v2f32:
; SSE: # %bb.0:
; SSE-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v2i32_v2f32:
; SSE41: # %bb.0:
; SSE41-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v2i32_v2f32:
; AVX: # %bb.0:
; AVX-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x float> @llvm.experimental.constrained.sitofp.v2f32.v2i32(<2 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x float> %result
}
define <2 x float> @uitofp_v2i32_v2f32(<2 x i32> %x) #0 {
; SSE-LABEL: uitofp_v2i32_v2f32:
; SSE: # %bb.0:
; SSE-NEXT: xorpd %xmm1, %xmm1
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movapd {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; SSE-NEXT: orpd %xmm1, %xmm0
; SSE-NEXT: subpd %xmm1, %xmm0
; SSE-NEXT: cvtpd2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v2i32_v2f32:
; SSE41: # %bb.0:
; SSE41-NEXT: xorpd %xmm1, %xmm1
; SSE41-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: movapd {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; SSE41-NEXT: orpd %xmm1, %xmm0
; SSE41-NEXT: subpd %xmm1, %xmm0
; SSE41-NEXT: cvtpd2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX1-LABEL: uitofp_v2i32_v2f32:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vsubpd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vcvtpd2ps %xmm0, %xmm0
; AVX1-NEXT: ret{{[l|q]}}
;
; AVX512F-LABEL: uitofp_v2i32_v2f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512F-NEXT: vcvtudq2ps %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: ret{{[l|q]}}
;
; AVX512VL-LABEL: uitofp_v2i32_v2f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512VL-NEXT: vcvtudq2ps %xmm0, %xmm0
; AVX512VL-NEXT: ret{{[l|q]}}
;
; AVX512DQ-LABEL: uitofp_v2i32_v2f32:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512DQ-NEXT: vcvtudq2ps %zmm0, %zmm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-LABEL: uitofp_v2i32_v2f32:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512DQVL-NEXT: vcvtudq2ps %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x float> @llvm.experimental.constrained.uitofp.v2f32.v2i32(<2 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x float> %result
}
define <2 x float> @sitofp_v2i64_v2f32(<2 x i64> %x) #0 {
; SSE-32-LABEL: sitofp_v2i64_v2f32:
; SSE-32: # %bb.0:
; SSE-32-NEXT: pushl %ebp
; SSE-32-NEXT: .cfi_def_cfa_offset 8
; SSE-32-NEXT: .cfi_offset %ebp, -8
; SSE-32-NEXT: movl %esp, %ebp
; SSE-32-NEXT: .cfi_def_cfa_register %ebp
; SSE-32-NEXT: andl $-8, %esp
; SSE-32-NEXT: subl $24, %esp
; SSE-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fstps (%esp)
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fstps {{[0-9]+}}(%esp)
; SSE-32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-32-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-32-NEXT: movl %ebp, %esp
; SSE-32-NEXT: popl %ebp
; SSE-32-NEXT: .cfi_def_cfa %esp, 4
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: sitofp_v2i64_v2f32:
; SSE-64: # %bb.0:
; SSE-64-NEXT: movq %xmm0, %rax
; SSE-64-NEXT: cvtsi2ss %rax, %xmm1
; SSE-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-64-NEXT: movq %xmm0, %rax
; SSE-64-NEXT: xorps %xmm0, %xmm0
; SSE-64-NEXT: cvtsi2ss %rax, %xmm0
; SSE-64-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE-64-NEXT: movaps %xmm1, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: sitofp_v2i64_v2f32:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: pushl %ebp
; SSE41-32-NEXT: .cfi_def_cfa_offset 8
; SSE41-32-NEXT: .cfi_offset %ebp, -8
; SSE41-32-NEXT: movl %esp, %ebp
; SSE41-32-NEXT: .cfi_def_cfa_register %ebp
; SSE41-32-NEXT: andl $-8, %esp
; SSE41-32-NEXT: subl $24, %esp
; SSE41-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fstps (%esp)
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fstps {{[0-9]+}}(%esp)
; SSE41-32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE41-32-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-32-NEXT: movl %ebp, %esp
; SSE41-32-NEXT: popl %ebp
; SSE41-32-NEXT: .cfi_def_cfa %esp, 4
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: sitofp_v2i64_v2f32:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: movq %xmm0, %rax
; SSE41-64-NEXT: cvtsi2ss %rax, %xmm1
; SSE41-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-64-NEXT: movq %xmm0, %rax
; SSE41-64-NEXT: xorps %xmm0, %xmm0
; SSE41-64-NEXT: cvtsi2ss %rax, %xmm0
; SSE41-64-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE41-64-NEXT: movaps %xmm1, %xmm0
; SSE41-64-NEXT: retq
;
; AVX-32-LABEL: sitofp_v2i64_v2f32:
; AVX-32: # %bb.0:
; AVX-32-NEXT: pushl %ebp
; AVX-32-NEXT: .cfi_def_cfa_offset 8
; AVX-32-NEXT: .cfi_offset %ebp, -8
; AVX-32-NEXT: movl %esp, %ebp
; AVX-32-NEXT: .cfi_def_cfa_register %ebp
; AVX-32-NEXT: andl $-8, %esp
; AVX-32-NEXT: subl $24, %esp
; AVX-32-NEXT: vmovlps %xmm0, {{[0-9]+}}(%esp)
; AVX-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX-32-NEXT: vmovlps %xmm0, {{[0-9]+}}(%esp)
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fstps (%esp)
