On 08/12/13 11:10 PM, Jeff Tan wrote: > Hi Sébastien > >> How many rank are you using per Blue Gene node ? > > Appears to have been 4 processes per node on the BG/Q. Is there a safe > level of distribution per node? >
Hi, When I did my tests a while ago, I think I was running at 4 ranks per node on BGQ (at least for the white spruce data I think). I did some runs at 16 ranks per node, 1024 nodes. http://dskernel.blogspot.ca/2012/12/plant-genome-white-spruce-illumina.html But I do remember that later stages of the computation used more memory and I needed to lower 16 to something lower. Some of my tests: https://github.com/sebhtml/Ray-on-IBM-Blue-Gene-Q/tree/master/scinet > Regards > Jeff > ------------------------------------------------------------------------------ Sponsored by Intel(R) XDK Develop, test and display web and hybrid apps with a single code base. Download it for free now! http://pubads.g.doubleclick.net/gampad/clk?id=111408631&iu=/4140/ostg.clktrk _______________________________________________ Denovoassembler-users mailing list Denovoassembler-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/denovoassembler-users
