OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[Clang][AVX512][intrinsics] Adding missing intrinsics div_pd and div_ps 

Differential Revision: http://reviews.llvm.org/D20626

llvm-svn: 272658
This commit is contained in:
Michael Zuckerman 2016-06-14 12:38:58 +00:00
parent f9c111bd07
commit 223676d2cc
2 changed files with 25 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
clang/lib/Headers/avx512fintrin.h
View File

@ -2446,6 +2446,12 @@ _mm_maskz_div_sd(__mmask8 __U,__m128d __A, __m128d __B) {
(__v2df)_mm_setzero_pd(), \ (__v2df)_mm_setzero_pd(), \
(__mmask8)(U), (int)(R)); }) (__mmask8)(U), (int)(R)); })
static __inline __m512d __DEFAULT_FN_ATTRS
_mm512_div_pd(__m512d __a, __m512d __b)
{
return (__m512d)((__v8df)__a/(__v8df)__b);
}
static __inline__ __m512d __DEFAULT_FN_ATTRS static __inline__ __m512d __DEFAULT_FN_ATTRS
_mm512_mask_div_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) { _mm512_mask_div_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) {
return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __A, return (__m512d) __builtin_ia32_divpd512_mask ((__v8df) __A,
@ -2465,6 +2471,12 @@ _mm512_maskz_div_pd(__mmask8 __U, __m512d __A, __m512d __B) {
_MM_FROUND_CUR_DIRECTION); _MM_FROUND_CUR_DIRECTION);
} }
static __inline __m512 __DEFAULT_FN_ATTRS
_mm512_div_ps(__m512 __a, __m512 __b)
{
return (__m512)((__v16sf)__a/(__v16sf)__b);
}
static __inline__ __m512 __DEFAULT_FN_ATTRS static __inline__ __m512 __DEFAULT_FN_ATTRS
_mm512_mask_div_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) { _mm512_mask_div_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A, return (__m512) __builtin_ia32_divps512_mask ((__v16sf) __A,

16
clang/test/CodeGen/avx512f-builtins.c
View File

@ -1972,10 +1972,15 @@ __m512d test_mm512_maskz_div_round_pd(__mmask8 __U, __m512d __A, __m512d __B) {
// CHECK: @llvm.x86.avx512.mask.div.pd.512 // CHECK: @llvm.x86.avx512.mask.div.pd.512
return _mm512_maskz_div_round_pd(__U,__A,__B,_MM_FROUND_TO_NEAREST_INT); return _mm512_maskz_div_round_pd(__U,__A,__B,_MM_FROUND_TO_NEAREST_INT);
} }
__m512d test_mm512_mask_div_pd(__m512d __W, __mmask8 __U, __m512d __A, __m512d __B) { __m512d test_mm512_div_pd(__m512d __a, __m512d __b) {
// CHECK-LABEL: @test_mm512_mask_div_pd // CHECK-LABLE: @test_mm512_div_pd
// CHECK: fdiv <8 x double>
return _mm512_div_pd(__a,__b);
}
__m512d test_mm512_mask_div_pd(__m512d __w, __mmask8 __u, __m512d __a, __m512d __b) {
// CHECK-LABLE: @test_mm512_mask_div_pd
// CHECK: @llvm.x86.avx512.mask.div.pd.512 // CHECK: @llvm.x86.avx512.mask.div.pd.512
return _mm512_mask_div_pd(__W,__U,__A,__B); return _mm512_mask_div_pd(__w,__u,__a,__b);
} }
__m512d test_mm512_maskz_div_pd(__mmask8 __U, __m512d __A, __m512d __B) { __m512d test_mm512_maskz_div_pd(__mmask8 __U, __m512d __A, __m512d __B) {
// CHECK-LABEL: @test_mm512_maskz_div_pd // CHECK-LABEL: @test_mm512_maskz_div_pd
@ -1997,6 +2002,11 @@ __m512 test_mm512_maskz_div_round_ps(__mmask16 __U, __m512 __A, __m512 __B) {
// CHECK: @llvm.x86.avx512.mask.div.ps.512 // CHECK: @llvm.x86.avx512.mask.div.ps.512
return _mm512_maskz_div_round_ps(__U,__A,__B,_MM_FROUND_TO_NEAREST_INT); return _mm512_maskz_div_round_ps(__U,__A,__B,_MM_FROUND_TO_NEAREST_INT);
} }
__m512 test_mm512_div_ps(__m512 __A, __m512 __B) {
// CHECK-LABEL: @test_mm512_div_ps
// CHECK: fdiv <16 x float>
return _mm512_div_ps(__A,__B);
}
__m512 test_mm512_mask_div_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) { __m512 test_mm512_mask_div_ps(__m512 __W, __mmask16 __U, __m512 __A, __m512 __B) {
// CHECK-LABEL: @test_mm512_mask_div_ps // CHECK-LABEL: @test_mm512_mask_div_ps
// CHECK: @llvm.x86.avx512.mask.div.ps.512 // CHECK: @llvm.x86.avx512.mask.div.ps.512