diff options
| author | Lucas A. M. Magalhaes <lamm@linux.ibm.com> | 2021-04-30 18:12:08 -0300 |
|---|---|---|
| committer | Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com> | 2021-04-30 18:12:08 -0300 |
| commit | dd59655e9371af86043b97e38953f43bd9496699 (patch) | |
| tree | 47b67f7c25e588b27618a72bc58cfd13d9ad163d /sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S | |
| parent | e046d73e5f2fa9cb53540bb967c33e403c7917e1 (diff) | |
| download | glibc-dd59655e9371af86043b97e38953f43bd9496699.zip glibc-dd59655e9371af86043b97e38953f43bd9496699.tar.gz glibc-dd59655e9371af86043b97e38953f43bd9496699.tar.bz2 | |
powerpc64le: Optimized memmove for POWER10
This patch was initially based on the __memmove_power7 with some ideas
from strncpy implementation for Power 9.
Improvements from __memmove_power7:
1. Use lxvl/stxvl for alignment code.
The code for Power 7 uses branches when the input is not naturally
aligned to the width of a vector. The new implementation uses
lxvl/stxvl instead which reduces pressure on GPRs. It also allows
the removal of branch instructions, implicitly removing branch stalls
and mispredictions.
2. Use of lxv/stxv and lxvl/stxvl pair is safe to use on Cache Inhibited
memory.
On Power 10 vector load and stores are safe to use on CI memory for
addresses unaligned to 16B. This code takes advantage of this to
do unaligned loads.
The unaligned loads don't have a significant performance impact by
themselves. However doing so decreases register pressure on GPRs
and interdependence stalls on load/store pairs. This also improved
readability as there are now less code paths for different alignments.
Finally this reduces the overall code size.
3. Improved performance.
This version runs on average about 30% better than memmove_power7
for lengths larger than 8KB. For input lengths shorter than 8KB
the improvement is smaller, it has on average about 17% better
performance.
This version has a degradation of about 50% for input lengths
in the 0 to 31 bytes range when dest is unaligned.
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
Diffstat (limited to 'sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S b/sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S index d66da58..27b196d 100644 --- a/sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S +++ b/sysdeps/powerpc/powerpc64/multiarch/memmove-power7.S @@ -21,7 +21,7 @@ #undef libc_hidden_builtin_def #define libc_hidden_builtin_def(name) -#undef bcopy -#define bcopy __bcopy_power7 +#undef __bcopy +#define __bcopy __bcopy_power7 #include <sysdeps/powerpc/powerpc64/power7/memmove.S> |