mirror of
https://sourceware.org/git/glibc.git
synced 2025-09-11 12:10:50 +03:00
c7c4a5906f
On SPR, it improves atanh bench performance by: Before After Improvement reciprocal-throughput 15.1715 14.8628 2% latency 57.1941 56.1883 2% Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
167 lines
3.7 KiB
Makefile
167 lines
3.7 KiB
Makefile
ifeq ($(subdir),math)
|
|
CFLAGS-e_asin-fma.c = -mfma -mavx2
|
|
CFLAGS-e_atan2-fma.c = -mfma -mavx2
|
|
CFLAGS-e_atanh-fma.c = -mfma -mavx2
|
|
CFLAGS-e_exp-fma.c = -mfma -mavx2
|
|
CFLAGS-e_log-fma.c = -mfma -mavx2
|
|
CFLAGS-e_log2-fma.c = -mfma -mavx2
|
|
CFLAGS-e_pow-fma.c = -mfma -mavx2
|
|
CFLAGS-e_sinh-fma.c = -mfma -mavx2
|
|
CFLAGS-s_atan-fma.c = -mfma -mavx2
|
|
CFLAGS-s_expm1-fma.c = -mfma -mavx2
|
|
CFLAGS-s_log1p-fma.c = -mfma -mavx2
|
|
CFLAGS-s_sin-fma.c = -mfma -mavx2
|
|
CFLAGS-s_tan-fma.c = -mfma -mavx2
|
|
CFLAGS-s_tanh-fma.c = -mfma -mavx2
|
|
CFLAGS-s_sincos-fma.c = -mfma -mavx2
|
|
CFLAGS-s_exp10m1f-fma.c = -mfma -mavx2
|
|
CFLAGS-s_exp2m1f-fma.c = -mfma -mavx2
|
|
|
|
CFLAGS-e_exp2f-fma.c = -mfma -mavx2
|
|
CFLAGS-e_expf-fma.c = -mfma -mavx2
|
|
CFLAGS-e_log2f-fma.c = -mfma -mavx2
|
|
CFLAGS-e_logf-fma.c = -mfma -mavx2
|
|
CFLAGS-e_powf-fma.c = -mfma -mavx2
|
|
CFLAGS-s_sinf-fma.c = -mfma -mavx2
|
|
CFLAGS-s_cosf-fma.c = -mfma -mavx2
|
|
CFLAGS-s_sincosf-fma.c = -mfma -mavx2
|
|
|
|
# Check if ISA level is 3 or above.
|
|
ifneq (,$(filter $(have-x86-isa-level),$(x86-isa-level-3-or-above)))
|
|
libm-sysdep_routines += \
|
|
s_ceil-avx \
|
|
s_ceilf-avx \
|
|
s_floor-avx \
|
|
s_floorf-avx \
|
|
s_nearbyint-avx \
|
|
s_nearbyintf-avx \
|
|
s_rint-avx \
|
|
s_rintf-avx \
|
|
s_roundeven-avx \
|
|
s_roundevenf-avx \
|
|
s_trunc-avx \
|
|
s_truncf-avx \
|
|
# libm-sysdep_routines
|
|
else
|
|
ifeq (no,$(have-x86-apx))
|
|
libm-sysdep_routines += \
|
|
e_asin-fma4 \
|
|
e_atan2-fma4 \
|
|
e_exp-fma4 \
|
|
e_log-fma4 \
|
|
e_pow-fma4 \
|
|
s_atan-fma4 \
|
|
s_sin-fma4 \
|
|
s_sincos-fma4 \
|
|
s_tan-fma4 \
|
|
# libm-sysdep_routines
|
|
endif
|
|
libm-sysdep_routines += \
|
|
e_asin-fma \
|
|
e_atan2-avx \
|
|
e_atan2-fma \
|
|
e_atanh-fma \
|
|
e_exp-avx \
|
|
e_exp-fma \
|
|
e_exp2f-fma \
|
|
e_expf-fma \
|
|
e_log-avx \
|
|
e_log-fma \
|
|
e_log2-fma \
|
|
e_log2f-fma \
|
|
e_logf-fma \
|
|
e_pow-fma \
|
|
e_powf-fma \
|
|
e_sinh-fma \
|
|
s_atan-avx \
|
|
s_atan-fma \
|
|
s_ceil-sse4_1 \
|
|
s_ceilf-sse4_1 \
|
|
s_cosf-fma \
|
|
s_cosf-sse2 \
|
|
s_exp10m1f-fma \
|
|
s_exp2m1f-fma \
|
|
s_expm1-fma \
|
|
s_floor-sse4_1 \
|
|
s_floorf-sse4_1 \
|
|
s_log1p-fma \
|
|
s_nearbyint-sse4_1 \
|
|
s_nearbyintf-sse4_1 \
|
|
s_rint-sse4_1 \
|
|
s_rintf-sse4_1 \
|
|
s_roundeven-sse4_1 \
|
|
s_roundevenf-sse4_1 \
|
|
s_sin-avx \
|
|
s_sin-fma \
|
|
s_sincos-avx \
|
|
s_sincos-fma \
|
|
s_sincosf-fma \
|
|
s_sincosf-sse2 \
|
|
s_sinf-fma \
|
|
s_sinf-sse2 \
|
|
s_tan-avx \
|
|
s_tan-fma \
|
|
s_tanh-fma \
|
|
s_trunc-sse4_1 \
|
|
s_truncf-sse4_1 \
|
|
# libm-sysdep_routines
|
|
ifeq ($(have-x86-isa-level),baseline)
|
|
libm-sysdep_routines += \
|
|
s_ceil-c \
|
|
s_ceilf-c \
|
|
s_floor-c \
|
|
s_floorf-c \
|
|
s_nearbyint-c \
|
|
s_nearbyintf-c \
|
|
s_rint-c \
|
|
s_rintf-c \
|
|
s_roundeven-c \
|
|
s_roundevenf-c \
|
|
s_trunc-c \
|
|
s_truncf-c \
|
|
# libm-sysdep_routines
|
|
endif
|
|
endif
|
|
|
|
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-s_atan-fma4.c = -mfma4
|
|
CFLAGS-s_sin-fma4.c = -mfma4
|
|
CFLAGS-s_tan-fma4.c = -mfma4
|
|
CFLAGS-s_sincos-fma4.c = -mfma4
|
|
|
|
CFLAGS-e_atan2-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-e_exp-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-e_log-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_atan-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_sin-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_tan-avx.c = -msse2avx -DSSE2AVX
|
|
CFLAGS-s_sincos-avx.c = -msse2avx -DSSE2AVX
|
|
endif
|
|
|
|
ifeq ($(subdir),mathvec)
|
|
libmvec-multiarch-double-func-list = \
|
|
2_core-sse2 \
|
|
2_core_sse4 \
|
|
4_core-sse \
|
|
4_core_avx2 \
|
|
8_core-avx2 \
|
|
8_core_avx512
|
|
libmvec-multiarch-float-func-list = \
|
|
f4_core-sse2 \
|
|
f4_core_sse4 \
|
|
f8_core-sse \
|
|
f8_core_avx2 \
|
|
f16_core-avx2 \
|
|
f16_core_avx512
|
|
|
|
libmvec-sysdep_routines += \
|
|
$(foreach l,$(libmvec-multiarch-double-func-list), \
|
|
$(addprefix svml_d_,$(addsuffix $(l),$(libmvec-funcs)))) \
|
|
$(foreach l,$(libmvec-multiarch-float-func-list), \
|
|
$(addprefix svml_s_,$(addsuffix $(l),$(libmvec-funcs))))
|
|
endif
|