AuroraMiddleware/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2024-11-22 13:00:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
4d8965f130
glibc/sysdeps/aarch64/fpu/test-float-sve-wrappers.c

71 lines
3.4 KiB
C
Raw Normal View History

Enable libmvec support for AArch64 This patch enables libmvec on AArch64. The proposed change is mainly implementing build infrastructure to add the new routines to ABI, tests and benchmarks. I have demonstrated how this all fits together by adding implementations for vector cos, in both single and double precision, targeting both Advanced SIMD and SVE. The implementations of the routines themselves are just loops over the scalar routine from libm for now, as we are more concerned with getting the plumbing right at this point. We plan to contribute vector routines from the Arm Optimized Routines repo that are compliant with requirements described in the libmvec wiki. Building libmvec requires minimum GCC 10 for SVE ACLE. To avoid raising the minimum GCC by such a big jump, we allow users to disable libmvec if their compiler is too old. Note that at this point users have to manually call the vector math functions. This seems to be acceptable to some downstream users. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-04-12 13:37:49 +00:00
/* Scalar wrappers for single-precision SVE vector math functions.
Update copyright dates with scripts/update-copyrights
2024-01-01 18:12:26 +00:00
Copyright (C) 2023-2024 Free Software Foundation, Inc.
Enable libmvec support for AArch64 This patch enables libmvec on AArch64. The proposed change is mainly implementing build infrastructure to add the new routines to ABI, tests and benchmarks. I have demonstrated how this all fits together by adding implementations for vector cos, in both single and double precision, targeting both Advanced SIMD and SVE. The implementations of the routines themselves are just loops over the scalar routine from libm for now, as we are more concerned with getting the plumbing right at this point. We plan to contribute vector routines from the Arm Optimized Routines repo that are compliant with requirements described in the libmvec wiki. Building libmvec requires minimum GCC 10 for SVE ACLE. To avoid raising the minimum GCC by such a big jump, we allow users to disable libmvec if their compiler is too old. Note that at this point users have to manually call the vector math functions. This seems to be acceptable to some downstream users. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-04-12 13:37:49 +00:00
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
<https://www.gnu.org/licenses/>. */
#include <arm_sve.h>
#include "test-float-sve.h"
/* Wrapper from scalar to SVE function. Cannot just use VECTOR_WRAPPER due to
predication. */
#define SVE_VECTOR_WRAPPER(scalar_func, vector_func) \
extern VEC_TYPE vector_func (VEC_TYPE, svbool_t); \
FLOAT scalar_func (FLOAT x) \
{ \
VEC_TYPE mx = svdup_n_f32 (x); \
VEC_TYPE mr = vector_func (mx, svptrue_b32 ()); \
return svlastb_f32 (svptrue_b32 (), mr); \
}
aarch64: Add vector implementations of atan2 routines
2023-11-03 12:12:22 +00:00
#define SVE_VECTOR_WRAPPER_ff(scalar_func, vector_func) \
extern VEC_TYPE vector_func (VEC_TYPE, VEC_TYPE, svbool_t); \
FLOAT scalar_func (FLOAT x, FLOAT y) \
{ \
VEC_TYPE mx = svdup_n_f32 (x); \
VEC_TYPE my = svdup_n_f32 (y); \
VEC_TYPE mr = vector_func (mx, my, svptrue_b32 ()); \
return svlastb_f32 (svptrue_b32 (), mr); \
}
aarch64: Add vector implementations of acos routines
2023-11-03 12:12:20 +00:00
SVE_VECTOR_WRAPPER (acosf_sve, _ZGVsMxv_acosf)
aarch64/fpu: Add vector variants of acosh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:40 +00:00
SVE_VECTOR_WRAPPER (acoshf_sve, _ZGVsMxv_acoshf)
aarch64: Add vector implementations of asin routines
2023-11-03 12:12:19 +00:00
SVE_VECTOR_WRAPPER (asinf_sve, _ZGVsMxv_asinf)
aarch64/fpu: Add vector variants of asinh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:41 +00:00
SVE_VECTOR_WRAPPER (asinhf_sve, _ZGVsMxv_asinhf)
aarch64: Add vector implementations of atan routines
2023-11-03 12:12:21 +00:00
SVE_VECTOR_WRAPPER (atanf_sve, _ZGVsMxv_atanf)
aarch64/fpu: Add vector variants of atanh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-04-03 11:13:53 +00:00
SVE_VECTOR_WRAPPER (atanhf_sve, _ZGVsMxv_atanhf)
aarch64: Add vector implementations of atan2 routines
2023-11-03 12:12:22 +00:00
SVE_VECTOR_WRAPPER_ff (atan2f_sve, _ZGVsMxvv_atan2f)
aarch64/fpu: Add vector variants of cbrt Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-04-30 12:49:59 +00:00
SVE_VECTOR_WRAPPER (cbrtf_sve, _ZGVsMxv_cbrtf)
