search for: fast_random

...hen >> again it costs RAM. >> - reduce contention on hot counters by not incrementing them if they are >> big enough: >> {if (counter < 65536) counter++}; This reduces the accuracy though. Is >> that bad for PGO? >> - self-cooling logarithmic counters: if ((fast_random() % (1 << counter)) >> == 0) counter++; >> >> Other thoughts? >> >> --kcc >> >> >> >> >> _______________________________________________ >> LLVM Developers mailing list >> LLVMdev at cs.uiuc.edu http://llvm.cs.uiu...

...;It is not practical. Especially for TLS counters -- it creates huge > pressure on stack memory. > > Do we have any numbers about number of counters? If there are 100K 1-byte > counters, I would consider it as practical. > > > > > - self-cooling logarithmic counters: if ((fast_random() % (1 << > counter)) == 0) counter++; > > This option did not receive any attention. While it has O(1) memory > consumption and reduces contention. > Note that there are several tunables here: first -- how implement > fast_rand: it can be a per-thread LCG, or per-thread cou...

...oblem partially, better with larger values of N, but then again it costs RAM. - reduce contention on hot counters by not incrementing them if they are big enough: {if (counter < 65536) counter++}; This reduces the accuracy though. Is that bad for PGO? - self-cooling logarithmic counters: if ((fast_random() % (1 << counter)) == 0) counter++; Other thoughts? --kcc -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20140417/8cff753e/attachment.html>

...huge >>> pressure on stack memory. >>> >>> Do we have any numbers about number of counters? If there are 100K >>> 1-byte counters, I would consider it as practical. >>> >>> >>> >>> > - self-cooling logarithmic counters: if ((fast_random() % (1 << >>> counter)) == 0) counter++; >>> >>> This option did not receive any attention. While it has O(1) memory >>> consumption and reduces contention. >>> Note that there are several tunables here: first -- how implement >>> fast_ran...

On Apr 17, 2014, at 2:04 PM, Chandler Carruth <chandlerc at google.com> wrote: > On Thu, Apr 17, 2014 at 1:27 PM, Justin Bogner <mail at justinbogner.com> wrote: > Chandler Carruth <chandlerc at google.com> writes: > > if (thread-ID != main's thread-ID && shard_count < std::min(MAX, NUMBER_OF_CORES)) { > > shard_count = std::min(MAX,