Re: [Beowulf] Re: overclocking with liquids

Jim Lux wrote: > The disadvantage of oil? It's a mess if you have to remove the stuff. Why doesn't anyone ever mention higher heat capacity, relatively inert gases? How does the heat capacity of pure CO2 or N2 compare with air? There must be other candidates that would give you 2 maybe 3 times

Re: [Beowulf] Re: overclocking with liquids

At 07:42 AM 9/21/2007, Peter St. John wrote: Thanks all; a couple of people sent me this same article: http://www.tomshardware.com/2006/01/09/strip_out_the_fans/ http://www.tomshardware.com/2006/02/02/strip_out_the_fans/ They tried i

Re: [Beowulf] Big storage

In any case by the end of the year I should have at least ten X4500s, and can do some testing myself. But your collection is an order of magnitude larger, so you can collect much more useful statistics. If those statistics show no data corruption, then someone like myself with many fewer systems

Re: [Beowulf] overclocking with liquids

My apologies (not that I think the 3-processor thing is bad), but my mistake, AMD not Intel. The item was from Slashdot's 9-19 "headlines", AMD Announces Triple-Core Phenom Processors from the chips-that-don't-require-dipping dept. posted by Zonk on Monday September 17, @23:26 (AMD) http:

Re: [Beowulf] overclocking with liquids

On Thu, Sep 20, 2007 at 11:32:26AM -0400, Peter St. John wrote: > > P.S. also Intel (according to slashdot) intends to sell 3-core processors > (so they can sell quad cores that have a manufacturing defect; reminds me of > the 487 "SX" math coprocessor, an i486 with a defect in the CPU component).

RS: [Beowulf] overclocking with liquids

Hi. Been there, done that. Bad results, since *all* the chips including the CPU overheated. It looked like there was not enough convection to make the oil circulate fast enough to evacuate heat. I didn't try with an immersed fan, however -- a fan that should be powerful enough to push the oil

[Beowulf] Graphics Processing Unit: Measured speeds for Molecular Dynamics Codes

Hi, Here is the abstract and link to a pre-print of an article evaluating the application an NVIDIA graphics processing unit to molecular dynamics calculations. Have a good day, Don arXiv:0709.3225 Date: Thu, 20 Sep 2007 13:07:49 GMT (26

[Beowulf] Re: overclocking with liquids

Thanks all; a couple of people sent me this same article: http://www.tomshardware.com/2006/01/09/strip_out_the_fans/ http://www.tomshardware.com/2006/02/02/strip_out_the_fans/ They tried immersion in "ion-free" water (which I would not have considered; I thought that since the water molecule is el