mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-27 07:20:11 +00:00
a6336cc446
Here is implementation of vectorized sincosf 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 sincosf. * math/test-float-vlen16.h: Added wrapper for sincosf tests. * 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 sincosf 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_s_sincosf16_core.S * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core.S * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core.S * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S * sysdeps/x86_64/fpu/svml_s_sincosf16_core.S * sysdeps/x86_64/fpu/svml_s_sincosf4_core.S * sysdeps/x86_64/fpu/svml_s_sincosf8_core.S * sysdeps/x86_64/fpu/svml_s_sincosf8_core_avx.S * sysdeps/x86_64/fpu/svml_s_sincosf_data.S: New file. * sysdeps/x86_64/fpu/svml_s_sincosf_data.h: New file. * sysdeps/x86_64/fpu/svml_s_wrapper_impl.h: Added 3 argument wrappers. * sysdeps/x86_64/fpu/test-float-vlen16.c: : Vector sincosf tests. * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.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.
75 lines
2.7 KiB
Makefile
75 lines
2.7 KiB
Makefile
ifeq ($(subdir),math)
|
|
libm-sysdep_routines += s_floor-c s_ceil-c s_floorf-c s_ceilf-c \
|
|
s_rint-c s_rintf-c s_nearbyint-c s_nearbyintf-c
|
|
|
|
ifeq ($(have-mfma4),yes)
|
|
libm-sysdep_routines += e_exp-fma4 e_log-fma4 e_pow-fma4 s_atan-fma4 \
|
|
e_asin-fma4 e_atan2-fma4 s_sin-fma4 s_tan-fma4 \
|
|
mplog-fma4 mpa-fma4 slowexp-fma4 slowpow-fma4 \
|
|
sincos32-fma4 doasin-fma4 dosincos-fma4 \
|
|
halfulp-fma4 mpexp-fma4 \
|
|
mpatan2-fma4 mpatan-fma4 mpsqrt-fma4 mptan-fma4
|
|
|
|
CFLAGS-doasin-fma4.c = -mfma4
|
|
CFLAGS-dosincos-fma4.c = -mfma4
|
|
CFLAGS-e_asin-fma4.c = -mfma4
|
|
CFLAGS-e_atan2-fma4.c = -mfma4
|
|
CFLAGS-e_exp-fma4.c = -mfma4
|
|
CFLAGS-e_log-fma4.c = -mfma4
|
|
CFLAGS-e_pow-fma4.c = -mfma4
|
|
CFLAGS-halfulp-fma4.c = -mfma4
|
|
CFLAGS-mpa-fma4.c = -mfma4
|
|
CFLAGS-mpatan-fma4.c = -mfma4
|
|
CFLAGS-mpatan2-fma4.c = -mfma4
|
|
CFLAGS-mpexp-fma4.c = -mfma4
|
|
CFLAGS-mplog-fma4.c = -mfma4
|
|
CFLAGS-mpsqrt-fma4.c = -mfma4
|
|
CFLAGS-mptan-fma4.c = -mfma4
|
|
CFLAGS-s_atan-fma4.c = -mfma4
|
|
CFLAGS-sincos32-fma4.c = -mfma4
|
|
CFLAGS-slowexp-fma4.c = -mfma4
|
|
CFLAGS-slowpow-fma4.c = -mfma4
|
|
CFLAGS-s_sin-fma4.c = -mfma4
|
|
CFLAGS-s_tan-fma4.c = -mfma4
|
|
endif
|
|
|
|
ifeq ($(config-cflags-sse2avx),yes)
|
|
libm-sysdep_routines += e_exp-avx e_log-avx s_atan-avx \
|
|
e_atan2-avx s_sin-avx s_tan-avx \
|
|
mplog-avx mpa-avx slowexp-avx \
|
|
mpexp-avx
|
|
|
|
CFLAGS-e_atan2-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-e_exp-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-e_log-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-mpa-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-mpexp-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-mplog-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_atan-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_sin-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-slowexp-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_tan-avx.c = -msse2avx -DSSE2AVX
|
|
endif
|
|
endif
|
|
|
|
ifeq ($(subdir),mathvec)
|
|
libmvec-sysdep_routines += svml_d_cos2_core_sse4 svml_d_cos4_core_avx2 \
|
|
svml_d_cos8_core_avx512 svml_d_sin2_core_sse4 \
|
|
svml_d_sin4_core_avx2 svml_d_sin8_core_avx512 \
|
|
svml_d_log2_core_sse4 svml_d_log4_core_avx2 \
|
|
svml_d_log8_core_avx512 svml_d_sincos2_core_sse4 \
|
|
svml_d_sincos4_core_avx2 svml_d_sincos8_core_avx512 \
|
|
svml_s_cosf4_core_sse4 svml_s_cosf8_core_avx2 \
|
|
svml_s_cosf16_core_avx512 svml_s_sinf4_core_sse4 \
|
|
svml_s_sinf8_core_avx2 svml_s_sinf16_core_avx512 \
|
|
svml_s_logf4_core_sse4 svml_s_logf8_core_avx2 \
|
|
svml_s_logf16_core_avx512 svml_d_exp2_core_sse4 \
|
|
svml_d_exp4_core_avx2 svml_d_exp8_core_avx512 \
|
|
svml_s_expf4_core_sse4 svml_s_expf8_core_avx2 \
|
|
svml_s_expf16_core_avx512 svml_d_pow2_core_sse4 \
|
|
svml_d_pow4_core_avx2 svml_d_pow8_core_avx512 \
|
|
svml_s_powf4_core_sse4 svml_s_powf8_core_avx2 \
|
|
svml_s_powf16_core_avx512 svml_s_sincosf4_core_sse4 \
|
|
svml_s_sincosf8_core_avx2 svml_s_sincosf16_core_avx512
|
|
endif
|