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fstps {{[0-9]+}}(%esp)
; AVX-32-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-32-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; AVX-32-NEXT: movl %ebp, %esp
; AVX-32-NEXT: popl %ebp
; AVX-32-NEXT: .cfi_def_cfa %esp, 4
; AVX-32-NEXT: retl
;
; AVX-64-LABEL: sitofp_v2i64_v2f32:
; AVX-64: # %bb.0:
; AVX-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX-64-NEXT: vcvtsi2ss %rax, %xmm1, %xmm1
; AVX-64-NEXT: vmovq %xmm0, %rax
; AVX-64-NEXT: vcvtsi2ss %rax, %xmm2, %xmm0
; AVX-64-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; AVX-64-NEXT: retq
;
; AVX512DQ-32-LABEL: sitofp_v2i64_v2f32:
; AVX512DQ-32: # %bb.0:
; AVX512DQ-32-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512DQ-32-NEXT: vcvtqq2ps %zmm0, %ymm1
; AVX512DQ-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX512DQ-32-NEXT: vcvtqq2ps %zmm0, %ymm0
; AVX512DQ-32-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],zero,zero
; AVX512DQ-32-NEXT: vzeroupper
; AVX512DQ-32-NEXT: retl
;
; AVX512DQ-64-LABEL: sitofp_v2i64_v2f32:
; AVX512DQ-64: # %bb.0:
; AVX512DQ-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX512DQ-64-NEXT: vcvtsi2ss %rax, %xmm1, %xmm1
; AVX512DQ-64-NEXT: vmovq %xmm0, %rax
; AVX512DQ-64-NEXT: vcvtsi2ss %rax, %xmm2, %xmm0
; AVX512DQ-64-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; AVX512DQ-64-NEXT: retq
;
; AVX512DQVL-LABEL: sitofp_v2i64_v2f32:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtqq2ps %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x float> @llvm.experimental.constrained.sitofp.v2f32.v2i64(<2 x i64> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x float> %result
}
define <2 x float> @uitofp_v2i64_v2f32(<2 x i64> %x) #0 {
; SSE-32-LABEL: uitofp_v2i64_v2f32:
; SSE-32: # %bb.0:
; SSE-32-NEXT: pushl %ebp
; SSE-32-NEXT: .cfi_def_cfa_offset 8
; SSE-32-NEXT: .cfi_offset %ebp, -8
; SSE-32-NEXT: movl %esp, %ebp
; SSE-32-NEXT: .cfi_def_cfa_register %ebp
; SSE-32-NEXT: andl $-8, %esp
; SSE-32-NEXT: subl $24, %esp
; SSE-32-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSE-32-NEXT: movq %xmm1, {{[0-9]+}}(%esp)
; SSE-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE-32-NEXT: pshufd {{.*#+}} xmm1 = xmm0[3,1,2,3]
; SSE-32-NEXT: movd %xmm1, %eax
; SSE-32-NEXT: xorl %ecx, %ecx
; SSE-32-NEXT: testl %eax, %eax
; SSE-32-NEXT: setns %cl
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; SSE-32-NEXT: fstps (%esp)
; SSE-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE-32-NEXT: movd %xmm0, %eax
; SSE-32-NEXT: xorl %ecx, %ecx
; SSE-32-NEXT: testl %eax, %eax
; SSE-32-NEXT: setns %cl
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; SSE-32-NEXT: fstps {{[0-9]+}}(%esp)
; SSE-32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE-32-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-32-NEXT: movl %ebp, %esp
; SSE-32-NEXT: popl %ebp
; SSE-32-NEXT: .cfi_def_cfa %esp, 4
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: uitofp_v2i64_v2f32:
; SSE-64: # %bb.0:
; SSE-64-NEXT: movdqa %xmm0, %xmm1
; SSE-64-NEXT: movq %xmm0, %rax
; SSE-64-NEXT: movq %rax, %rcx
; SSE-64-NEXT: shrq %rcx
; SSE-64-NEXT: movl %eax, %edx
; SSE-64-NEXT: andl $1, %edx
; SSE-64-NEXT: orq %rcx, %rdx
; SSE-64-NEXT: testq %rax, %rax
; SSE-64-NEXT: cmovnsq %rax, %rdx
; SSE-64-NEXT: xorps %xmm0, %xmm0
; SSE-64-NEXT: cvtsi2ss %rdx, %xmm0
; SSE-64-NEXT: jns .LBB3_2
; SSE-64-NEXT: # %bb.1:
; SSE-64-NEXT: addss %xmm0, %xmm0
; SSE-64-NEXT: .LBB3_2:
; SSE-64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE-64-NEXT: movq %xmm1, %rax
; SSE-64-NEXT: movq %rax, %rcx
; SSE-64-NEXT: shrq %rcx
; SSE-64-NEXT: movl %eax, %edx
; SSE-64-NEXT: andl $1, %edx
; SSE-64-NEXT: orq %rcx, %rdx
; SSE-64-NEXT: testq %rax, %rax
; SSE-64-NEXT: cmovnsq %rax, %rdx
; SSE-64-NEXT: xorps %xmm1, %xmm1
; SSE-64-NEXT: cvtsi2ss %rdx, %xmm1
; SSE-64-NEXT: jns .LBB3_4
; SSE-64-NEXT: # %bb.3:
; SSE-64-NEXT: addss %xmm1, %xmm1
; SSE-64-NEXT: .LBB3_4:
; SSE-64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: uitofp_v2i64_v2f32:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: pushl %ebp
; SSE41-32-NEXT: .cfi_def_cfa_offset 8
; SSE41-32-NEXT: .cfi_offset %ebp, -8
; SSE41-32-NEXT: movl %esp, %ebp
; SSE41-32-NEXT: .cfi_def_cfa_register %ebp
; SSE41-32-NEXT: andl $-8, %esp
; SSE41-32-NEXT: subl $24, %esp
; SSE41-32-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; SSE41-32-NEXT: movq %xmm1, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: pshufd {{.*#+}} xmm1 = xmm0[3,1,2,3]
; SSE41-32-NEXT: movd %xmm1, %eax
; SSE41-32-NEXT: xorl %ecx, %ecx
; SSE41-32-NEXT: testl %eax, %eax
; SSE41-32-NEXT: setns %cl
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; SSE41-32-NEXT: fstps (%esp)
; SSE41-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE41-32-NEXT: movd %xmm0, %eax
; SSE41-32-NEXT: xorl %ecx, %ecx
; SSE41-32-NEXT: testl %eax, %eax
; SSE41-32-NEXT: setns %cl
