glibc/sysdeps/x86_64/fpu/svml_d_wrapper_impl.h

291 lines
8.9 KiB
C
Raw Normal View History

Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
/* Wrapper implementations of vector math functions.
Copyright (C) 2014-2021 Free Software Foundation, Inc.
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +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
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
<https://www.gnu.org/licenses/>. */
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
/* SSE2 ISA version as wrapper to scalar. */
.macro WRAPPER_IMPL_SSE2 callee
subq $40, %rsp
cfi_adjust_cfa_offset(40)
movaps %xmm0, (%rsp)
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
movsd %xmm0, 16(%rsp)
movsd 8(%rsp), %xmm0
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
movsd 16(%rsp), %xmm1
movsd %xmm0, 24(%rsp)
unpcklpd %xmm0, %xmm1
movaps %xmm1, %xmm0
addq $40, %rsp
cfi_adjust_cfa_offset(-40)
ret
.endm
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
/* 2 argument SSE2 ISA version as wrapper to scalar. */
.macro WRAPPER_IMPL_SSE2_ff callee
subq $56, %rsp
cfi_adjust_cfa_offset(56)
movaps %xmm0, (%rsp)
movaps %xmm1, 16(%rsp)
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
movsd %xmm0, 32(%rsp)
movsd 8(%rsp), %xmm0
movsd 24(%rsp), %xmm1
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
movsd 32(%rsp), %xmm1
movsd %xmm0, 40(%rsp)
unpcklpd %xmm0, %xmm1
movaps %xmm1, %xmm0
addq $56, %rsp
cfi_adjust_cfa_offset(-56)
ret
.endm
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
/* 3 argument SSE2 ISA version as wrapper to scalar. */
.macro WRAPPER_IMPL_SSE2_fFF callee
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
pushq %rbx
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbx, 0)
movq %rdi, %rbp
movq %rsi, %rbx
subq $40, %rsp
cfi_adjust_cfa_offset(40)
leaq 16(%rsp), %rsi
leaq 24(%rsp), %rdi
movaps %xmm0, (%rsp)
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
leaq 16(%rsp), %rsi
leaq 24(%rsp), %rdi
movsd 24(%rsp), %xmm0
movapd (%rsp), %xmm1
movsd %xmm0, 0(%rbp)
unpckhpd %xmm1, %xmm1
movsd 16(%rsp), %xmm0
movsd %xmm0, (%rbx)
movapd %xmm1, %xmm0
Use JUMPTARGET in x86-64 mathvec When PLT may be used, JUMPTARGET should be used instead calling the function directly. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S (_ZGVbN2v_cos_sse4): Use JUMPTARGET to call cos. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S (_ZGVdN4v_cos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S (_ZGVdN4v_cos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp2_core_sse4.S (_ZGVbN2v_exp_sse4): Use JUMPTARGET to call exp. * sysdeps/x86_64/fpu/multiarch/svml_d_exp4_core_avx2.S (_ZGVdN4v_exp_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S (_ZGVdN4v_exp): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log2_core_sse4.S (_ZGVbN2v_log_sse4): Use JUMPTARGET to call log. * sysdeps/x86_64/fpu/multiarch/svml_d_log4_core_avx2.S (_ZGVdN4v_log_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S (_ZGVdN4v_log): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S (_ZGVbN2vv_pow_sse4): Use JUMPTARGET to call pow. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S (_ZGVdN4vv_pow_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S (_ZGVdN4vv_pow): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin2_core_sse4.S (_ZGVbN2v_sin_sse4): Use JUMPTARGET to call sin. * sysdeps/x86_64/fpu/multiarch/svml_d_sin4_core_avx2.S (_ZGVdN4v_sin_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S (_ZGVdN4v_sin): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S (_ZGVbN2vvv_sincos_sse4): Use JUMPTARGET to call sin and cos. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S (_ZGVdN4vvv_sincos_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S (_ZGVdN4vvv_sincos): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S (_ZGVdN8v_cosf): Use JUMPTARGET to call cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf4_core_sse4.S (_ZGVbN4v_cosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf8_core_avx2.S (_ZGVdN8v_cosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S (_ZGVdN8v_expf): Use JUMPTARGET to call expf. