PDA

View Full Version : OSU Grad Student Explores Strengths, Challenges of Cray, IBM, and Nvidia


News
03-29-12, 06:30 AM
http://www.osc.edu/press/releases/2012/images/SaniyahBokharislrg.jpg (http://www.osc.edu/press/releases/2012/Bokhari.shtml)When it comes to benchmarks, your performance mileage may vary. Now an Ohio State University researcher has established some side-by-side performance comparisons that surveying the wide range of parallel system architectures offered in the supercomputer market, .

We explore the parallelization of the subset-sum problem on three contemporary but very different architectures, a 128-processor Cray massively multithreaded machine, a 16-processor IBM shared memory machine, and a 240-core NVIDIA graphics processing unit,?? said Bokhari.*??These experiments highlighted the strengths and weaknesses of these architectures in the context of a well-defined combinatorial problem.??

Read the Full Story (http://www.osc.edu/press/releases/2012/Bokhari.shtml).

http://insidehpc.com/?ak_action=api_record_view&id=28156&type=feedRelated posts:

NVIDIA snuggles up with 2 TFLOPS (http://insidehpc.com/2009/01/12/nvidia-snuggles-up-with-2-tflops/)
Nvidia Announces Latest Tesla Platform (http://insidehpc.com/2008/06/16/nvidia-announces-latest-tesla-platform/)
Dell Spikes Xeon E5/R Servers with Nvidia GPUs (http://insidehpc.com/2012/03/06/dell-spikes-xeon-e5r-servers-with-nvidia-gpus/)


http://feeds.feedburner.com/~ff/InsideHPC?d=yIl2AUoC8zA (http://feeds.feedburner.com/~ff/InsideHPC?a=dtGG64eWEFM:quyQFLiPxd8:yIl2AUoC8zA) http://feeds.feedburner.com/~ff/InsideHPC?i=dtGG64eWEFM:quyQFLiPxd8:F7zBnMyn0Lo (http://feeds.feedburner.com/~ff/InsideHPC?a=dtGG64eWEFM:quyQFLiPxd8:F7zBnMyn0Lo) http://feeds.feedburner.com/~ff/InsideHPC?i=dtGG64eWEFM:quyQFLiPxd8:V_sGLiPBpWU (http://feeds.feedburner.com/~ff/InsideHPC?a=dtGG64eWEFM:quyQFLiPxd8:V_sGLiPBpWU)
http://feeds.feedburner.com/~r/InsideHPC/~4/dtGG64eWEFM

More... (http://feedproxy.google.com/~r/InsideHPC/~3/dtGG64eWEFM/)