Scott, They are about to release a 85kW version of the rack, same dimensions. Let me know if you want me to connect you with their founder/inventor.
--Jeff On Tue, Mar 10, 2020 at 1:08 PM Scott Atchley <e.scott.atch...@gmail.com> wrote: > Hi Jeff, > > Interesting, I have not seen this yet. > > Looking at their 52 kW rack's dimensions, it works out to 3.7 kW/ft^2 for > the enclosure if we do not count the row pitch. If we add 4-5 feet for row > pitch, then it drops to 2.2-2.4 kW/ft^2. Assuming Summit's IBM AC922 nodes > fit and again a row pitch of 4-5 feet, the performance per area would be > 31-34 TF/ft^2. Both the performance per area and the power per are are > close to Summit. Their PUE (1.15-1.2) is higher than we get on Summit (1.05 > for 9 months and 1.1-1.2 for 3 months). It is very interesting for data > centers that have widely varying loads for adjacent cabinets. > > Scott > > On Tue, Mar 10, 2020 at 3:47 PM Jeff Johnson < > jeff.john...@aeoncomputing.com> wrote: > >> Scott, >> >> It's not immersion but it's a different approach to the conventional rack >> cooling approach. It's really cool (literally and figuratively). They're >> based here in San Diego. >> >> https://ddcontrol.com/ >> >> --Jeff >> >> On Tue, Mar 10, 2020 at 12:37 PM Scott Atchley <e.scott.atch...@gmail.com> >> wrote: >> >>> Hi everyone, >>> >>> I am wondering whether immersion cooling makes sense. We are most >>> limited by datacenter floor space. We can manage to bring in more power (up >>> to 40 MW for Frontier) and install more cooling towers (ditto), but we >>> cannot simply add datacenter space. We have asked to build new building and >>> the answer has been consistently "No." >>> >>> Summit is mostly water cooled. Each node has cold plates on the CPUs and >>> GPUs. Fans are needed to cool the memory and power supplies and is captured >>> by rear-door heart exchangers. It occupies roughly 5,600 ft^2. With 200 PF >>> of performance and 14 MW of power, that is 36 TF/ft^2 and 2.5 kW/ft^2. >>> >>> I am wondering what the comparable performance and power is per square >>> foot for the densest, deployed (not theoretical) immersion cooled systems. >>> Any ideas? >>> >>> To make the exercise even more fun, what is the weight per square foot >>> for immersion systems? Our data centers have a limit of 250 or 500 >>> pounds per square foot. I expect immersion systems to need higher loadings >>> than that. >>> >>> Thanks, >>> >>> Scott >>> _______________________________________________ >>> Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing >>> To change your subscription (digest mode or unsubscribe) visit >>> https://beowulf.org/cgi-bin/mailman/listinfo/beowulf >>> >> >> >> -- >> ------------------------------ >> Jeff Johnson >> Co-Founder >> Aeon Computing >> >> jeff.john...@aeoncomputing.com >> www.aeoncomputing.com >> t: 858-412-3810 x1001 f: 858-412-3845 >> m: 619-204-9061 >> >> 4170 Morena Boulevard, Suite C - San Diego, CA 92117 >> >> High-Performance Computing / Lustre Filesystems / Scale-out Storage >> > -- ------------------------------ Jeff Johnson Co-Founder Aeon Computing jeff.john...@aeoncomputing.com www.aeoncomputing.com t: 858-412-3810 x1001 f: 858-412-3845 m: 619-204-9061 4170 Morena Boulevard, Suite C - San Diego, CA 92117 High-Performance Computing / Lustre Filesystems / Scale-out Storage
_______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit https://beowulf.org/cgi-bin/mailman/listinfo/beowulf
