----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/3297/#review9193 -----------------------------------------------------------
I've posted an updated version of this patch which removes conflicts with a recent commit. We should coordinate which should be updated/reviewed/discarded. - Matthew Poremba On Jan. 23, 2016, 8:59 p.m., Joel Hestness wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/3297/ > ----------------------------------------------------------- > > (Updated Jan. 23, 2016, 8:59 p.m.) > > > Review request for Default. > > > Repository: gem5 > > > Description > ------- > > Changeset 11299:483fab98c031 > --------------------------- > ruby: Add occupancy stats to MessageBuffers > > The most important statistic for measuring memory hierarchy performance is > throughput, which is affected by independent variables, buffer sizing and > communication latency. It is difficult/impossible to debug performance issues > through series buffers without knowing which are the bottlenecks. For finite > buffers, this patch adds statistics for the average number of messages in the > buffer, the occupancy of the buffer slots, and number of message stalls. > > > Diffs > ----- > > src/mem/ruby/network/MessageBuffer.hh d1f8610cdffd > src/mem/ruby/network/MessageBuffer.cc d1f8610cdffd > > Diff: http://reviews.gem5.org/r/3297/diff/ > > > Testing > ------- > > NOTE: The message count stat could be used as an alternative way to count > total buffered messages RE: http://reviews.gem5.org/r/3283/. Input on how to > tighten things up is welcome. > > > Thanks, > > Joel Hestness > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
