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

[X86] Flesh out more of the avx512erintrin.h file. 

llvm-svn: 227719
This commit is contained in:
Craig Topper 2015-02-01 08:52:55 +00:00
parent 534a99d878
commit c4b852a909
1 changed files with 79 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
clang/lib/Headers/avx512erintrin.h
View File

@ -29,23 +29,61 @@
// rsqrt28
#define _mm512_rsqrt28_round_pd(A, R) __extension ({ \
#define _mm512_rsqrt28_round_pd(A, R) __extension__ ({ \
(__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
(__v8df)_mm512_setzero_pd(), \
(__mmask8)-1, (R)); })
#define _mm512_mask_rsqrt28_round_pd(S, M, A, R) __extension__ ({ \
(__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
(__v8df)(__m512d)(S), \
(__mmask8)(M), (R)); })
#define _mm512_maskz_rsqrt28_round_pd(M, A, R) __extension__ ({ \
(__m512d)__builtin_ia32_rsqrt28pd_mask((__v8df)(__m512d)(A), \
(__v8df)_mm512_setzero_pd(), \
(__mmask8)(M), (R)); })
#define _mm512_rsqrt28_pd(A) \
_mm512_rsqrt28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rsqrt28_pd(S, M, A) \
_mm512_mask_rsqrt28_round_pd(S, M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rsqrt28_pd(M, A) \
_mm512_maskz_rsqrt28_round_pd(M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rsqrt28_round_ps(A, R) __extension__ ({ \
(__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)_mm512_setzero_ps(), \
(__mmask16)-1, (R)); })
#define _mm512_mask_rsqrt28_round_ps(S, M, A, R) __extension__ ({ \
(__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)(__m512)(S), \
(__mmask16)(M), (R)); })
#define _mm512_maskz_rsqrt28_round_ps(M, A, R) __extension__ ({ \
(__m512)__builtin_ia32_rsqrt28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)_mm512_setzero_ps(), \
(__mmask16)(M), (R)); })
#define _mm512_rsqrt28_ps(A) \
_mm512_rsqrt28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rsqrt28_ps(S, M, A) \
_mm512_mask_rsqrt28_round_ps(S, M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rsqrt28_ps(M, A) \
_mm512_maskz_rsqrt28_round_ps(M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rsqrt28_round_ss(A, B, R) __extension__ ({ \
(__m128)__builtin_ia32_rsqrt28ss_mask((__v4sf)(__m128)(A), \
(__v4sf)(__m128(B), \
(__v4sf)(__m128)(B), \
(__v4sf)_mm_setzero_ps(), \
(__mmask8)-1, (R)); })
#define _mm_rsqrt28_round_sd (A, B, R) __extension__ ({ \
#define _mm_rsqrt28_round_sd(A, B, R) __extension__ ({ \
(__m128d)__builtin_ia32_rsqrt28sd_mask((__v2df)(__m128d)(A), \
(__v2df)(__m128d)(B), \
(__v2df)_mm_setzero_pd(), \
@ -58,11 +96,49 @@
(__v8df)_mm512_setzero_pd(), \
(__mmask8)-1, (R)); })
#define _mm512_mask_rcp28_round_pd(S, M, A, R) __extension__ ({ \
(__m512d)__builtin_ia32_rcp28pd_mask((__v8df)(__m512d)(A), \
(__v8df)(__m512d)(S), \
(__mmask8)(M), (R)); })
#define _mm512_maskz_rcp28_round_pd(M, A, R) __extension__ ({ \
(__m512d)__builtin_ia32_rcp28pd_mask((__v8df)(__m512d)(A), \
(__v8df)_mm512_setzero_pd(), \
(__mmask8)(M), (R)); })
#define _mm512_rcp28_pd(A) \
_mm512_rcp28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rcp28_pd(S, M, A) \
_mm512_mask_rcp28_round_pd(S, M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rcp28_pd(M, A) \
_mm512_maskz_rcp28_round_pd(M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rcp28_round_ps(A, R) __extension__ ({ \
(__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)_mm512_setzero_ps(), \
(__mmask16)-1, (R)); })
#define _mm512_mask_rcp28_round_ps(S, M, A, R) __extension__ ({ \
(__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)(__m512)(S), \
(__mmask16)(M), (R)); })
#define _mm512_maskz_rcp28_round_ps(M, A, R) __extension__ ({ \
(__m512)__builtin_ia32_rcp28ps_mask((__v16sf)(__m512)(A), \
(__v16sf)_mm512_setzero_ps(), \
(__mmask16)(M), (R)); })
#define _mm512_rcp28_ps(A) \
_mm512_rcp28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rcp28_ps(S, M, A) \
_mm512_mask_rcp28_round_ps(S, M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rcp28_ps(M, A) \
_mm512_maskz_rcp28_round_ps(M, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rcp28_round_ss(A, B, R) __extension__ ({ \
(__m128) __builtin_ia32_rcp28ss_mask ((__v4sf)(__m128)(A), \
(__v4sf)(__m128)(B), \