The Community for Technology Leaders
2013 21st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2013) (2013)
Belfast
Feb. 27, 2013 to March 1, 2013
ISSN: 1066-6192
ISBN: 978-1-4673-5321-2
pp: 131-139
D. Buono , Dept. Comput. Sci., Univ. of Pisa, Pisa, Italy
M. Danelutto , Dept. Comput. Sci., Univ. of Pisa, Pisa, Italy
S. Lametti , Dept. Comput. Sci., Univ. of Pisa, Pisa, Italy
M. Torquati , Dept. Comput. Sci., Univ. of Pisa, Pisa, Italy
ABSTRACT
Efficient programming of general purpose many-core accelerators poses several challenging problems. The high number of cores available, the peculiarity of the interconnection network, and the complex memory hierarchy organization, all contribute to make efficient programming of such devices difficult. We propose to use parallel design patterns, implemented using algorithmic skeletons, to abstract and hide most of the difficulties related to the efficient programming of many-core accelerators. In particular, we discuss the porting of the FastFlow framework on the Tilera TilePro64 architecture and the results obtained running synthetic benchmarks as well as true application kernels. These results demonstrate the efficiency achieved while using patterns on the TilePro64 both to program stand-alone skeleton-based parallel applications and to accelerate existing sequential code.
INDEX TERMS
Skeleton, Memory management, Programming, Instruction sets, Coherence, Libraries,TilePro64, Structured programming, many-core, shared memory, accelerators
CITATION
D. Buono, M. Danelutto, S. Lametti, M. Torquati, "Parallel Patterns for General Purpose Many-Core", 2013 21st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2013), vol. 00, no. , pp. 131-139, 2013, doi:10.1109/PDP.2013.27
94 ms
(Ver 3.3 (11022016))