@einjen That's a good question, and it's probably more about regional politics. I know that in the case of some of our customers, they performed environmental studies and worked with local authorities to make sure any discharge was not ha... #whyhpccooling https://t.co/WmmT2Nt2VM
@einjen Yes, and we at Cray want to design systems that are flexible enough to make use of what's available to a data center to both save money and save power. #whyhpccooling https://t.co/pynO2BfPSx
@StaceyMc_HPC This includes looking at the data center as a whole so that weโre able to bring the best performance but optimized for space, power, performance, schedule, individually or across all of them. #whyhpccooling https://t.co/lZ09iACJBB
@cray_inc (1/2) More effective and efficient cooling reduces wasted power therefore reducing costs. Keeping modern processors cool also creates higher performance leading to better TCO since there is more profit and lower costs. #whyhpccooling https://t.co/1ZnduRtJli
@einjen We've had some customers use cool water from neighboring lakes and some that pull cool water from underground aquifers making good use of "free" chilled water. #whyhpccooling https://t.co/iky3vFa8Hz
@einjen The most cost effective solution is usually to use the water at the temp it's available if it works within the specifications for the chips. Cooler water available for "free" is always a plus. #whyhpccooling https://t.co/xjTcuxFWDE
@cray_inc Itโs not just that they produce more heat, itโs that they also perform worse. By bringing that cooling directly to the processor, weโre able to keep all of the processors working a single problem working to their best. #whyhpccooling https://t.co/NqEApUyOhD
@einjen (1/2) Good question, and it somewhat depends on the technologies involved. With some processor types, they can perform at their best even when cooled with 40C water. Others may not and might require 32C. #whyhpccooling https://t.co/VqEudF9Z9c
@cray_inc Overall climate that the data center is in, current data center conditions and capabilities, other equipment in the data center, and access & costs of cool or warm water for cooling all play a role. #whyhpccooling https://t.co/dcKlSQ3LC1
@cray_inc (2/2) At smaller scales, perhaps itโs more about fitting an existing environment with minor changes to the data center yet looking for the best performance available. #whyhpccooling https://t.co/IePVOhokxl
@cray_inc (1/2) The approach doesnโt change, as the physics and the challenges are the same, but the optimization and options may differ based on scale. #whyhpccooling https://t.co/EVI5o4pV18
@cray_inc That's a bit subjective, and it differs by metric. By performance, I'd say about 1PF peak for some of this discussion. #whyhpccooling https://t.co/XP86232f5A
I think that the decision criteria often comes down to the best TCO while meeting performance goals. That TCO calculation should include the costs for installing in a data center and any changes required, the acquisition costs, and the ru... #whyhpccooling https://t.co/CAWa9Y2BV9
(3/3) For data center considerations, it's often about reducing the costs of the cooling solution. Some have access to "free" air cooling, and others have access to water that can reduce their TCO. #whyhpccooling https://t.co/Q7UdXsXh1A