• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

University is buying new supercomputer

C

cmdrmoocow

Golden Member
It's a Dell Blade server array with 256 3.2 Xeons with 6 managing Xeons. I have no idea on the RAM capacity.

Google has failed me for an estimater. Anyone know of one?
 
Originally posted by: cmdrmoocow
It's a Dell Blade server array with 256 3.2 Xeons with 6 managing Xeons. I have no idea on the RAM capacity.

Google has failed me for an estimater. Anyone know of one?
Click to expand...

If you assume you get one FLOP/clock cycle on the Xeons (I have no idea how accurate this really is when running scientific apps; something like SSE2/3 can probably improve wildly on this), I would estimate the general computational power at somewhere around 256 * 3,200,000,000 = 819,200,000,000 ~= 800GFLOPS/sec. Optimized code using SSE might double or triple that, assuming the problem is conducive to SIMD parallelization. That's a pretty rough estimate, admittedly...
 
Originally posted by: clarkey01
If they had scence they'd get opteron, fools.

you cant beat a point to point bus.
Click to expand...


And if you knew how to spell 'sense', your opinion (biased it may be), may be more important.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top