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; SSE41-32-NEXT: fstps {{[0-9]+}}(%esp)
; SSE41-32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE41-32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE41-32-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-32-NEXT: movl %ebp, %esp
; SSE41-32-NEXT: popl %ebp
; SSE41-32-NEXT: .cfi_def_cfa %esp, 4
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: uitofp_v2i64_v2f32:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: movdqa %xmm0, %xmm1
; SSE41-64-NEXT: movq %xmm0, %rax
; SSE41-64-NEXT: movq %rax, %rcx
; SSE41-64-NEXT: shrq %rcx
; SSE41-64-NEXT: movl %eax, %edx
; SSE41-64-NEXT: andl $1, %edx
; SSE41-64-NEXT: orq %rcx, %rdx
; SSE41-64-NEXT: testq %rax, %rax
; SSE41-64-NEXT: cmovnsq %rax, %rdx
; SSE41-64-NEXT: xorps %xmm0, %xmm0
; SSE41-64-NEXT: cvtsi2ss %rdx, %xmm0
; SSE41-64-NEXT: jns .LBB3_2
; SSE41-64-NEXT: # %bb.1:
; SSE41-64-NEXT: addss %xmm0, %xmm0
; SSE41-64-NEXT: .LBB3_2:
; SSE41-64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE41-64-NEXT: movq %xmm1, %rax
; SSE41-64-NEXT: movq %rax, %rcx
; SSE41-64-NEXT: shrq %rcx
; SSE41-64-NEXT: movl %eax, %edx
; SSE41-64-NEXT: andl $1, %edx
; SSE41-64-NEXT: orq %rcx, %rdx
; SSE41-64-NEXT: testq %rax, %rax
; SSE41-64-NEXT: cmovnsq %rax, %rdx
; SSE41-64-NEXT: xorps %xmm1, %xmm1
; SSE41-64-NEXT: cvtsi2ss %rdx, %xmm1
; SSE41-64-NEXT: jns .LBB3_4
; SSE41-64-NEXT: # %bb.3:
; SSE41-64-NEXT: addss %xmm1, %xmm1
; SSE41-64-NEXT: .LBB3_4:
; SSE41-64-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-64-NEXT: retq
;
; AVX-32-LABEL: uitofp_v2i64_v2f32:
; AVX-32: # %bb.0:
; AVX-32-NEXT: pushl %ebp
; AVX-32-NEXT: .cfi_def_cfa_offset 8
; AVX-32-NEXT: .cfi_offset %ebp, -8
; AVX-32-NEXT: movl %esp, %ebp
; AVX-32-NEXT: .cfi_def_cfa_register %ebp
; AVX-32-NEXT: andl $-8, %esp
; AVX-32-NEXT: subl $24, %esp
; AVX-32-NEXT: vmovlps %xmm0, {{[0-9]+}}(%esp)
; AVX-32-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX-32-NEXT: vmovlps %xmm1, {{[0-9]+}}(%esp)
; AVX-32-NEXT: vextractps $1, %xmm0, %eax
; AVX-32-NEXT: xorl %ecx, %ecx
; AVX-32-NEXT: testl %eax, %eax
; AVX-32-NEXT: setns %cl
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; AVX-32-NEXT: fstps {{[0-9]+}}(%esp)
; AVX-32-NEXT: vextractps $3, %xmm0, %eax
; AVX-32-NEXT: xorl %ecx, %ecx
; AVX-32-NEXT: testl %eax, %eax
; AVX-32-NEXT: setns %cl
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; AVX-32-NEXT: fstps (%esp)
; AVX-32-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-32-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
; AVX-32-NEXT: movl %ebp, %esp
; AVX-32-NEXT: popl %ebp
; AVX-32-NEXT: .cfi_def_cfa %esp, 4
; AVX-32-NEXT: retl
;
; AVX1-64-LABEL: uitofp_v2i64_v2f32:
; AVX1-64: # %bb.0:
; AVX1-64-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
; AVX1-64-NEXT: vpsrlq $1, %xmm0, %xmm2
; AVX1-64-NEXT: vpor %xmm1, %xmm2, %xmm1
; AVX1-64-NEXT: vblendvpd %xmm0, %xmm1, %xmm0, %xmm1
; AVX1-64-NEXT: vpextrq $1, %xmm1, %rax
; AVX1-64-NEXT: vcvtsi2ss %rax, %xmm3, %xmm2
; AVX1-64-NEXT: vmovq %xmm1, %rax
; AVX1-64-NEXT: vcvtsi2ss %rax, %xmm3, %xmm1
; AVX1-64-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],zero,zero
; AVX1-64-NEXT: vaddps %xmm1, %xmm1, %xmm2
; AVX1-64-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX1-64-NEXT: vpcmpgtq %xmm0, %xmm3, %xmm0
; AVX1-64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; AVX1-64-NEXT: vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX1-64-NEXT: retq
;
; AVX512F-64-LABEL: uitofp_v2i64_v2f32:
; AVX512F-64: # %bb.0:
; AVX512F-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX512F-64-NEXT: vcvtusi2ss %rax, %xmm1, %xmm1
; AVX512F-64-NEXT: vmovq %xmm0, %rax
; AVX512F-64-NEXT: vcvtusi2ss %rax, %xmm2, %xmm0
; AVX512F-64-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; AVX512F-64-NEXT: retq
;
; AVX512VL-64-LABEL: uitofp_v2i64_v2f32:
; AVX512VL-64: # %bb.0:
; AVX512VL-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX512VL-64-NEXT: vcvtusi2ss %rax, %xmm1, %xmm1
; AVX512VL-64-NEXT: vmovq %xmm0, %rax
; AVX512VL-64-NEXT: vcvtusi2ss %rax, %xmm2, %xmm0
; AVX512VL-64-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; AVX512VL-64-NEXT: retq
;
; AVX512DQ-32-LABEL: uitofp_v2i64_v2f32:
; AVX512DQ-32: # %bb.0:
; AVX512DQ-32-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512DQ-32-NEXT: vcvtuqq2ps %zmm0, %ymm1
; AVX512DQ-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX512DQ-32-NEXT: vcvtuqq2ps %zmm0, %ymm0
; AVX512DQ-32-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],zero,zero
; AVX512DQ-32-NEXT: vzeroupper
; AVX512DQ-32-NEXT: retl
;
; AVX512DQ-64-LABEL: uitofp_v2i64_v2f32:
; AVX512DQ-64: # %bb.0:
; AVX512DQ-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX512DQ-64-NEXT: vcvtusi2ss %rax, %xmm1, %xmm1
; AVX512DQ-64-NEXT: vmovq %xmm0, %rax
; AVX512DQ-64-NEXT: vcvtusi2ss %rax, %xmm2, %xmm0
; AVX512DQ-64-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
; AVX512DQ-64-NEXT: retq
;
