Extending MPI to accelerators
暂无分享,去创建一个
Current trends in computing and system architecture point towards a need for accelerators such as GPUs to have inherent communication capabilities. We review previous and current software libraries that provide pseudo-communication abilities through direct message passing. We show how these libraries are beneficial to the HPC community, but are not forward-thinking enough. We give motivation as to why MPI should be extended to support these accelerators, and provide a road map of achievable milestones to complete such an extension, some of which require advances in hardware and device drivers.
[1] Orion S. Lawlor,et al. Message passing for GPGPU clusters: CudaMPI , 2009, 2009 IEEE International Conference on Cluster Computing and Workshops.
[2] John D. Owens,et al. GPU-to-CPU Callbacks , 2010, Euro-Par Workshops.
[3] John D. Owens,et al. Message passing on data-parallel architectures , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.