Output details
11 - Computer Science and Informatics
University of Warwick
An investigation of the performance portability of OpenCL
<02> Published in one of the top three journals in the field, this paper reports on a three-year industry/government-funded research project, with AWE and SNL, on code development strategies for heterogeneous HPC architectures. Preliminary versions of the paper were presented at the Daresbury GPU Workshop 2010 (NVIDIA prize for best paper), the Many-core and Reconfigurable Supercomputing Conference 2011 (ranked as the top paper), and SC’12. It is the first paper to report on OpenCL device fissioning and has impacted on other research areas including parallel run-time verification (Berkovich, Waterloo) and porting of Navier-Stokes codes to GPUs (Rossi, Barcelona).