; AVX512DQVL-LABEL: uitofp_v2i64_v2f32:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtuqq2ps %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x float> @llvm.experimental.constrained.uitofp.v2f32.v2i64(<2 x i64> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x float> %result
}
define <4 x float> @sitofp_v4i1_v4f32(<4 x i1> %x) #0 {
; SSE-LABEL: sitofp_v4i1_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v4i1_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: pslld $31, %xmm0
; SSE41-NEXT: psrad $31, %xmm0
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v4i1_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vpsrad $31, %xmm0, %xmm0
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i1(<4 x i1> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @uitofp_v4i1_v4f32(<4 x i1> %x) #0 {
; SSE-32-LABEL: uitofp_v4i1_v4f32:
; SSE-32: # %bb.0:
; SSE-32-NEXT: andps {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: uitofp_v4i1_v4f32:
; SSE-64: # %bb.0:
; SSE-64-NEXT: andps {{.*}}(%rip), %xmm0
; SSE-64-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: uitofp_v4i1_v4f32:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: andps {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: uitofp_v4i1_v4f32:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: andps {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-64-NEXT: retq
;
; AVX1-32-LABEL: uitofp_v4i1_v4f32:
; AVX1-32: # %bb.0:
; AVX1-32-NEXT: vandps {{\.LCPI.*}}, %xmm0, %xmm0
; AVX1-32-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX1-32-NEXT: retl
;
; AVX1-64-LABEL: uitofp_v4i1_v4f32:
; AVX1-64: # %bb.0:
; AVX1-64-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
; AVX1-64-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX1-64-NEXT: retq
;
; AVX512F-LABEL: uitofp_v4i1_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
; AVX512F-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512F-NEXT: ret{{[l|q]}}
;
; AVX512VL-32-LABEL: uitofp_v4i1_v4f32:
; AVX512VL-32: # %bb.0:
; AVX512VL-32-NEXT: vpandd {{\.LCPI.*}}{1to4}, %xmm0, %xmm0
; AVX512VL-32-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512VL-32-NEXT: retl
;
; AVX512VL-64-LABEL: uitofp_v4i1_v4f32:
; AVX512VL-64: # %bb.0:
; AVX512VL-64-NEXT: vpandd {{.*}}(%rip){1to4}, %xmm0, %xmm0
; AVX512VL-64-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512VL-64-NEXT: retq
;
; AVX512DQ-LABEL: uitofp_v4i1_v4f32:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
; AVX512DQ-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-32-LABEL: uitofp_v4i1_v4f32:
; AVX512DQVL-32: # %bb.0:
; AVX512DQVL-32-NEXT: vandps {{\.LCPI.*}}{1to4}, %xmm0, %xmm0
; AVX512DQVL-32-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512DQVL-32-NEXT: retl
;
; AVX512DQVL-64-LABEL: uitofp_v4i1_v4f32:
; AVX512DQVL-64: # %bb.0:
; AVX512DQVL-64-NEXT: vandps {{.*}}(%rip){1to4}, %xmm0, %xmm0
; AVX512DQVL-64-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX512DQVL-64-NEXT: retq
%result = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i1(<4 x i1> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @sitofp_v4i8_v4f32(<4 x i8> %x) #0 {
; SSE-LABEL: sitofp_v4i8_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE-NEXT: psrad $24, %xmm0
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v4i8_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE41-NEXT: psrad $24, %xmm0
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v4i8_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vpmovsxbd %xmm0, %xmm0
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i8(<4 x i8> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @uitofp_v4i8_v4f32(<4 x i8> %x) #0 {
; SSE-LABEL: uitofp_v4i8_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v4i8_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: uitofp_v4i8_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i8(<4 x i8> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @sitofp_v4i16_v4f32(<4 x i16> %x) #0 {
; SSE-LABEL: sitofp_v4i16_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v4i16_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE41-NEXT: psrad $16, %xmm0
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v4i16_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vpmovsxwd %xmm0, %xmm0
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i16(<4 x i16> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @uitofp_v4i16_v4f32(<4 x i16> %x) #0 {
; SSE-LABEL: uitofp_v4i16_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v4i16_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: uitofp_v4i16_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i16(<4 x i16> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @sitofp_v4i32_v4f32(<4 x i32> %x) #0 {
; SSE-LABEL: sitofp_v4i32_v4f32:
; SSE: # %bb.0:
; SSE-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v4i32_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: cvtdq2ps %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v4i32_v4f32:
