mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-28 21:41:08 +00:00
8aa92022e2
Here is implementation of vectorized powf containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for powf. * sysdeps/x86_64/fpu/Makefile (libmvec-support): Added new files. * sysdeps/x86_64/fpu/Versions: New versions added. * sysdeps/x86_64/fpu/libm-test-ulps: Regenerated. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S: New file. * sysdeps/x86_64/fpu/svml_s_powf16_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf4_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf8_core.S: New file. * sysdeps/x86_64/fpu/svml_s_powf8_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_s_powf_data.S: New file. * sysdeps/x86_64/fpu/svml_s_powf_data.h: New file. * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Vector powf tests. * sysdeps/x86_64/fpu/test-float-vlen16.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8.c: Likewise. * math/test-float-vlen16.h: Fixed 2 argument macro. * math/test-float-vlen4.h: Likewise. * math/test-float-vlen8.h: Likewise. * NEWS: Mention addition of x86_64 vector powf.
77 lines
2.6 KiB
C
77 lines
2.6 KiB
C
/* Offsets for data table for function powf.
|
|
Copyright (C) 2014-2015 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#ifndef S_POWF_DATA_H
|
|
#define S_POWF_DATA_H
|
|
|
|
#define _Log2Rcp_lookup -4218496
|
|
#define _NMINNORM 0
|
|
#define _NMAXVAL 64
|
|
#define _INF 128
|
|
#define _ABSMASK 192
|
|
#define _DOMAINRANGE 256
|
|
#define _Log_HA_table 320
|
|
#define _Log_LA_table 8576
|
|
#define _poly_coeff_1 12736
|
|
#define _poly_coeff_2 12800
|
|
#define _poly_coeff_3 12864
|
|
#define _poly_coeff_4 12928
|
|
#define _ExpMask 12992
|
|
#define _Two10 13056
|
|
#define _MinNorm 13120
|
|
#define _MaxNorm 13184
|
|
#define _HalfMask 13248
|
|
#define _One 13312
|
|
#define _L2H 13376
|
|
#define _L2L 13440
|
|
#define _Threshold 13504
|
|
#define _Bias 13568
|
|
#define _Bias1 13632
|
|
#define _L2 13696
|
|
#define _dInfs 13760
|
|
#define _dOnes 13824
|
|
#define _dZeros 13888
|
|
#define __dbT 13952
|
|
#define __dbInvLn2 30400
|
|
#define __dbShifter 30464
|
|
#define __dbHALF 30528
|
|
#define __dbC1 30592
|
|
#define __lbLOWKBITS 30656
|
|
#define __iAbsMask 30720
|
|
#define __iDomainRange 30784
|
|
|
|
.macro double_vector offset value
|
|
.if .-__svml_spow_data != \offset
|
|
.err
|
|
.endif
|
|
.rept 8
|
|
.quad \value
|
|
.endr
|
|
.endm
|
|
|
|
.macro float_vector offset value
|
|
.if .-__svml_spow_data != \offset
|
|
.err
|
|
.endif
|
|
.rept 16
|
|
.long \value
|
|
.endr
|
|
.endm
|
|
|
|
#endif
|