Enable libmvec support for AArch64 This patch enables libmvec on AArch64. The proposed change is mainly implementing build infrastructure to add the new routines to ABI, tests and benchmarks. I have demonstrated how this all fits together by adding implementations for vector cos, in both single and double precision, targeting both Advanced SIMD and SVE. The implementations of the routines themselves are just loops over the scalar routine from libm for now, as we are more concerned with getting the plumbing right at this point. We plan to contribute vector routines from the Arm Optimized Routines repo that are compliant with requirements described in the libmvec wiki. Building libmvec requires minimum GCC 10 for SVE ACLE. To avoid raising the minimum GCC by such a big jump, we allow users to disable libmvec if their compiler is too old. Note that at this point users have to manually call the vector math functions. This seems to be acceptable to some downstream users. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-04-12 13:37:49 +00:00
SVE_VECTOR_WRAPPER (cosf_sve, _ZGVsMxv_cosf)
aarch64/fpu: Add vector variants of cosh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:39 +00:00
SVE_VECTOR_WRAPPER (coshf_sve, _ZGVsMxv_coshf)
aarch64/fpu: Add vector variants of erf Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:38 +00:00
SVE_VECTOR_WRAPPER (erff_sve, _ZGVsMxv_erff)
aarch64/fpu: Add vector variants of erfc Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:45 +00:00
SVE_VECTOR_WRAPPER (erfcf_sve, _ZGVsMxv_erfcf)
aarch64: Add vector implementations of exp routines Optimised implementations for single and double precision, Advanced SIMD and SVE, copied from Arm Optimized Routines. As previously, data tables are used via a barrier to prevent overly aggressive constant inlining. Special-case handlers are marked NOINLINE to avoid incurring the penalty of switching call standards unnecessarily. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-06-28 11:19:39 +00:00
SVE_VECTOR_WRAPPER (expf_sve, _ZGVsMxv_expf)
aarch64: Add vector implementations of exp10 routines Double-precision routines either reuse the exp table (AdvSIMD) or use SVE FEXPA intruction.
2023-10-05 16:10:52 +00:00
SVE_VECTOR_WRAPPER (exp10f_sve, _ZGVsMxv_exp10f)
aarch64: Add vector implementations of exp2 routines Some routines reuse table from v_exp_data.c
2023-10-05 16:10:49 +00:00
SVE_VECTOR_WRAPPER (exp2f_sve, _ZGVsMxv_exp2f)
aarch64: Add vector implementations of expm1 routines May discard sign of 0 - auto tests for -0 and -0x1p-10000 updated accordingly.
2023-11-16 13:24:18 +00:00
SVE_VECTOR_WRAPPER (expm1f_sve, _ZGVsMxv_expm1f)
aarch64/fpu: Add vector variants of hypot Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-04-30 12:49:58 +00:00
SVE_VECTOR_WRAPPER_ff (hypotf_sve, _ZGVsMxvv_hypotf)
aarch64: Add vector implementations of log routines Optimised implementations for single and double precision, Advanced SIMD and SVE, copied from Arm Optimized Routines. Log lookup table added as HIDDEN symbol to allow it to be shared between AdvSIMD and SVE variants. As previously, data tables are used via a barrier to prevent overly aggressive constant inlining. Special-case handlers are marked NOINLINE to avoid incurring the penalty of switching call standards unnecessarily. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-06-28 11:19:38 +00:00
SVE_VECTOR_WRAPPER (logf_sve, _ZGVsMxv_logf)
aarch64: Add vector implementations of log10 routines A table is also added, which is shared between AdvSIMD and SVE log10.
2023-10-05 16:10:51 +00:00
SVE_VECTOR_WRAPPER (log10f_sve, _ZGVsMxv_log10f)
aarch64: Add vector implementations of log1p routines May discard sign of zero.
2023-11-03 12:12:23 +00:00
SVE_VECTOR_WRAPPER (log1pf_sve, _ZGVsMxv_log1pf)
aarch64: Add vector implementations of log2 routines A table is also added, which is shared between AdvSIMD and SVE log2.
2023-10-05 16:10:50 +00:00
SVE_VECTOR_WRAPPER (log2f_sve, _ZGVsMxv_log2f)
aarch64/fpu: Add vector variants of pow Plus a small amount of moving includes around in order to be able to remove duplicate definition of asuint64. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-05-16 08:21:24 +00:00
SVE_VECTOR_WRAPPER_ff (powf_sve, _ZGVsMxvv_powf)
aarch64: Add vector implementations of sin routines Optimised implementations for single and double precision, Advanced SIMD and SVE, copied from Arm Optimized Routines. As previously, data tables are used via a barrier to prevent overly aggressive constant inlining. Special-case handlers are marked NOINLINE to avoid incurring the penalty of switching call standards unnecessarily. Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2023-06-28 11:19:37 +00:00
SVE_VECTOR_WRAPPER (sinf_sve, _ZGVsMxv_sinf)
aarch64/fpu: Add vector variants of sinh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-04-03 11:15:41 +00:00
SVE_VECTOR_WRAPPER (sinhf_sve, _ZGVsMxv_sinhf)
aarch64: Add vector implementations of tan routines This includes some utility headers for evaluating polynomials using various schemes.
2023-10-05 16:10:48 +00:00
SVE_VECTOR_WRAPPER (tanf_sve, _ZGVsMxv_tanf)
aarch64/fpu: Add vector variants of tanh Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
2024-02-20 16:59:44 +00:00
SVE_VECTOR_WRAPPER (tanhf_sve, _ZGVsMxv_tanhf)
Reference in New Issue Copy Permalink