diff options
| author | Vidya Ranganathan <vidya@linux.vnet.ibm.com> | 2014-05-05 19:10:45 -0500 |
|---|---|---|
| committer | Adhemerval Zanella <azanella@linux.vnet.ibm.com> | 2014-05-06 09:54:25 -0500 |
| commit | f360f94a05570045be615649e9a411cefba2e210 (patch) | |
| tree | ac6fb86d01ea80b3bf914c2f74aa231b42bfda28 /ChangeLog | |
| parent | 978a41c35738dbe4592edb7dcaa155fec31dab50 (diff) | |
| download | glibc-f360f94a05570045be615649e9a411cefba2e210.tar.gz glibc-f360f94a05570045be615649e9a411cefba2e210.tar.xz glibc-f360f94a05570045be615649e9a411cefba2e210.zip | |
PowerPC: strncpy/stpncpy optimization for PPC64/POWER7
The optimization is achieved by following techniques:
> data alignment [gain from aligned memory access on read/write]
> POWER7 gains performance with loop unrolling/unwinding
[gain by reduction of branch penalty].
> zero padding done by calling optimized memset
Diffstat (limited to 'ChangeLog')
| -rw-r--r-- | ChangeLog | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/ChangeLog b/ChangeLog index 6ccf04111b..588bcee2f1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,20 @@ +2014-05-06 Vidya Ranganathan <vidya@linux.vnet.ibm.com> + + * sysdeps/powerpc/powerpc64/power7/strncpy.S: New file: Optimization. + * sysdeps/powerpc/powerpc64/multiarch/strncpy.c: New file: + multiarch strncpy for PPC64. + * sysdeps/powerpc/powerpc64/multiarch/strncpy-ppc64.c: New file + * sysdeps/powerpc/powerpc64/multiarch/strncpy-power7.S: New file + * sysdeps/powerpc/powerpc64/multiarch/Makefile: Add strpcpy, stpncpy + multiarch optimizations. + * sysdeps/powerpc/powerpc64/multiarch/ifunc-impl-list.c: + (__libc_ifunc_impl_list): Likewise. + * sysdeps/powerpc/powerpc64/power7/stpncpy.S: New file: Optimization. + * sysdeps/powerpc/powerpc64/multiarch/stpncpy.c: New file: + multiarch stpncpy for PPC64. + * sysdeps/powerpc/powerpc64/multiarch/stpncpy-ppc64.c: New file + * sysdeps/powerpc/powerpc64/multiarch/stpncpy-power7.S: New file + 2014-05-06 Andreas Schwab <schwab@suse.de> [BZ #16912] |