yes, a typo. 2.2kW or 2200W full tilt. About 1800W in fluid. On Tue, Aug 23, 2016 at 10:04 PM, Joe Landman < land...@scalableinformatics.com> wrote:
> Erp ... > > On 08/23/2016 09:58 AM, Prentice Bisbal wrote: > >> How much power does that system use at full-tilt? I'm guessing about >> 2250 - 2500 kW. >> >> Prentice >> >> On 08/22/2016 07:40 PM, Stu Midgley wrote: >> >>> I measured the power draw of our 2RU 8 phi nodes with and without >>> fans... the fans draw about 20% power. >>> >>> On a 2200kW node that's considerable. >>> >> > paraphrasing Shakespeare ... > > Methinks thou art 3 orders of magnitude too high and protesteth too much. > > 2.2MW anyone? 2200kW = 2.2MW. Per node. Thermals on that are gonna be > wild ... > > At SC15, we saw the Russian machines at 400kW/rack ... so ... I am > assuming a typo here ... > > FWIW: they were using specialized nodes and liquid cooling in closed > loops. I think it was DI water, but I don't quite remember. > > Incredible (performance) density, tiny space. > > > -- > Joseph Landman, Ph.D > Founder and CEO > Scalable Informatics, Inc. > e: land...@scalableinformatics.com > w: http://scalableinformatics.com > t: @scalableinfo > p: +1 734 786 8423 x121 > c: +1 734 612 4615 > _______________________________________________ > Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing > To change your subscription (digest mode or unsubscribe) visit > http://www.beowulf.org/mailman/listinfo/beowulf > -- Dr Stuart Midgley sdm...@sdm900.com
_______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
