mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-10 07:10:06 +00:00
c9a8c526ac
Here is implementation of vectorized sincos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * NEWS: Mention addition of x86_64 vector sincos. * bits/libm-simd-decl-stubs.h: Added stubs for sincos. * math/math.h (__MATHDECL_VEC): New macro. * math/bits/mathcalls.h: Added sincos declaration with __MATHDECL_VEC. * math/gen-libm-have-vector-test.sh: Added generation of sincos wrapper declaration under condition. * math/test-vec-loop.h (TEST_VEC_LOOP): Refactored. * math/test-double-vlen2.h: Added wrapper for sincos tests, reflected TEST_VEC_LOOP change. * math/test-double-vlen4.h: Likewise. * math/test-double-vlen8.h: Likewise. * math/test-float-vlen16.h: Reflected TEST_VEC_LOOP change. * math/test-float-vlen4.h: Likewise. * math/test-float-vlen8.h: Likewise. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added. * sysdeps/x86/fpu/bits/math-vector.h: Added sincos SIMD declaration. * 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/multiarch/svml_d_sincos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_sincos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: Added wrappers for sincos. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Vector sincos tests. * sysdeps/x86_64/fpu/test-double-vlen2.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-avx2-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-avx2.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen4.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen8-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-double-vlen8.c: Likewise.
91 lines
3.0 KiB
C
91 lines
3.0 KiB
C
/* Definitions for double vector tests with vector length 4.
|
|
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/>. */
|
|
|
|
#define FLOAT double
|
|
#define FUNC(function) function
|
|
#define TEST_MSG "testing double vector math (without inline functions)\n"
|
|
#define MATHCONST(x) x
|
|
#define CHOOSE(Clongdouble,Cdouble,Cfloat,Cinlinelongdouble,Cinlinedouble,Cinlinefloat) Cdouble
|
|
#define PRINTF_EXPR "e"
|
|
#define PRINTF_XEXPR "a"
|
|
#define PRINTF_NEXPR "f"
|
|
#define TEST_DOUBLE 1
|
|
#define TEST_MATHVEC 1
|
|
|
|
#ifndef __NO_MATH_INLINES
|
|
# define __NO_MATH_INLINES
|
|
#endif
|
|
|
|
#define EXCEPTION_TESTS_double 0
|
|
#define ROUNDING_TESTS_double(MODE) ((MODE) == FE_TONEAREST)
|
|
|
|
#define CNCT(x, y) x ## y
|
|
#define CONCAT(a, b) CNCT (a, b)
|
|
|
|
#define VEC_SUFF _vlen4
|
|
#define WRAPPER_NAME(function) CONCAT (function, VEC_SUFF)
|
|
|
|
#define FUNC_TEST(function) function ## _VEC_SUFF
|
|
|
|
#define WRAPPER_DECL(function) extern FLOAT function (FLOAT);
|
|
#define WRAPPER_DECL_ff(function) extern FLOAT function (FLOAT, FLOAT);
|
|
#define WRAPPER_DECL_fFF(function) extern void function (FLOAT, FLOAT *, FLOAT *);
|
|
|
|
// Wrapper from scalar to vector function with vector length 4.
|
|
#define VECTOR_WRAPPER(scalar_func, vector_func) \
|
|
extern VEC_TYPE vector_func (VEC_TYPE); \
|
|
FLOAT scalar_func (FLOAT x) \
|
|
{ \
|
|
int i; \
|
|
VEC_TYPE mx; \
|
|
INIT_VEC_LOOP (mx, x, 4); \
|
|
VEC_TYPE mr = vector_func (mx); \
|
|
TEST_VEC_LOOP (mr, 4); \
|
|
return ((FLOAT) mr[0]); \
|
|
}
|
|
|
|
// Wrapper from scalar 2 argument function to vector one.
|
|
#define VECTOR_WRAPPER_ff(scalar_func, vector_func) \
|
|
extern VEC_TYPE vector_func (VEC_TYPE, VEC_TYPE); \
|
|
FLOAT scalar_func (FLOAT x, FLOAT y) \
|
|
{ \
|
|
int i; \
|
|
VEC_TYPE mx, my; \
|
|
INIT_VEC_LOOP (mx, x, 4); \
|
|
INIT_VEC_LOOP (my, y, 4); \
|
|
VEC_TYPE mr = vector_func (mx, my); \
|
|
TEST_VEC_LOOP (mr, 4); \
|
|
return ((FLOAT) mr[0]); \
|
|
}
|
|
|
|
// Wrapper from scalar 3 argument function to vector one.
|
|
#define VECTOR_WRAPPER_fFF(scalar_func, vector_func) \
|
|
extern void vector_func (VEC_TYPE, VEC_TYPE *, VEC_TYPE *); \
|
|
void scalar_func (FLOAT x, FLOAT * r, FLOAT * r1) \
|
|
{ \
|
|
int i; \
|
|
VEC_TYPE mx, mr, mr1; \
|
|
INIT_VEC_LOOP (mx, x, 4); \
|
|
vector_func (mx, &mr, &mr1); \
|
|
TEST_VEC_LOOP (mr, 4); \
|
|
TEST_VEC_LOOP (mr1, 4); \
|
|
*r = (FLOAT) mr[0]; \
|
|
*r1 = (FLOAT) mr1[0]; \
|
|
return; \
|
|
}
|