[Beowulf] Re: cheap PCs this christmas
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.
David Mathog mathog at mendel.bio.caltech.eduTue Nov 15 11:27:09 PST 2005
- Previous message: [Beowulf] memory bandwidth estimation
- Next message: [Beowulf] Reminder: Annual Beowulf Bash tonight (Wednesday) at SC05 in Seattle
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> > Good point, but I'm not using memtest86, I'm using "memtester": > > http://pyropus.ca/software/memtester/ I was just informed by the memtest86+ people that that tool already contains a bit fade test. It doesn't run by default though. To start it change the configuration via the keyboard. It then writes solid 1's and checks it 90 mins later, then solid 0's, and again, checks 90 mins later. I've also modified the code for memtester so that it too supports bit fade testing. Those changes have been submitted back to the memtester site. I'm running a 2 hour per mode test of that on our cluster now, on a slice of 128M memory each, and will try to remember to report tomorrow what the results are. Probably all OK since this uses ECC memory, which was the result for a 10 minute fade test. Regards, David Mathog mathog at caltech.edu Manager, Sequence Analysis Facility, Biology Division, Caltech
- Previous message: [Beowulf] memory bandwidth estimation
- Next message: [Beowulf] Reminder: Annual Beowulf Bash tonight (Wednesday) at SC05 in Seattle
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
