On 2012-11-11, Pandu Poluan <pa...@poluan.info> wrote: > And, IIRC, Seymour Cray likes to use some inert fluoride-based coolant to > dunk the components of his supercomputer machines. And he would even go to > lengths to design a "coolant fountain" that's not only functional, but also > decorative.
Back in the 80's one of the local supercomputer companies (ETA Systems) built (and actually sold) machines which used CMOS CPU boards that ran submerged in liquid nitrogen. IIRC, they ran at around 150MHz and achieved 10 GFLOPS which was pretty amazing at the time... However, the system software was crap. Like Cray, ETA was a CDC spin-off and AFAICT, all CDC system software was awful. In any case, the product was a commercial failure. I heard through the grapevine that maintenance was a headache, and lots of boards failed due to thermal stress when they were taken in/out of the LN2. > That's the only qualms I have Re: water-coolant. I always an afraid > of leaks. So, I always wimped out and use the thermal wick kind of > almost, but not quite, somewhat similar to liquid coolant ;-) One of the nice things about LN2 is that it doesn't make such a mess when there's a leak. :) -- Grant
