glibc/sysdeps/x86_64/fpu/multiarch/Makefile
Shen-Ta Hsieh 1683249d17 x86_64: roundeven with sse4.1 support
This patch adds support for the sse4.1 hardware floating point
roundeven.

Here is some benchmark results on my systems:

=AMD Ryzen 9 3900X 12-Core Processor=

* benchmark result before this commit
|            |    roundeven |   roundevenf |
|------------|--------------|--------------|
| duration   |  3.75587e+09 |  3.75114e+09 |
| iterations |  3.93053e+08 |  4.35402e+08 |
| max        | 52.592       | 58.71        |
| min        |  7.98        |  7.22        |
| mean       |  9.55563     |  8.61535     |

* benchmark result after this commit
|            |     roundeven |   roundevenf |
|------------|---------------|--------------|
| duration   |   3.73815e+09 |  3.73738e+09 |
| iterations |   5.82692e+08 |  5.91498e+08 |
| max        |  56.468       | 51.642       |
| min        |   6.27        |  6.156       |
| mean       |   6.41532     |  6.3185      |

=Intel(R) Pentium(R) CPU D1508 @ 2.20GHz=

* benchmark result before this commit
|            |    roundeven |   roundevenf |
|------------|--------------|--------------|
| duration   |  2.18208e+09 |  2.18258e+09 |
| iterations |  2.39932e+08 |  2.46924e+08 |
| max        | 96.378       | 98.035       |
| min        |  6.776       |  5.94        |
| mean       |  9.09456     |  8.83907     |

* benchmark result after this commit
|            |    roundeven |   roundevenf |
|------------|--------------|--------------|
| duration   |  2.17415e+09 |  2.17005e+09 |
| iterations |  3.56193e+08 |  4.09824e+08 |
| max        | 51.693       | 97.192       |
| min        |  5.926       |  5.093       |
| mean       |  6.10385     |  5.29507     |

Signed-off-by: Shen-Ta Hsieh <ibmibmibm.tw@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
2021-06-27 07:56:57 -07:00

111 lines
4.0 KiB
Makefile

ifeq ($(subdir),math)
libm-sysdep_routines += s_floor-c s_ceil-c s_floorf-c s_ceilf-c \
s_rint-c s_rintf-c s_nearbyint-c s_nearbyintf-c \
s_roundeven-c s_roundevenf-c s_trunc-c s_truncf-c
libm-sysdep_routines += s_ceil-sse4_1 s_ceilf-sse4_1 s_floor-sse4_1 \
s_floorf-sse4_1 s_nearbyint-sse4_1 \
s_nearbyintf-sse4_1 s_roundeven-sse4_1 \
s_roundevenf-sse4_1 s_rint-sse4_1 s_rintf-sse4_1 \
s_trunc-sse4_1 s_truncf-sse4_1
libm-sysdep_routines += e_exp-fma e_log-fma e_pow-fma s_atan-fma \
e_asin-fma e_atan2-fma s_sin-fma s_tan-fma
CFLAGS-e_asin-fma.c = -mfma -mavx2
CFLAGS-e_atan2-fma.c = -mfma -mavx2
CFLAGS-e_exp-fma.c = -mfma -mavx2
CFLAGS-e_log-fma.c = -mfma -mavx2
CFLAGS-e_pow-fma.c = -mfma -mavx2
CFLAGS-s_atan-fma.c = -mfma -mavx2
CFLAGS-s_sin-fma.c = -mfma -mavx2
CFLAGS-s_tan-fma.c = -mfma -mavx2
libm-sysdep_routines += s_sinf-sse2 s_cosf-sse2 s_sincosf-sse2
libm-sysdep_routines += e_exp2f-fma e_expf-fma e_log2f-fma e_logf-fma \
e_powf-fma s_sinf-fma s_cosf-fma s_sincosf-fma
CFLAGS-e_exp2f-fma.c = -mfma -mavx2
CFLAGS-e_expf-fma.c = -mfma -mavx2
CFLAGS-e_log2f-fma.c = -mfma -mavx2
CFLAGS-e_logf-fma.c = -mfma -mavx2
CFLAGS-e_powf-fma.c = -mfma -mavx2
CFLAGS-s_sinf-fma.c = -mfma -mavx2
CFLAGS-s_cosf-fma.c = -mfma -mavx2
CFLAGS-s_sincosf-fma.c = -mfma -mavx2
libm-sysdep_routines += e_exp-fma4 e_log-fma4 e_pow-fma4 s_atan-fma4 \
e_asin-fma4 e_atan2-fma4 s_sin-fma4 s_tan-fma4
CFLAGS-e_asin-fma4.c = -mfma4
CFLAGS-e_atan2-fma4.c = -mfma4
CFLAGS-e_exp-fma4.c = -mfma4
CFLAGS-e_log-fma4.c = -mfma4
CFLAGS-e_pow-fma4.c = -mfma4
CFLAGS-s_atan-fma4.c = -mfma4
CFLAGS-s_sin-fma4.c = -mfma4
CFLAGS-s_tan-fma4.c = -mfma4
libm-sysdep_routines += e_exp-avx e_log-avx s_atan-avx \
e_atan2-avx s_sin-avx s_tan-avx
CFLAGS-e_atan2-avx.c = -msse2avx -DSSE2AVX
CFLAGS-e_exp-avx.c = -msse2avx -DSSE2AVX
CFLAGS-e_log-avx.c = -msse2avx -DSSE2AVX
CFLAGS-s_atan-avx.c = -msse2avx -DSSE2AVX
CFLAGS-s_sin-avx.c = -msse2avx -DSSE2AVX
CFLAGS-s_tan-avx.c = -msse2avx -DSSE2AVX
endif
ifeq ($(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 \
svml_d_cos2_core-sse2 svml_d_cos4_core-sse \
svml_d_cos8_core-avx2 svml_d_exp2_core-sse2 \
svml_d_exp4_core-sse svml_d_exp8_core-avx2 \
svml_d_log2_core-sse2 svml_d_log4_core-sse \
svml_d_log8_core-avx2 svml_d_pow2_core-sse2 \
svml_d_pow4_core-sse svml_d_pow8_core-avx2 \
svml_d_sin2_core-sse2 svml_d_sin4_core-sse \
svml_d_sin8_core-avx2 \
svml_d_sincos2_core-sse2 \
svml_d_sincos4_core-sse \
svml_d_sincos8_core-avx2 \
svml_s_cosf16_core-avx2 \
svml_s_cosf4_core-sse2 \
svml_s_cosf8_core-sse \
svml_s_expf16_core-avx2 \
svml_s_expf4_core-sse2 \
svml_s_expf8_core-sse \
svml_s_logf16_core-avx2 \
svml_s_logf4_core-sse2 \
svml_s_logf8_core-sse \
svml_s_powf16_core-avx2 \
svml_s_powf4_core-sse2 \
svml_s_powf8_core-sse \
svml_s_sincosf16_core-avx2 \
svml_s_sincosf4_core-sse2 \
svml_s_sincosf8_core-sse \
svml_s_sinf16_core-avx2 \
svml_s_sinf4_core-sse2 \
svml_s_sinf8_core-sse
endif