| commit | 5d15c9697577d2c342b5ade820bfd7b84a736b23 | |
| author | H.J. Lu <hjl.tools@gmail.com> | |
| Sun, 22 Oct 2017 14:55:49 +0000 (22 07:55 -0700) | ||
| committer | H.J. Lu <hjl.tools@gmail.com> | |
| Sun, 22 Oct 2017 14:57:50 +0000 (22 07:57 -0700) | ||
| tree | d16d35b14e05b635b9dc8d147fbd6c147852d446 | treesnapshot (tar.gz zip) |
| parent | b2f6137ea570933fb4be286574cc58b794eb5b5f | commitdiff |
x86-64: Add exp2f with FMA
For workload-spec2017.wrf, on Skylake, it improves performance by:
Before After Improvement
reciprocal-throughput 13.0291 11.2225 16%
latency 44.5154 37.5766 18%
* sysdeps/x86_64/fpu/multiarch/Makefile (libm-sysdep_routines):
Add e_exp2f-fma.
(CFLAGS-e_exp2f-fma.c): New.
* sysdeps/x86_64/fpu/multiarch/e_exp2f-fma.c: New file.
* sysdeps/x86_64/fpu/multiarch/e_exp2f.c: Likewise.
For workload-spec2017.wrf, on Skylake, it improves performance by:
Before After Improvement
reciprocal-throughput 13.0291 11.2225 16%
latency 44.5154 37.5766 18%
* sysdeps/x86_64/fpu/multiarch/Makefile (libm-sysdep_routines):
Add e_exp2f-fma.
(CFLAGS-e_exp2f-fma.c): New.
* sysdeps/x86_64/fpu/multiarch/e_exp2f-fma.c: New file.
* sysdeps/x86_64/fpu/multiarch/e_exp2f.c: Likewise.
| ChangeLog | diffblobblamehistory | |
| sysdeps/x86_64/fpu/multiarch/Makefile | diffblobblamehistory | |
| sysdeps/x86_64/fpu/multiarch/e_exp2f-fma.c | [new file with mode: 0644] | blob |
| sysdeps/x86_64/fpu/multiarch/e_exp2f.c | [new file with mode: 0644] | blob |