diff options
| author | Paul E. Murphy <murphyp@linux.vnet.ibm.com> | 2020-05-18 11:16:06 -0500 |
|---|---|---|
| committer | Paul E. Murphy <murphyp@linux.vnet.ibm.com> | 2020-06-05 15:30:00 -0500 |
| commit | a23bd00f9d810c28d9e83ce1d7cf53968375937d (patch) | |
| tree | ad8b0472058d43b628bb9882d999fa3b3514cd7c /sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S | |
| parent | 6ef422750985f7e60a8d480f07ecda59e0311fdf (diff) | |
| download | glibc-a23bd00f9d810c28d9e83ce1d7cf53968375937d.tar.gz glibc-a23bd00f9d810c28d9e83ce1d7cf53968375937d.tar.xz glibc-a23bd00f9d810c28d9e83ce1d7cf53968375937d.zip | |
powerpc64le: add optimized strlen for P9
This started as a trivial change to Anton's rawmemchr. I got carried away. This is a hybrid between P8's asympotically faster 64B checks with extremely efficient small string checks e.g <64B (and sometimes a little bit more depending on alignment). The second trick is to align to 64B by running a 48B checking loop 16B at a time until we naturally align to 64B (i.e checking 48/96/144 bytes/iteration based on the alignment after the first 5 comparisons). This allieviates the need to check page boundaries. Finally, explicly use the P7 strlen with the runtime loader when building P9. We need to be cautious about vector/vsx extensions here on P9 only builds.
Diffstat (limited to 'sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S')
| -rw-r--r-- | sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S b/sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S new file mode 100644 index 0000000000..e9d83323ac --- /dev/null +++ b/sysdeps/powerpc/powerpc64/le/power9/rtld-strlen.S @@ -0,0 +1 @@ +#include <sysdeps/powerpc/powerpc64/power7/strlen.S> |