The deep computing messaging framework

作者: Sameer Kumar , Joseph Ratterman , Brian Smith , Charles J. Archer , Gabor Dozsa

DOI: 10.1145/1375527.1375544

关键词:

摘要: We present the architecture of Deep Computing Messaging Framework (DCMF), a message passing runtime designed for Blue Gene/P machine and other HPC architectures. DCMF has been to easily support several programming paradigms such as Message Passing Interface (MPI), Aggregate Remote Memory Copy (ARMCI), Charm++, others. This is made possible provides an application interface (API) with active messages non-blocking collectives. being open sourced layered component based multiple levels abstraction, allowing members community contribute new components its design at various layers. The can be extended architectures through development specific implementations classes. production on takes advantage direct memory access (DMA) hardware offload work achieve good overlap computation communication. take fact that node symmetric multi-processor four cache-coherent cores use multi-threading optimize performance collective network. also evaluation show it delivers close limits.

参考文章(9)
L.V. Kale, M. Bhandarkar, N. Jagathesan, S. Krishnan, J. Yelon, Converse: an interoperable framework for parallel programming international conference on parallel processing. pp. 212- 217 ,(1996) , 10.1109/IPPS.1996.508060
Jarek Nieplocha, Bryan Carpenter, ARMCI: A Portable Remote Memory Copy Libray for Ditributed Array Libraries and Compiler Run-Time Systems international parallel processing symposium. pp. 533- 546 ,(1999) , 10.1007/BFB0097937
William Gropp, Ewing Lusk, Nathan Doss, Anthony Skjellum, A high-performance, portable implementation of the MPI message passing interface standard parallel computing. ,vol. 22, pp. 789- 828 ,(1996) , 10.1016/0167-8191(96)00024-5
F. Petrini, Wu-chun Feng, A. Hoisie, S. Coll, E. Frachtenberg, The Quadrics network: high-performance clustering technology IEEE Micro. ,vol. 22, pp. 46- 57 ,(2002) , 10.1109/40.988689
Gheorghe Almasi, Laxmikant V. Kalé, Sameer Kumar, Chao Huang, Achieving strong scaling with NAMD on Blue Gene/L international parallel and distributed processing symposium. pp. 61- 61 ,(2006) , 10.5555/1898953.1898995
N. R. Adiga, M. A. Blumrich, D. Chen, P. Coteus, A. Gara, M. E. Giampapa, P. Heidelberger, S. Singh, B. D. Steinmacher-Burow, T. Takken, M. Tsao, P. Vranas, Blue Gene/L torus interconnection network Ibm Journal of Research and Development. ,vol. 49, pp. 265- 276 ,(2005) , 10.1147/RD.492.0265
G. Almasi, C. Archer, J. G. Castanos, J. A. Gunnels, C. C. Erway, P. Heidelberger, X. Martorell, J. E. Moreira, K. Pinnow, J. Ratterman, B. D. Steinmacher-Burow, W. Gropp, B. Toonen, Design and implementation of message-passing services for the Blue Gene/L supercomputer Ibm Journal of Research and Development. ,vol. 49, pp. 393- 406 ,(2005) , 10.1147/RD.492.0393
Christopher Barton, CĆlin Casçaval, George Almási, Yili Zheng, Montse Farreras, Siddhartha Chatterje, José Nelson Amaral, Shared memory programming for large scale machines ACM SIGPLAN Notices. ,vol. 41, pp. 108- 117 ,(2006) , 10.1145/1133255.1133995
M. Banikazemi, R.K. Govihdaraju, R. Blackmore, D.K. Panda, MPI-LAPI: an efficient implementation of MPI for IBM RS/6000 SP systems IEEE Transactions on Parallel and Distributed Systems. ,vol. 12, pp. 1081- 1093 ,(2001) , 10.1109/71.963419