Nimbic’s parallelization strategy, built upon a two‐layer foundation of (a) fine‐grained, multithreaded solver architectures for the multicore environment and (b) coarse‐grained, distributed architectures for
multiple processors connected by high‐speed buses is summarized. Nimbic’s parallelization methodology is tuned to simultaneously exploit Nimbic’s proprietary fast solver technology and to take advantage of emerging multicore and many‐core processors.
|
Editorial
Upcoming Events
DAC 2012 at San Francisco CA - Jun 3 - 7, 2012
|
|
|
