mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-15 13:30:09 +00:00
1663be053d
Here is implementation of vectorized expf containing SSE, AVX, AVX2 and AVX512 versions according to Vector ABI <https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>. * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added. * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration and asm redirections for expf. * 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_s_expf16_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_expf4_core_sse4.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core.S: New file. * sysdeps/x86_64/fpu/multiarch/svml_s_expf8_core_avx2.S: New file. * sysdeps/x86_64/fpu/svml_s_expf16_core.S: New file. * sysdeps/x86_64/fpu/svml_s_expf4_core.S: New file. * sysdeps/x86_64/fpu/svml_s_expf8_core.S: New file. * sysdeps/x86_64/fpu/svml_s_expf8_core_avx.S: New file. * sysdeps/x86_64/fpu/svml_s_expf_data.S: New file. * sysdeps/x86_64/fpu/svml_s_expf_data.h: New file. * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Vector expf tests. * sysdeps/x86_64/fpu/test-float-vlen16.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen4.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-avx2.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise. * sysdeps/x86_64/fpu/test-float-vlen8.c: Likewise. * NEWS: Mention addition of x86_64 vector expf.
48 lines
1.7 KiB
Makefile
48 lines
1.7 KiB
Makefile
ifeq ($(subdir),mathvec)
|
|
libmvec-support += svml_d_cos2_core svml_d_cos4_core_avx \
|
|
svml_d_cos4_core svml_d_cos8_core \
|
|
svml_d_cos_data svml_d_sin2_core svml_d_sin4_core_avx \
|
|
svml_d_sin4_core svml_d_sin8_core svml_d_sin_data \
|
|
svml_s_cosf4_core svml_s_cosf8_core_avx \
|
|
svml_s_cosf8_core svml_s_cosf16_core svml_s_cosf_data \
|
|
svml_s_sinf4_core svml_s_sinf8_core_avx \
|
|
svml_s_sinf8_core svml_s_sinf16_core svml_s_sinf_data \
|
|
svml_d_log2_core svml_d_log4_core_avx svml_d_log4_core \
|
|
svml_d_log8_core svml_d_log_data svml_s_logf4_core \
|
|
svml_s_logf8_core_avx svml_s_logf8_core svml_s_logf16_core \
|
|
svml_s_logf_data svml_d_exp2_core svml_d_exp4_core_avx \
|
|
svml_d_exp4_core svml_d_exp8_core svml_d_exp_data \
|
|
svml_s_expf4_core svml_s_expf8_core_avx svml_s_expf8_core \
|
|
svml_s_expf16_core svml_s_expf_data \
|
|
init-arch
|
|
endif
|
|
|
|
# Variables for libmvec tests.
|
|
ifeq ($(subdir),math)
|
|
ifeq ($(build-mathvec),yes)
|
|
libmvec-tests += double-vlen2 double-vlen4 double-vlen4-avx2 \
|
|
float-vlen4 float-vlen8 float-vlen8-avx2
|
|
|
|
ifeq (yes,$(config-cflags-avx512))
|
|
libmvec-tests += double-vlen8 float-vlen16
|
|
endif
|
|
|
|
double-vlen2-arch-ext-cflags = -msse4
|
|
double-vlen4-arch-ext-cflags = -mavx
|
|
double-vlen4-arch-ext2-cflags = -mavx2
|
|
double-vlen8-arch-ext-cflags = -mavx512f
|
|
|
|
float-vlen4-arch-ext-cflags = -msse4
|
|
float-vlen8-arch-ext-cflags = -mavx
|
|
float-vlen8-arch-ext2-cflags = -mavx2
|
|
float-vlen16-arch-ext-cflags = -mavx512f
|
|
|
|
CFLAGS-test-double-vlen4-avx2.c = $(libm-test-vec-cflags)
|
|
CFLAGS-test-double-vlen4-avx2-wrappers.c = $(double-vlen4-arch-ext2-cflags)
|
|
|
|
CFLAGS-test-float-vlen8-avx2.c = $(libm-test-vec-cflags)
|
|
CFLAGS-test-float-vlen8-avx2-wrappers.c = $(float-vlen8-arch-ext2-cflags)
|
|
|
|
endif
|
|
endif
|