On 11/08/2017 13:44, Paolo Bonzini wrote: > Overall, they provide a 15% improvement for my favorite testcase (QEMU's > "no-op" build). These were first sent out last November, but there > have been quite a few changes since then: > > - I have dropped the SSE-optimized replacement for strpbrk, because > it does not provide any improvement when tested with a newer glibc. > > - the improved hash function is now used for all case-insensitive > hash tables, including those with NUL-terminated keys. > > - there are two new minor optimizations (patches 3 and 6) > > The benchmarks were rerun with a newer version of QEMU that has an > improved Makefile. For this reason the times are lower and the speedup > from patch 5 is smaller than I had reported for v1.
Any news? Thanks, Paolo > Paolo > > Paolo Bonzini (6): > use Jenkins hash > use strchr for simple case of find_char_unquote > use strchr/memmove in collapse_continuations > remove MAP_PERCENT > speedup parsing of functions > do not use STOP_SET for singleton sets > > configure.ac | 1 + > function.c | 9 +++- > hash.c | 148 > +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ > hash.h | 40 ++++++++-------- > main.c | 5 +- > makeint.h | 2 +- > misc.c | 84 ++++++++++++++------------------- > read.c | 79 +++++++++++++++++++++++-------- > 8 files changed, 275 insertions(+), 93 deletions(-) > _______________________________________________ Bug-make mailing list Bug-make@gnu.org https://lists.gnu.org/mailman/listinfo/bug-make
