The Community for Technology Leaders
2010 19th International Conference on Parallel Architectures and Compilation Techniques (PACT) (2010)
Vienna, Austria
Sept. 11, 2010 to Sept. 15, 2010
ISBN: 978-1-5090-5032-1
pp: 205-215
Jayanth Gummaraju , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
Ben Sander , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
Laurent Morichetti , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
Benedict R. Gaster , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
Michael Houston , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
Bixia Zheng , Compute Research Group, Advanced Micro Devices Inc., Sunnyvale, California, USA
ABSTRACT
Modern processors are evolving into hybrid, heterogeneous processors with both CPU and GPU cores used for general-purpose computation. Several languages such as Brook, CUDA, and more recently OpenCL are being developed to fully harness the potential of these processors. These languages typically involve the control code running on the CPU and the performance-critical, data-parallel kernel code running on the GPUs. In this paper, we present Twin Peaks, a software platform for heterogeneous computing that executes code originally targeted for GPUs efficiently on CPUs as well. This permits a more balanced execution between the CPU and GPU, and enables portability of code between these architectures and to CPU-only environments. We propose several techniques in the runtime system to efficiently utilize the caches and functional units present in CPUs. Using OpenCL as a canonical language for heterogeneous computing, and running several experiments on real hardware, we show that our techniques enable GPGPU-style code to execute efficiently on multicore CPUs with minimal runtime overhead. These results also show that for maximum performance, it is beneficial for applications to utilize both CPUs and GPUs as accelerator targets.
INDEX TERMS
Runtime, GPGPU, Multicore, OpenCL, Programmability
CITATION
Jayanth Gummaraju, Ben Sander, Laurent Morichetti, Benedict R. Gaster, Michael Houston, Bixia Zheng, "Twin Peaks: A software platform for heterogeneous computing on general-purpose and graphics processors", 2010 19th International Conference on Parallel Architectures and Compilation Techniques (PACT), vol. 00, no. , pp. 205-215, 2010, doi:
216 ms
(Ver 3.3 (11022016))