Assuming the later, check among Supermicro & Dell servers. Last time I needed to setup a cluster, the Dell R610s were a good pick, giving great manageability over the LAN, low volume and decent features (balanced storage space along with cpu capacity, around 8 cores + 8 TBs per 1u blade). Don't rule out also options like Shuttle XPCs, they are damned robust in thermal aspects (hey, you'll be running these continuously, won't you?). Finally, don't underestimate the need for local sysadmining; you will likely need to setup a queueing system (Torque, *PBS*, SLURM, SGE, LSF, NQS, Condor) and manage the whole thing. This won't happen automatically, take a note on that. If you run something of the pbs or sge family I can happily help with setting up a tool called qtop
I'm pretty certain that the science is sound), Morgado's pump is in limbo because he hasn't yet found anyone who'd lend him $4-million or $10-million to build a factory. He has plenty of offers to buy the technology outright, but he has the audacity to presume that he should be the one to profit from his invention.
Imagine if the demand for energy suddenly plunged by more than 25%. Oil is only going for $100/barell because demand roughly matches supply. If supply exceeds demand by a significant percentage, we'd be back to $1/gallon gas in a heartbeat.
If Morgado's invention is at present tested and reliable enough to do all that, it worths more than 10^7 $ and everyone who has that money not investing it is stupid. If not, don't make us cry for his uninvested intellectual property, he is just a hacking good inventor who can build something lesser to raise 10^7 $s until the next stage. In short, if he has faith about this invention, then he should make a business compromise. btw. oil supply is controlled by OPEC, prices are not really an accident.
"Indecision is the basis of flexibility" -- button at a Science Fiction convention.