mirror of git://sourceware.org/git/glibc.git
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. |
||
|---|---|---|
| .. | ||
| Makefile | ||
| doasin-fma4.c | ||
| dosincos-fma4.c | ||
| e_asin-fma4.c | ||
| e_asin.c | ||
| e_atan2-avx.c | ||
| e_atan2-fma4.c | ||
| e_atan2.c | ||
| e_exp-avx.c | ||
| e_exp-fma4.c | ||
| e_exp.c | ||
| e_log-avx.c | ||
| e_log-fma4.c | ||
| e_log.c | ||
| e_pow-fma4.c | ||
| e_pow.c | ||
| halfulp-fma4.c | ||
| mpa-avx.c | ||
| mpa-fma4.c | ||
| mpatan-fma4.c | ||
| mpatan2-fma4.c | ||
| mpexp-avx.c | ||
| mpexp-fma4.c | ||
| mplog-avx.c | ||
| mplog-fma4.c | ||
| mpsqrt-fma4.c | ||
| mptan-fma4.c | ||
| s_atan-avx.c | ||
| s_atan-fma4.c | ||
| s_atan.c | ||
| s_ceil-c.c | ||
| s_ceil.S | ||
| s_ceilf-c.c | ||
| s_ceilf.S | ||
| s_floor-c.c | ||
| s_floor.S | ||
| s_floorf-c.c | ||
| s_floorf.S | ||
| s_fma.c | ||
| s_fmaf.c | ||
| s_nearbyint-c.c | ||
| s_nearbyint.S | ||
| s_nearbyintf-c.c | ||
| s_nearbyintf.S | ||
| s_rint-c.c | ||
| s_rint.S | ||
| s_rintf-c.c | ||
| s_rintf.S | ||
| s_sin-avx.c | ||
| s_sin-fma4.c | ||
| s_sin.c | ||
| s_tan-avx.c | ||
| s_tan-fma4.c | ||
| s_tan.c | ||
| sincos32-fma4.c | ||
| slowexp-avx.c | ||
| slowexp-fma4.c | ||
| slowpow-fma4.c | ||
| svml_d_cos2_core.S | ||
| svml_d_cos2_core_sse4.S | ||
| svml_d_cos4_core.S | ||
| svml_d_cos4_core_avx2.S | ||
| svml_d_cos8_core.S | ||
| svml_d_cos8_core_avx512.S | ||
| svml_d_exp2_core.S | ||
| svml_d_exp2_core_sse4.S | ||
| svml_d_exp4_core.S | ||
| svml_d_exp4_core_avx2.S | ||
| svml_d_exp8_core.S | ||
| svml_d_exp8_core_avx512.S | ||
| svml_d_log2_core.S | ||
| svml_d_log2_core_sse4.S | ||
| svml_d_log4_core.S | ||
| svml_d_log4_core_avx2.S | ||
| svml_d_log8_core.S | ||
| svml_d_log8_core_avx512.S | ||
| svml_d_sin2_core.S | ||
| svml_d_sin2_core_sse4.S | ||
| svml_d_sin4_core.S | ||
| svml_d_sin4_core_avx2.S | ||
| svml_d_sin8_core.S | ||
| svml_d_sin8_core_avx512.S | ||
| svml_s_cosf4_core.S | ||
| svml_s_cosf4_core_sse4.S | ||
| svml_s_cosf8_core.S | ||
| svml_s_cosf8_core_avx2.S | ||
| svml_s_cosf16_core.S | ||
| svml_s_cosf16_core_avx512.S | ||
| svml_s_expf4_core.S | ||
| svml_s_expf4_core_sse4.S | ||
| svml_s_expf8_core.S | ||
| svml_s_expf8_core_avx2.S | ||
| svml_s_expf16_core.S | ||
| svml_s_expf16_core_avx512.S | ||
| svml_s_logf4_core.S | ||
| svml_s_logf4_core_sse4.S | ||
| svml_s_logf8_core.S | ||
| svml_s_logf8_core_avx2.S | ||
| svml_s_logf16_core.S | ||
| svml_s_logf16_core_avx512.S | ||
| svml_s_sinf4_core.S | ||
| svml_s_sinf4_core_sse4.S | ||
| svml_s_sinf8_core.S | ||
| svml_s_sinf8_core_avx2.S | ||
| svml_s_sinf16_core.S | ||
| svml_s_sinf16_core_avx512.S | ||