[Beowulf] IBM Sequoia

David N. Lombard dnlombar at ichips.intel.com
Wed Feb 4 14:47:12 PST 2009


On Wed, Feb 04, 2009 at 12:58:27PM -0700, Robert G. Brown wrote:
> On Wed, 4 Feb 2009, John Hearns wrote:
> 
> > 2009/2/4 Bruno Coutinho <coutinho at dcc.ufmg.br>:
> >>>
> >> Each compute card could have a octa core processor and some memory chips.
> >> Like Blue Gene/P, each node card could have 16 compute cards and each card
> >> will be 2U high (but they will put two sideways like older Blue Genes).
> >> So they can pack 100 cores in a 1U space without magic! :)
> >>
> >> But cool this thing will now be easy.
> >> Probably they will use something like refrigerated doors (or walls).
> >
> > Special packaging? Engineering effort and expertise given to cooling a
> > system which would otherwise melt?
> > Systems cabinets arranged in rings or squares?
> > Seymour Cray is laughing out loud on his personal cloud of freon
> > vapour right now.

Fluoroinert perhaps.

> Immersion in liquid nitrogen.

Some of the dinosaurs^Wmore experienced list members will remember the
ETA-10 which used LN2 in all but their air-cooled "Piper" system.  My
undertanding at the time was the Piper was a vehicle to consume the 
Honeywell VHSIC chips not suitable for the LN2-cooled versions.

For today's more adventerous, less exotic mineral oil is being used, e.g.,
as shown in <http://www.pugetsystems.com/submerged.php>

-- 
David N. Lombard, Intel, Irvine, CA
I do not speak for Intel Corporation; all comments are strictly my own.



More information about the Beowulf mailing list