The following patch makes "pre-sorting" in parallel mode. The clean final sorting is in one-thread mode.
I have done some performance measurements. In 4-thread-mode with 2*10^5 particles the calculation speed is higher on 20%, than without patch. No performance regression with smaller number of particles. But anyway, sorting mechanism takes the most of calculation time. Good to hear opinions. ** Patch added: "pre-sort in parallel mode patch" https://bugs.launchpad.net/yade/+bug/729079/+attachment/1936051/+files/patch_parallel_sort.patch -- You received this bug notification because you are a member of Yade developers, which is the registrant for Yade. https://bugs.launchpad.net/bugs/729079 Title: Performance optimization of InsertionSortCollider Status in Yet Another Dynamic Engine: New Bug description: Sergei Dorofeenko (https://launchpad.net/~sergei.dorofeenko) found, that InsertionSortCollider is probably is a "bottle neck" in simulations with >10^5 number of particles even in many-threads mode. http://www.mail-archive.com/[email protected]/msg06573.html Сitation: "...I did a perfomance test for parallel mode and results in no good. Performance boost only about 40% from 1 thread to 4 thread for 200k particles... Cause is a non-parallelised InsertionSortCollider, who need about 80% time with 4 threads. Results attached." _______________________________________________ Mailing list: https://launchpad.net/~yade-dev Post to : [email protected] Unsubscribe : https://launchpad.net/~yade-dev More help : https://help.launchpad.net/ListHelp