; AVX: # %bb.0:
; AVX-NEXT: vcvtdq2ps %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.sitofp.v4f32.v4i32(<4 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <4 x float> @uitofp_v4i32_v4f32(<4 x i32> %x) #0 {
; SSE-32-LABEL: uitofp_v4i32_v4f32:
; SSE-32: # %bb.0:
; SSE-32-NEXT: movdqa {{.*#+}} xmm1 = [65535,65535,65535,65535]
; SSE-32-NEXT: pand %xmm0, %xmm1
; SSE-32-NEXT: por {{\.LCPI.*}}, %xmm1
; SSE-32-NEXT: psrld $16, %xmm0
; SSE-32-NEXT: por {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: subps {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: addps %xmm1, %xmm0
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: uitofp_v4i32_v4f32:
; SSE-64: # %bb.0:
; SSE-64-NEXT: movdqa {{.*#+}} xmm1 = [65535,65535,65535,65535]
; SSE-64-NEXT: pand %xmm0, %xmm1
; SSE-64-NEXT: por {{.*}}(%rip), %xmm1
; SSE-64-NEXT: psrld $16, %xmm0
; SSE-64-NEXT: por {{.*}}(%rip), %xmm0
; SSE-64-NEXT: subps {{.*}}(%rip), %xmm0
; SSE-64-NEXT: addps %xmm1, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: uitofp_v4i32_v4f32:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: movdqa {{.*#+}} xmm1 = [65535,65535,65535,65535]
; SSE41-32-NEXT: pand %xmm0, %xmm1
; SSE41-32-NEXT: por {{\.LCPI.*}}, %xmm1
; SSE41-32-NEXT: psrld $16, %xmm0
; SSE41-32-NEXT: por {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: subps {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: addps %xmm1, %xmm0
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: uitofp_v4i32_v4f32:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: movdqa {{.*#+}} xmm1 = [65535,65535,65535,65535]
; SSE41-64-NEXT: pand %xmm0, %xmm1
; SSE41-64-NEXT: por {{.*}}(%rip), %xmm1
; SSE41-64-NEXT: psrld $16, %xmm0
; SSE41-64-NEXT: por {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: subps {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: addps %xmm1, %xmm0
; SSE41-64-NEXT: retq
;
; AVX1-32-LABEL: uitofp_v4i32_v4f32:
; AVX1-32: # %bb.0:
; AVX1-32-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; AVX1-32-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-32-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; AVX1-32-NEXT: vsubps {{\.LCPI.*}}, %xmm0, %xmm0
; AVX1-32-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-32-NEXT: retl
;
; AVX1-64-LABEL: uitofp_v4i32_v4f32:
; AVX1-64: # %bb.0:
; AVX1-64-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; AVX1-64-NEXT: vpsrld $16, %xmm0, %xmm0
; AVX1-64-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; AVX1-64-NEXT: vsubps {{.*}}(%rip), %xmm0, %xmm0
; AVX1-64-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-64-NEXT: retq
;
; AVX512F-LABEL: uitofp_v4i32_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovaps %xmm0, %xmm0
; AVX512F-NEXT: vcvtudq2ps %zmm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: ret{{[l|q]}}
;
; AVX512VL-LABEL: uitofp_v4i32_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vcvtudq2ps %xmm0, %xmm0
; AVX512VL-NEXT: ret{{[l|q]}}
;
; AVX512DQ-LABEL: uitofp_v4i32_v4f32:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovaps %xmm0, %xmm0
; AVX512DQ-NEXT: vcvtudq2ps %zmm0, %zmm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-LABEL: uitofp_v4i32_v4f32:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtudq2ps %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <4 x float> @llvm.experimental.constrained.uitofp.v4f32.v4i32(<4 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <4 x float> %result
}
define <2 x double> @sitofp_v2i1_v2f64(<2 x i1> %x) #0 {
; SSE-LABEL: sitofp_v2i1_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: pslld $31, %xmm0
; SSE-NEXT: psrad $31, %xmm0
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v2i1_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT: pslld $31, %xmm0
; SSE41-NEXT: psrad $31, %xmm0
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v2i1_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-NEXT: vpslld $31, %xmm0, %xmm0
; AVX-NEXT: vpsrad $31, %xmm0, %xmm0
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i1(<2 x i1> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @uitofp_v2i1_v2f64(<2 x i1> %x) #0 {
; SSE-32-LABEL: uitofp_v2i1_v2f64:
; SSE-32: # %bb.0:
; SSE-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-32-NEXT: pand {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: uitofp_v2i1_v2f64:
; SSE-64: # %bb.0:
; SSE-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-64-NEXT: pand {{.*}}(%rip), %xmm0
; SSE-64-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: uitofp_v2i1_v2f64:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-32-NEXT: pand {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: uitofp_v2i1_v2f64:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-64-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-64-NEXT: retq
;
; AVX1-32-LABEL: uitofp_v2i1_v2f64:
; AVX1-32: # %bb.0:
