> On Aug. 6, 2013, 5:32 p.m., Amin Farmahini wrote: > > With this patch, some changes to addToReadQueue() is needed. The reason is > > that codes in addToReadQueue currently check to see if the starting address > > of a read packet is the same as that of a write packet in the write queue > > (my earlier patch considers the packet size as well). With this new patch, > > we should simply check to see if a read packet falls into boundaries of a > > write packet.
True. I also need to add a check to ensure we don't merge packets that are already burst size. Will bump the patch. - Andreas ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/1962/#review4575 ----------------------------------------------------------- On Aug. 5, 2013, 4:55 p.m., Andreas Hansson wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/1962/ > ----------------------------------------------------------- > > (Updated Aug. 5, 2013, 4:55 p.m.) > > > Review request for Default. > > > Repository: gem5 > > > Description > ------- > > Changeset 9830:58ba238410d5 > --------------------------- > mem: Perform write merging in the DRAM write queue > > This patch implements basic write merging in the DRAM to avoid > redundant bursts. When a new access is added to the queue it is > compared against the existing entries, and if it is either > intersecting or immediately succeeding/preceeding an existing item it > is merged. > > There is currently no attempt made at avoiding iterating over the > existing items in determining whether merging is possible or not. > > > Diffs > ----- > > src/mem/simple_dram.hh 2492d7ccda7e > src/mem/simple_dram.cc 2492d7ccda7e > > Diff: http://reviews.gem5.org/r/1962/diff/ > > > Testing > ------- > > With the Alpha quiesce patch and stats updates all regressions pass. > > > Thanks, > > Andreas Hansson > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
