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.