; AVX1-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-32-NEXT: vandps {{\.LCPI.*}}, %xmm0, %xmm0
; AVX1-32-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX1-32-NEXT: retl
;
; AVX1-64-LABEL: uitofp_v2i1_v2f64:
; AVX1-64: # %bb.0:
; AVX1-64-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-64-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
; AVX1-64-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX1-64-NEXT: retq
;
; AVX512F-LABEL: uitofp_v2i1_v2f64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
; AVX512F-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX512F-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512F-NEXT: ret{{[l|q]}}
;
; AVX512VL-32-LABEL: uitofp_v2i1_v2f64:
; AVX512VL-32: # %bb.0:
; AVX512VL-32-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-32-NEXT: vpandd {{\.LCPI.*}}{1to4}, %xmm0, %xmm0
; AVX512VL-32-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512VL-32-NEXT: retl
;
; AVX512VL-64-LABEL: uitofp_v2i1_v2f64:
; AVX512VL-64: # %bb.0:
; AVX512VL-64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-64-NEXT: vpandd {{.*}}(%rip){1to4}, %xmm0, %xmm0
; AVX512VL-64-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512VL-64-NEXT: retq
;
; AVX512DQ-LABEL: uitofp_v2i1_v2f64:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512DQ-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
; AVX512DQ-NEXT: vandps %xmm1, %xmm0, %xmm0
; AVX512DQ-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-32-LABEL: uitofp_v2i1_v2f64:
; AVX512DQVL-32: # %bb.0:
; AVX512DQVL-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512DQVL-32-NEXT: vandps {{\.LCPI.*}}{1to4}, %xmm0, %xmm0
; AVX512DQVL-32-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512DQVL-32-NEXT: retl
;
; AVX512DQVL-64-LABEL: uitofp_v2i1_v2f64:
; AVX512DQVL-64: # %bb.0:
; AVX512DQVL-64-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512DQVL-64-NEXT: vandps {{.*}}(%rip){1to4}, %xmm0, %xmm0
; AVX512DQVL-64-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX512DQVL-64-NEXT: retq
%result = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i1(<2 x i1> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @sitofp_v2i8_v2f64(<2 x i8> %x) #0 {
; SSE-LABEL: sitofp_v2i8_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE-NEXT: psrad $24, %xmm0
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v2i8_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE41-NEXT: psrad $24, %xmm0
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v2i8_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vpmovsxbd %xmm0, %xmm0
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i8(<2 x i8> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @uitofp_v2i8_v2f64(<2 x i8> %x) #0 {
; SSE-LABEL: uitofp_v2i8_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v2i8_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: uitofp_v2i8_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i8(<2 x i8> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @sitofp_v2i16_v2f64(<2 x i16> %x) #0 {
; SSE-LABEL: sitofp_v2i16_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v2i16_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
; SSE41-NEXT: psrad $16, %xmm0
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v2i16_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vpmovsxwd %xmm0, %xmm0
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i16(<2 x i16> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @uitofp_v2i16_v2f64(<2 x i16> %x) #0 {
; SSE-LABEL: uitofp_v2i16_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v2i16_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: pxor %xmm1, %xmm1
; SSE41-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: uitofp_v2i16_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i16(<2 x i16> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @sitofp_v2i32_v2f64(<2 x i32> %x) #0 {
; SSE-LABEL: sitofp_v2i32_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: sitofp_v2i32_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX-LABEL: sitofp_v2i32_v2f64:
; AVX: # %bb.0:
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i32(<2 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @uitofp_v2i32_v2f64(<2 x i32> %x) #0 {
; SSE-LABEL: uitofp_v2i32_v2f64:
; SSE: # %bb.0:
; SSE-NEXT: xorpd %xmm1, %xmm1
; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movapd {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; SSE-NEXT: orpd %xmm1, %xmm0
; SSE-NEXT: subpd %xmm1, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; SSE41-LABEL: uitofp_v2i32_v2f64:
; SSE41: # %bb.0:
; SSE41-NEXT: xorpd %xmm1, %xmm1
; SSE41-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT: movapd {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; SSE41-NEXT: orpd %xmm1, %xmm0
; SSE41-NEXT: subpd %xmm1, %xmm0
; SSE41-NEXT: ret{{[l|q]}}
;
; AVX1-LABEL: uitofp_v2i32_v2f64:
; AVX1: # %bb.0:
; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [4.503599627370496E+15,4.503599627370496E+15]
