On Sun, Mar 29, 2015 at 2:05 PM, Thomas Helland <thomashellan...@gmail.com> wrote: > Here's the latest round of fixup on the hash-table patches. > I think I've gotten all the review feedback incorporated now. > These patches give a nice little boost, indicated in each commit. > As a side effect of upping the minimum size of the table and set > there is now also less spamming of rzalloc and friends. > _int_malloc is cut from 935'000 to 847'000 samples. > calloc is cut from 683'000 to 655'000 samples. > _int_free is cut from 644'000 to 617'000 samples > The series reduced shader-db run-time with NIR on my collection > from 180 seconds to about 160 seconds. > > Thomas Helland (3): > util: Change hash_table to use quadratic probing > util: Change util/set to use quadratic probing > util: Use 32 bit integer hash function for pointers > > src/util/hash_table.c | 132 > ++++++++++++++++++++++---------------------------- > src/util/hash_table.h | 3 +- > src/util/set.c | 124 ++++++++++++++++++----------------------------- > src/util/set.h | 3 +- > 4 files changed, 109 insertions(+), 153 deletions(-) > > -- > 2.3.4 > > _______________________________________________ > mesa-dev mailing list > mesa-dev@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/mesa-dev
I don't see any performance data on each commit, did you leave it out by accident? Other than that, the series is Reviewed-by: Connor Abbott <cwabbo...@gmail.com> but you'll want to get Eric to review it too. _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
