Learn More
Over the past few years a large number of heuristics for performing scheduling of non-pipelined designs have been proposed. The quality of results produced by these heuris-tics have not been quantified and neither have these heuris-tics been compared on a common platform. In this paper we first present a new heuristic for performing non-pipelined scheduling(More)
General Purpose Graphics Processing Units (GPGPUs) are rapidly becoming an integral part of highperformance system architectures. The Tianhe-1A and Tsubame systems have received significant attention for their architectures that leverage GPGPUs. Increasingly many scientific applications that were originally written for CPUs using MPI for parallelism are(More)
  • 1