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vsubpd %xmm1, %xmm0, %xmm0
; AVX1-NEXT: ret{{[l|q]}}
;
; AVX512F-LABEL: uitofp_v2i32_v2f64:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512F-NEXT: vcvtudq2pd %ymm0, %zmm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: ret{{[l|q]}}
;
; AVX512VL-LABEL: uitofp_v2i32_v2f64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VL-NEXT: ret{{[l|q]}}
;
; AVX512DQ-LABEL: uitofp_v2i32_v2f64:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512DQ-NEXT: vcvtudq2pd %ymm0, %zmm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-LABEL: uitofp_v2i32_v2f64:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i32(<2 x i32> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @sitofp_v2i64_v2f64(<2 x i64> %x) #0 {
; SSE-32-LABEL: sitofp_v2i64_v2f64:
; SSE-32: # %bb.0:
; SSE-32-NEXT: pushl %ebp
; SSE-32-NEXT: .cfi_def_cfa_offset 8
; SSE-32-NEXT: .cfi_offset %ebp, -8
; SSE-32-NEXT: movl %esp, %ebp
; SSE-32-NEXT: .cfi_def_cfa_register %ebp
; SSE-32-NEXT: andl $-8, %esp
; SSE-32-NEXT: subl $32, %esp
; SSE-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fstpl {{[0-9]+}}(%esp)
; SSE-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE-32-NEXT: fstpl (%esp)
; SSE-32-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-32-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
; SSE-32-NEXT: movl %ebp, %esp
; SSE-32-NEXT: popl %ebp
; SSE-32-NEXT: .cfi_def_cfa %esp, 4
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: sitofp_v2i64_v2f64:
; SSE-64: # %bb.0:
; SSE-64-NEXT: movq %xmm0, %rax
; SSE-64-NEXT: cvtsi2sd %rax, %xmm1
; SSE-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-64-NEXT: movq %xmm0, %rax
; SSE-64-NEXT: xorps %xmm0, %xmm0
; SSE-64-NEXT: cvtsi2sd %rax, %xmm0
; SSE-64-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
; SSE-64-NEXT: movapd %xmm1, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: sitofp_v2i64_v2f64:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: pushl %ebp
; SSE41-32-NEXT: .cfi_def_cfa_offset 8
; SSE41-32-NEXT: .cfi_offset %ebp, -8
; SSE41-32-NEXT: movl %esp, %ebp
; SSE41-32-NEXT: .cfi_def_cfa_register %ebp
; SSE41-32-NEXT: andl $-8, %esp
; SSE41-32-NEXT: subl $32, %esp
; SSE41-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-32-NEXT: movq %xmm0, {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fstpl {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fildll {{[0-9]+}}(%esp)
; SSE41-32-NEXT: fstpl (%esp)
; SSE41-32-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE41-32-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
; SSE41-32-NEXT: movl %ebp, %esp
; SSE41-32-NEXT: popl %ebp
; SSE41-32-NEXT: .cfi_def_cfa %esp, 4
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: sitofp_v2i64_v2f64:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: movq %xmm0, %rax
; SSE41-64-NEXT: cvtsi2sd %rax, %xmm1
; SSE41-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE41-64-NEXT: movq %xmm0, %rax
; SSE41-64-NEXT: xorps %xmm0, %xmm0
; SSE41-64-NEXT: cvtsi2sd %rax, %xmm0
; SSE41-64-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
; SSE41-64-NEXT: movapd %xmm1, %xmm0
; SSE41-64-NEXT: retq
;
; AVX-32-LABEL: sitofp_v2i64_v2f64:
; AVX-32: # %bb.0:
; AVX-32-NEXT: pushl %ebp
; AVX-32-NEXT: .cfi_def_cfa_offset 8
; AVX-32-NEXT: .cfi_offset %ebp, -8
; AVX-32-NEXT: movl %esp, %ebp
; AVX-32-NEXT: .cfi_def_cfa_register %ebp
; AVX-32-NEXT: andl $-8, %esp
; AVX-32-NEXT: subl $32, %esp
; AVX-32-NEXT: vmovlps %xmm0, {{[0-9]+}}(%esp)
; AVX-32-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX-32-NEXT: vmovlps %xmm0, {{[0-9]+}}(%esp)
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fstpl {{[0-9]+}}(%esp)
; AVX-32-NEXT: fildll {{[0-9]+}}(%esp)
; AVX-32-NEXT: fstpl (%esp)
; AVX-32-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-32-NEXT: vmovhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
; AVX-32-NEXT: movl %ebp, %esp
; AVX-32-NEXT: popl %ebp
; AVX-32-NEXT: .cfi_def_cfa %esp, 4
; AVX-32-NEXT: retl
;
; AVX-64-LABEL: sitofp_v2i64_v2f64:
; AVX-64: # %bb.0:
; AVX-64-NEXT: vpextrq $1, %xmm0, %rax
; AVX-64-NEXT: vcvtsi2sd %rax, %xmm1, %xmm1
; AVX-64-NEXT: vmovq %xmm0, %rax
; AVX-64-NEXT: vcvtsi2sd %rax, %xmm2, %xmm0
; AVX-64-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-64-NEXT: retq
;
; AVX512DQ-LABEL: sitofp_v2i64_v2f64:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovaps %xmm0, %xmm0
; AVX512DQ-NEXT: vcvtqq2pd %zmm0, %zmm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-LABEL: sitofp_v2i64_v2f64:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtqq2pd %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.sitofp.v2f64.v2i64(<2 x i64> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
define <2 x double> @uitofp_v2i64_v2f64(<2 x i64> %x) #0 {
; SSE-32-LABEL: uitofp_v2i64_v2f64:
; SSE-32: # %bb.0:
; SSE-32-NEXT: movdqa {{.*#+}} xmm1 = [4294967295,0,4294967295,0]
