ab-Stream - A Framework for programming Many-core

• Autorzy: Gan X. , Wang Z. , Shen L. , Zhu Q.

Warianty tytułu

PL

ab-Stream – struktura do programowania procesorów wielordzeniowych

• Języki publikacji: EN

Abstrakty

EN

The common approach to program many-core processor is to write processor-specific code with low level APIs for different processors, which could achieve good performance but would result in serious portability issues: programmers are required to write a specific version code for target architecture. Therefore, we present ab-Stream, an extensible framework for programming many-threaded processor based on SUIF Intermediate Representation. ab-Stream abstracts many-core many-threaded processor into a unified architecture and ab-Stream program is an OpenMP-like program with different directives for many-core processor. Furthermore, a prototype of ab-Stream was implemented to map ab-Stream programs into many-core GPU. Experiments show that our implementation can execute transformed code correctly and efficiently on CUDA-enabled GPUs. Furthermore, performance of ab-Stream version code produced by our prototype can outperform original GPU code and is close to handoptimized GPU code.

PL

Zaprezentowano szkielet (framework) ab-Stream do programowania wielordzeniowych procesorów. System bazuje na formacie SUIF (Standford University Intermediate Format).

Słowa kluczowe

EN

many-core; ab-Stream; intermediate representation; GPU

PL

procesory wielordzeniowe; programowanie

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2012
• Tom: R. 88, nr 7b
• Strony: 341--344
• Opis fizyczny: Bibliogr. 19 poz., schem., tab., wykr.

Twórcy

autor

Gan X.

• State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha 410073, China

autor

Wang Z.

• School of Computer, National University of Defense Technology University, Changsha 410073, China

autor

Shen L.

• School of Computer, National University of Defense Technology University, Changsha 410073, China

autor

Zhu Q.

• State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha 410073, China
• School of Computer, National University of Defense Technology University, Changsha 410073, China

Bibliografia

• [1] Bo Zhang, Zheng-Hui Xue, Ren Wu, et.al, “Acceleration of FDTD algorithm based on GPU computing”, Chinese Journal of Radio Science, Vol.26, No.1, pp108-112, 2011.
• [2] K.V. Kalgin, “Implementation of algorithms with a fine-grained parallelism on GPUs”, Numerical Analysis and Applications, Vol.4, No.1, pp 46-55, 2011.
• [3] F. Dehne, G. Hickey, A. Rau-Chaplin, et.al, “Parallel catastrophe modeling on a Cell/BE”, International Journal of Parallel, Emergent and Distributed Systems, Vol.25, No.5, pp 401-410, 2010.
• [4] H. Vandierendonck, S. Rul, M. Questier, et.al, “Experiences with parallelizing a bio-informatics program on the Cell BE”, Proceedings of the third International Conference on High Performance Embedded Architectures and Compilers (HiPEAC'08), pp 161-175, 2008.
• [5] Hai-yan Li, Chun-yuan Zhang, Li Li, et.al, “Transform coding on programmable stream processors”, Journal of Supercomputing, Vol.45, No.1, pp 66-87, 2008.
• [6] Xue-Jun Yang, Li-Fang Zeng, Yu Deng, et.al, “Optimization approaches of organizing streams on imagine processor”, Chinese Journal of Computers, Vol.31, No.7, pp 1092-1100, 2008.
• [7] Khronos Group. OpenCL specification.
• [8] Chuntao Hong, Dehao Chen, Wenguang Chen, et.al, “MapCG: Writing parallel program portable between CPU and GPU”, Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT'10), pp 217-226, 2010.
• [9] P. H. Wang, J. D. Collins, G. N. Chinya, et.al, “ EXOCHI: Architecture and programming environment for a heterogeneous multi-core multithreaded system”, Proceedings of International Conference on Programming Language Design and Implementation (PLDI'07), pp 156–166, 2007.
• [10] Pieter Bellens, Josep M Perez, Rosa M Badia, et.al, “CellSs: a programming model for the CELL BE Architecture”, Proceedings of ACM/IEEE Conference on Supercomputing (SC'06), pp 86–98, 2006.
• [11] Ian Buck, Tim Foley, Daniel Reiter Horn, et.al, “Brook for GPUs: stream computing on graphics hardware”, ACM Transaction on Graphics, Vol.23, No. 3, pp 777–786, 2004.
• [12] NVIDIA, “CUDA programming guide”, 2008.
• [13] Qiming Hou, Kun Zhou, Baining Guo, “BSGP: Bulksynchronous GPU programming”, ACM Transactions on Graphics, Vol.27, No.3, 9, 2008.
• [14] Peter Matton, et.al, Imagine Programming Systems User’s Guide, 2002.
• [15] Michael D. Linderman, Jamison D. Collins, Hong Wang, et.al, “Merge: A programming model for heterogeneous multicore systems”, ACM SIGPLAN Notices (ASPLOS'08), Vol.43, No.3, pp 287-296, 2008.
• [16] David L Moore, “The SUIF Programmer Guide”, 1999.
• [17] Xinbiao Gan, Zhiying Wang, LiShen, et.al, “Data Layout Pruning on GPU”, Applied Mathematics &Information Sciences, Vo.5, No.2, pp 129S-168S, 2011.
• [18] CUDA benchmark suite.
• [19] http://www.crhc.uiuc.edu/impact/cudabench.html. 2010.