Wade Doll

HPC Infrastructure visionary. My views are my own

[Wade Doll @DollWade]

@cray_inc You start at both ends of the problem. What does the processor require and what does the datacenter want to provide? Then you work through the solution in the middle to maximize performance and TCO. #whyhpccooling https://t.co/ytjoPnUcfS

[Wade Doll @DollWade]

@CurtW_HPC Curt, this is in total alignment with Cray's thinking. But I would stretch the goal to 45C warm water to cover EU markets #whyhpccooling https://t.co/Wr2HGfwVxK

[Wade Doll @DollWade]

@cray_inc Facilitating datacenters that want to get rid of chillers and use much more economical cooling towers. The result is the need to support much higher temperature coolants. #whyhpccooling https://t.co/OHNnN3ydz1

[Wade Doll @DollWade]

Jason, my comment about chilled water is just that it is an easier solution. But, not necessarily the right solution from a holistic view. #whyhpccooling https://t.co/7E5Rq59PZv

[Wade Doll @DollWade]

@CoolITSystems This sounds like a good question for CoolIT. Any insights? #whyhpccooling https://t.co/GlzcrGHQty

[Wade Doll @DollWade]

@cray_inc Cray would prefer ice water. But that is not in the best interest of the data center. it takes a lot more energy for the DC to create ice water than using "free" cooling tower methods #whyhpccooling https://t.co/0rZXQzrQfO

[Wade Doll @DollWade]

@cray_inc What solutions will fit into the data centers current and future desires wrt cooling infrastructure. How do these solutions satisfy cpu requirements, and how do we get there with the lowest TCO #whyhpccooling https://t.co/nDSA9NSLib

[Wade Doll @DollWade]

Jason, totally agree about the better granularity of rack based. But, I think when you get to large exascale systems (a lot of racks) there is some cost advantages of row based #whyhpccooling https://t.co/9dVDQJwHZN

[Wade Doll @DollWade]

@cray_inc (2/2) When you get to thousands of nodes, it makes sense to transition to liquid cooling for the performance, cost, and density advantages #whyhpccooling https://t.co/tiM4hye0EN

[Wade Doll @DollWade]

@cray_inc (1/2)To a degree. Small systems, say less than 256 nodes, produce a level of heat that can easily be handled by many data centers and by different methods. #whyhpccooling https://t.co/i6G5dRK3z4

[Wade Doll @DollWade]

@einjen RDHX gets you part of the way there. But, still having fans in the server uses up more power than directly liquid cooling with cold plates #whyhpccooling https://t.co/t3IbOirtgd

[Wade Doll @DollWade]

@cray_inc (2/2) Air cooling, while lower CAPEX, is at one end of the spectrum and water cooling is at the other with lower TCO. #whyhpccooling https://t.co/DcqnL2dCSQ

[Wade Doll @DollWade]

@cray_inc (1/2) There is a cross-over point where water cooling just makes more sense. This is driven by CPU requirements, desires to minimize cooling costs, and density. #whyhpccooling https://t.co/MCPjXSgpGk

[Wade Doll @DollWade]

Yes Brandon. Basically the more you can get into the liquid closest to the heat source will result in the lowest TCO #whyhpccooling https://t.co/joeU5fcj9v

[Wade Doll @DollWade]

@cray_inc I would also add Because of data center power constraints, the power demands of the cooling system take away from the available computational power. #whyhpccooling https://t.co/jE4VJyW7Py

[Wade Doll @DollWade]

@cray_inc The infrastructure and cost of the cooling systems scale with the high power demands of an Exascale system and is a significant burden on the full system TCO #whyhpccooling https://t.co/4GkgXabUZ4

[Wade Doll @DollWade]

Too Cool: A Look at the
Latest #Supercomputing Cooling Technologies | NEW #CrayBlog post from
@HPC_Badger https://t.co/W7bXmjwhEl
#HPCCooling #Exascale @ExascaleProject