[Beowulf] Re: Cooler room or cooler servers?
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.
Jack Wathey wathey at salk.eduMon Apr 11 12:57:18 PDT 2005
- Previous message: [Beowulf] Re: Cooler room or cooler servers?
- Next message: [Beowulf] 802.3ad: Should it behave in this way??
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Some overclockers have played around with this idea, for example see: http://www.octools.com/index.cgi?caller=articles/submersion/submersion8.html My gut reaction, though, is that it's not practical for a cluster (or even for overclocking, for that matter). You still have to remove the same amount of heat from the room. Jack On Mon, 11 Apr 2005 award at andorra.ad wrote: > Some time ago, I was thinking of using an inert liquid such as 3M's > Fluorinert for refrigeration. This stuff is electrically inert, has some > heat transport capacity - and a boiling point that can be engineered into > the 30 - 40'C range. > > The idea was to dip the mobos into a pan of the stuff, with the disks and > power supplies outside. You are ensured that the heatsink on the CPU will > not go over an external temperature of, for example, 34'C - no CPU fan > needed. Idem for the mobo chipset and RAM. The whole exterior surface of > the pan acts as a giant heat exchanger in the 2-3 sq.ft. range. > > Any gut reactions out there? > > > _______________________________________________ > Beowulf mailing list, Beowulf at beowulf.org > To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf >
- Previous message: [Beowulf] Re: Cooler room or cooler servers?
- Next message: [Beowulf] 802.3ad: Should it behave in this way??
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