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S (_ZGVbN4v_expf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S (_ZGVdN8v_expf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S (_ZGVdN8v_logf): Use JUMPTARGET to call logf. * sysdeps/x86_64/fpu/multiarch/svml_s_logf4_core_sse4.S (_ZGVbN4v_logf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf8_core_avx2.S (_ZGVdN8v_logf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call powf. * sysdeps/x86_64/fpu/multiarch/svml_s_powf4_core_sse4.S (_ZGVbN4vv_powf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf8_core_avx2.S (_ZGVdN8vv_powf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S (_ZGVdN8vv_powf): Use JUMPTARGET to call sinf and cosf. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S (_ZGVbN4vvv_sincosf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S (_ZGVdN8vvv_sincosf_avx2): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S (_ZGVdN8v_sinf): Use JUMPTARGET to call sinf. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S (_ZGVbN4v_sinf_sse4): Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S (_ZGVdN8v_sinf_avx2): Likewise. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h (WRAPPER_IMPL_SSE2): Use JUMPTARGET to call callee. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h (WRAPPER_IMPL_SSE2): Likewise. (WRAPPER_IMPL_SSE2_ff): Likewise. (WRAPPER_IMPL_SSE2_fFF): Likewise. (WRAPPER_IMPL_AVX): Likewise. (WRAPPER_IMPL_AVX_ff): Likewise. (WRAPPER_IMPL_AVX_fFF): Likewise. (WRAPPER_IMPL_AVX512): Likewise. (WRAPPER_IMPL_AVX512_ff): Likewise. (WRAPPER_IMPL_AVX512_fFF): Likewise.
2016-03-16 21:24:01 +00:00
call JUMPTARGET(\callee)
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
movsd 24(%rsp), %xmm0
movsd %xmm0, 8(%rbp)
movsd 16(%rsp), %xmm0
movsd %xmm0, 8(%rbx)
addq $40, %rsp
cfi_adjust_cfa_offset(-40)
popq %rbx
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbx)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
/* AVX/AVX2 ISA version as wrapper to SSE ISA version. */
.macro WRAPPER_IMPL_AVX callee
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-32, %rsp
subq $32, %rsp
vextractf128 $1, %ymm0, (%rsp)
vzeroupper
call HIDDEN_JUMPTARGET(\callee)
vmovapd %xmm0, 16(%rsp)
vmovaps (%rsp), %xmm0
call HIDDEN_JUMPTARGET(\callee)
vmovapd %xmm0, %xmm1
vmovapd 16(%rsp), %xmm0
vinsertf128 $1, %xmm1, %ymm0, %ymm0
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
/* 2 argument AVX/AVX2 ISA version as wrapper to SSE ISA version. */
.macro WRAPPER_IMPL_AVX_ff callee
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-32, %rsp
subq $64, %rsp
vextractf128 $1, %ymm0, 16(%rsp)
vextractf128 $1, %ymm1, (%rsp)
vzeroupper
call HIDDEN_JUMPTARGET(\callee)
vmovaps %xmm0, 32(%rsp)
vmovaps 16(%rsp), %xmm0
vmovaps (%rsp), %xmm1
call HIDDEN_JUMPTARGET(\callee)
vmovaps %xmm0, %xmm1
vmovaps 32(%rsp), %xmm0
vinsertf128 $1, %xmm1, %ymm0, %ymm0
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
/* 3 argument AVX/AVX2 ISA version as wrapper to SSE ISA version. */
.macro WRAPPER_IMPL_AVX_fFF callee
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-32, %rsp
pushq %r13
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%r13, 0)
pushq %r14
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%r14, 0)
subq $48, %rsp
movq %rsi, %r14
movq %rdi, %r13
vextractf128 $1, %ymm0, 32(%rsp)
vzeroupper
call HIDDEN_JUMPTARGET(\callee)
vmovaps 32(%rsp), %xmm0
lea (%rsp), %rdi
lea 16(%rsp), %rsi
call HIDDEN_JUMPTARGET(\callee)
vmovapd (%rsp), %xmm0
vmovapd 16(%rsp), %xmm1
vmovapd %xmm0, 16(%r13)
vmovapd %xmm1, 16(%r14)
addq $48, %rsp
popq %r14
cfi_adjust_cfa_offset (-8)
cfi_restore (%r14)
popq %r13
cfi_adjust_cfa_offset (-8)
cfi_restore (%r13)
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
/* AVX512 ISA version as wrapper to AVX2 ISA version. */
.macro WRAPPER_IMPL_AVX512 callee
pushq %rbp
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
subq $128, %rsp
vmovups %zmm0, (%rsp)
vmovupd (%rsp), %ymm0
call HIDDEN_JUMPTARGET(\callee)
vmovupd %ymm0, 64(%rsp)
vmovupd 32(%rsp), %ymm0
call HIDDEN_JUMPTARGET(\callee)
vmovupd %ymm0, 96(%rsp)
vmovups 64(%rsp), %zmm0
movq %rbp, %rsp
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
cfi_def_cfa_register (%rsp)
popq %rbp
