Please use this identifier to cite or link to this item:
https://doi.org/10.1109/SC.Companion.2012.279
Title: | Mapping streaming applications onto GPU systems | Authors: | Huynh, H.P. Hagiescu, A. Wong, W.-F. Goh, R.S.M. Ray, A. |
Keywords: | GPU Multi-GPU Streaming Application StreamIt |
Issue Date: | 2012 | Citation: | Huynh, H.P.,Hagiescu, A.,Wong, W.-F.,Goh, R.S.M.,Ray, A. (2012). Mapping streaming applications onto GPU systems. Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012 : 1488-1490. ScholarBank@NUS Repository. https://doi.org/10.1109/SC.Companion.2012.279 | Abstract: | We describe an efficient and scalable code generation framework that automatically maps general purpose streaming applications onto GPU systems. This architecture-driven framework takes into account the idiosyncrasies of the GPU pipeline and the unique memory hierarchy. The framework has been implemented as a back-end to the StreamIt programming language compiler. Several key features in this framework ensure maximized performance and scalability. First, the generated code increases the effectiveness of the on-chip memory hierarchy by employing a heterogeneous mix of compute and memory access threads. Our scheme goes against the conventional wisdom of GPU programming which is to use a large number of homogeneous threads. Second, we utilise an efficient stream graph partitioning algorithm to handle larger applications and achieve the best performance under the given on-chip memory constraints. Lastly, the framework maps complex applications onto multiple GPUs using a highly effective pipeline execution scheme. Our comprehensive experiments show its scalability and significant speedup compared to a state-of - The-art solution. © 2012 IEEE. | Source Title: | Proceedings - 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC 2012 | URI: | http://scholarbank.nus.edu.sg/handle/10635/78221 | ISBN: | 9780769549569 | DOI: | 10.1109/SC.Companion.2012.279 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.