; SSE-32-NEXT: pand %xmm0, %xmm1
; SSE-32-NEXT: por {{\.LCPI.*}}, %xmm1
; SSE-32-NEXT: psrlq $32, %xmm0
; SSE-32-NEXT: por {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: subpd {{\.LCPI.*}}, %xmm0
; SSE-32-NEXT: addpd %xmm1, %xmm0
; SSE-32-NEXT: retl
;
; SSE-64-LABEL: uitofp_v2i64_v2f64:
; SSE-64: # %bb.0:
; SSE-64-NEXT: movdqa {{.*#+}} xmm1 = [4294967295,4294967295]
; SSE-64-NEXT: pand %xmm0, %xmm1
; SSE-64-NEXT: por {{.*}}(%rip), %xmm1
; SSE-64-NEXT: psrlq $32, %xmm0
; SSE-64-NEXT: por {{.*}}(%rip), %xmm0
; SSE-64-NEXT: subpd {{.*}}(%rip), %xmm0
; SSE-64-NEXT: addpd %xmm1, %xmm0
; SSE-64-NEXT: retq
;
; SSE41-32-LABEL: uitofp_v2i64_v2f64:
; SSE41-32: # %bb.0:
; SSE41-32-NEXT: movdqa {{.*#+}} xmm1 = [4294967295,0,4294967295,0]
; SSE41-32-NEXT: pand %xmm0, %xmm1
; SSE41-32-NEXT: por {{\.LCPI.*}}, %xmm1
; SSE41-32-NEXT: psrlq $32, %xmm0
; SSE41-32-NEXT: por {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: subpd {{\.LCPI.*}}, %xmm0
; SSE41-32-NEXT: addpd %xmm1, %xmm0
; SSE41-32-NEXT: retl
;
; SSE41-64-LABEL: uitofp_v2i64_v2f64:
; SSE41-64: # %bb.0:
; SSE41-64-NEXT: movdqa {{.*#+}} xmm1 = [4294967295,4294967295]
; SSE41-64-NEXT: pand %xmm0, %xmm1
; SSE41-64-NEXT: por {{.*}}(%rip), %xmm1
; SSE41-64-NEXT: psrlq $32, %xmm0
; SSE41-64-NEXT: por {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: subpd {{.*}}(%rip), %xmm0
; SSE41-64-NEXT: addpd %xmm1, %xmm0
; SSE41-64-NEXT: retq
;
; AVX1-32-LABEL: uitofp_v2i64_v2f64:
; AVX1-32: # %bb.0:
; AVX1-32-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-32-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; AVX1-32-NEXT: vpor {{\.LCPI.*}}, %xmm1, %xmm1
; AVX1-32-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX1-32-NEXT: vpor {{\.LCPI.*}}, %xmm0, %xmm0
; AVX1-32-NEXT: vsubpd {{\.LCPI.*}}, %xmm0, %xmm0
; AVX1-32-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX1-32-NEXT: retl
;
; AVX1-64-LABEL: uitofp_v2i64_v2f64:
; AVX1-64: # %bb.0:
; AVX1-64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-64-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; AVX1-64-NEXT: vpor {{.*}}(%rip), %xmm1, %xmm1
; AVX1-64-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX1-64-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
; AVX1-64-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
; AVX1-64-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX1-64-NEXT: retq
;
; AVX512F-32-LABEL: uitofp_v2i64_v2f64:
; AVX512F-32: # %bb.0:
; AVX512F-32-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-32-NEXT: vpblendd {{.*#+}} xmm1 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; AVX512F-32-NEXT: vpor {{\.LCPI.*}}, %xmm1, %xmm1
; AVX512F-32-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX512F-32-NEXT: vpor {{\.LCPI.*}}, %xmm0, %xmm0
; AVX512F-32-NEXT: vsubpd {{\.LCPI.*}}, %xmm0, %xmm0
; AVX512F-32-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX512F-32-NEXT: retl
;
; AVX512F-64-LABEL: uitofp_v2i64_v2f64:
; AVX512F-64: # %bb.0:
; AVX512F-64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX512F-64-NEXT: vpblendd {{.*#+}} xmm1 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; AVX512F-64-NEXT: vpor {{.*}}(%rip), %xmm1, %xmm1
; AVX512F-64-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX512F-64-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-64-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
; AVX512F-64-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX512F-64-NEXT: retq
;
; AVX512VL-32-LABEL: uitofp_v2i64_v2f64:
; AVX512VL-32: # %bb.0:
; AVX512VL-32-NEXT: vpand {{\.LCPI.*}}, %xmm0, %xmm1
; AVX512VL-32-NEXT: vpor {{\.LCPI.*}}, %xmm1, %xmm1
; AVX512VL-32-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX512VL-32-NEXT: vpor {{\.LCPI.*}}, %xmm0, %xmm0
; AVX512VL-32-NEXT: vsubpd {{\.LCPI.*}}, %xmm0, %xmm0
; AVX512VL-32-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX512VL-32-NEXT: retl
;
; AVX512VL-64-LABEL: uitofp_v2i64_v2f64:
; AVX512VL-64: # %bb.0:
; AVX512VL-64-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
; AVX512VL-64-NEXT: vpor {{.*}}(%rip), %xmm1, %xmm1
; AVX512VL-64-NEXT: vpsrlq $32, %xmm0, %xmm0
; AVX512VL-64-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-64-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
; AVX512VL-64-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX512VL-64-NEXT: retq
;
; AVX512DQ-LABEL: uitofp_v2i64_v2f64:
; AVX512DQ: # %bb.0:
; AVX512DQ-NEXT: vmovaps %xmm0, %xmm0
; AVX512DQ-NEXT: vcvtuqq2pd %zmm0, %zmm0
; AVX512DQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: ret{{[l|q]}}
;
; AVX512DQVL-LABEL: uitofp_v2i64_v2f64:
; AVX512DQVL: # %bb.0:
; AVX512DQVL-NEXT: vcvtuqq2pd %xmm0, %xmm0
; AVX512DQVL-NEXT: ret{{[l|q]}}
%result = call <2 x double> @llvm.experimental.constrained.uitofp.v2f64.v2i64(<2 x i64> %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret <2 x double> %result
}
attributes #0 = { strictfp }
Reference in New Issue View Git Blame Copy Permalink