Start of series of patches with x86_64 vector math functions. Here is implementation of cos containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI which had been discussed in <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. Vector math library build and ABI testing enabled by default for x86_64. * sysdeps/x86_64/fpu/Makefile: New file. * sysdeps/x86_64/fpu/Versions: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.S: New file. * sysdeps/x86_64/fpu/svml_d_cos_data.h: New file. * sysdeps/x86_64/fpu/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_cos4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_wrapper_impl.h: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added build of SSE, AVX2 and AVX512 IFUNC versions. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for cos. * math/bits/mathcalls.h: Added cos declaration with __MATHCALL_VEC. * sysdeps/x86_64/configure.ac: Options for libmvec build. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/sysdep.h (cfi_offset_rel_rsp): New macro. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New file. * manual/install.texi (Configuring and compiling): Document --disable-mathvec. * INSTALL: Regenerated. * NEWS: Mention addition of libmvec and x86_64 vector cos.
2015-06-09 11:25:49 +00:00
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
/* 2 argument AVX512 ISA version as wrapper to AVX2 ISA version. */
.macro WRAPPER_IMPL_AVX512_ff callee
pushq %rbp
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
subq $192, %rsp
vmovups %zmm0, (%rsp)
vmovups %zmm1, 64(%rsp)
vmovupd (%rsp), %ymm0
vmovupd 64(%rsp), %ymm1
call HIDDEN_JUMPTARGET(\callee)
vmovupd %ymm0, 128(%rsp)
vmovupd 32(%rsp), %ymm0
vmovupd 96(%rsp), %ymm1
call HIDDEN_JUMPTARGET(\callee)
vmovupd %ymm0, 160(%rsp)
vmovups 128(%rsp), %zmm0
movq %rbp, %rsp
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
cfi_def_cfa_register (%rsp)
popq %rbp
Vector pow for x86_64 and tests. Here is implementation of vectorized pow containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * bits/libm-simd-decl-stubs.h: Added stubs for pow. * math/bits/mathcalls.h: Added pow declaration with __MATHCALL_VEC. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New versions added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for pow. * 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_d_wrapper_impl.h: Added 2 argument wrappers. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow2_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow4_core_avx2.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: New file. * sysdeps/x86_64/fpu/svml_d_pow2_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow4_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_d_pow8_core.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.S: New file. * sysdeps/x86_64/fpu/svml_d_pow_data.h: New file. * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Added vector pow test. * 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. * NEWS: Mention addition of x86_64 vector pow.
2015-06-17 13:22:26 +00:00
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
/* 3 argument AVX512 ISA version as wrapper to AVX2 ISA version. */
.macro WRAPPER_IMPL_AVX512_fFF callee
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
pushq %r12
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%r12, 0)
pushq %r13
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%r13, 0)
subq $176, %rsp
movq %rsi, %r13
vmovups %zmm0, (%rsp)
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
movq %rdi, %r12
vmovupd (%rsp), %ymm0
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
call HIDDEN_JUMPTARGET(\callee)
vmovupd 32(%rsp), %ymm0
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
lea 64(%rsp), %rdi
lea 96(%rsp), %rsi
call HIDDEN_JUMPTARGET(\callee)
vmovupd 64(%rsp), %ymm0
vmovupd 96(%rsp), %ymm1
vmovupd %ymm0, 32(%r12)
vmovupd %ymm1, 32(%r13)
vzeroupper
Vector sincos for x86_64 and tests. 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.
2015-06-18 14:55:55 +00:00
addq $176, %rsp
popq %r13
cfi_adjust_cfa_offset (-8)
cfi_restore (%r13)
popq %r12
cfi_adjust_cfa_offset (-8)
cfi_restore (%r12)
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.endm