GROMACS cluster benchmarks for d.dppc on Athlon
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
math at velocet.ca math at velocet.caThu Oct 25 11:02:52 PDT 2001
- Previous message: SGEEE easily mistaken as commercial version
- Next message: GROMACS cluster benchmarks for d.dppc on Athlon
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Anyone have a dual athlon board single node (and multiple nodes in parallel would be good) benchmark time (or ps/day) benchmark stat for GROMACS on the d.dppc benchmark file? Im curious as to your results. Please specify what the network topology is as well if you include parallel stats. (Parallel stats for 2,4,8,12,16,24 nodes are provided for on the benchmark results page, but only for some relatively old equipment). Also specify wether you have single or dual Athlon boards. Remmeber the results from mdrun are in ps/NODE HOUR so you have to multiple by 24 to get /DAY as they quote in their results. If you dont have this benchmark file, its available at http://www.gromacs.org under benchmark. Takes about 30 min to run on a single Athlon 1.333Ghz. Thanks alot! /kc -- Ken Chase, math at velocet.ca * Velocet Communications Inc. * Toronto, CANADA
- Previous message: SGEEE easily mistaken as commercial version
- Next message: GROMACS cluster benchmarks for d.dppc on Athlon
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
