Best way to accelerate embarrassingly parallel app

Best way to accelerate embarrassingly parallel app author Webmaster1 On: 11/30/2011 Views: 45



I'm helping someone with an embarrassingly parallel application. What's the best way to spend $10K to $15K to receive the maximum number of simultaneous threads of execution? The focus is on threads of execution as memory requirements are decently low e.g. ~512mb in memory at any given time (maybe up to 2 to 3X that at the very high end). I've looked at the latest Tesla card and am having trouble justifying the markup for what's essentially "double precision FP being enabled, a few heat improvements, and ECC which actually decreases available memory (I don't need the ECC)." Spending close to $11K for the 4 Teslas in a 1u setup seems ridiculous when GTX cards can be replaced for a fraction of the cost? Note, they don't have to pay the power/cooling bill. Amazon is too expensive for this level of performance, so can't go cloud. Any parallel architectures out there? Any good manycore offerings that I've missed e.g. somebody who can stuff a ton of ARM or other CPUs in a box? It would be great if this could be easily addressed via a PCI or other standard interface. Should I just stuff 4 GTX cards in a server and replace them as they die from heat? It's mainly single FP operations that I'm parallelizing, but double precision would be "nice to have". Thanks for any thoughts!Website: www.SinaBahram.comTwitter: @SinaBahram




For ThoughtLeader

CIO Index

Our Focus is On Your Agenda

CIO Index is the world's largest professional network for CIOs - of the CIO, for the CIO, by the CIO. 

Over 75,000 CIOs and other IT Executives use CIO Index to Learn, Network and Share.


Cioindex, Inc.

  • (+1) 800-309-3550
  • Mon - Fri 9:00am - 5:00 pm
  • 375 North Stephanie St., Ste 1411, Henderson, NV 89014