Slashdot Mirror
IBM Sets Supercomputer Speed Record
T.Hobbes writes "IBM's BlueGene/L has set a new speed record at 36.01 TFlops, beating the Earth Simulator's 35.86 TFlops, according to internal IBM testing. 'This is notable because of the fixation everyone has had on the Earth Simulator,' said Dave Turek, I.B.M.'s vice president for the high-performance computing division. The AP story is here; the NY Times' story is here."
Place your bets, people!
What percentage of posts in the first 15 minutes will be about the spelling of the last word in the title, and what percentage about the content?
G
Each node is running an embedded linux kernel.
No.
each node has 2 cpus and 4 fpus, custom non-preemptive kernel
I see a contradiction with your previous statement here...
As I said in my comment above, the compute nodes run an IBM proprietary kernel (apparently the kernel you're describing), and every 64 compute nodes are managed by an i/o node running Linux.
I can't resist adding that GCC won't use the second FPU on each die...
So what's the problem? It's not like anybody who could afford a highly specialized and expensive machine like this one couldn't afford to shell out some $$$ for xlf.
Anyways, I'm sure that if this modified PPC core gets popular outside multi-million dollar supercomputers, the gcc team will figure out how to utilize the second FPU.
You could probably consider a program to be thinking if the initial instructions allow it to develop it's own instructions (derived from something) and delete the old ones so it isn't bound to them.
-- Get
It's simple. Look at the Turing test. As long as any human interacting with it cannot distinguish it as being a machine and not a human, that's pretty much thinking. You really don't need to know the internals. In fact you don't know the brain's internals anyway.
Except during the first month or so of operation there was always a queue of jobs waiting to run. In fact, applying to use that computer is almost exactly like writing a grant proposal, except that the good proposals are awarded CPU hours instead of money.
In scientific computation, researchers can always use faster computers. The accuracy and scope of the models will expand to fill available computational resources.