Rubens H. P. de Almeida
Felipe M. G. França
ABSTRACT
This work presents a GPU-based implementation of the Gamma multiset rewriting paradigm. Inspired by the chemical reaction metaphor, Gamma was conceived as a highlevel abstract language for programs specification in a very simple, concise, and naturally parallel way, making clearer the distinction between the problem itself and the underlying implementation issues. We believe that the computational model adopted by Gamma matches naturally with the Graphics Processing Units execution mode, once both concepts consist basically in parallel processing of data. We extended an earlier distributed and parallel implementation of the Gamma language called Gamma-Base, adding support to execution of Gamma programs over the GPUs, and we called this new implementation Gamma-GPU. Practical experiments were conducted in a GPU cluster, which showed us the correctness of the new implementation, besides good speedups comparing to a sequential Gamma implementation, proving the contributions introduced by our work.
- J.-P. Banâtre and D. Le Métayer. A new computational model and its discipline of programming. In: Rapport de Recherche 566, INRIA, France, 1986.Google Scholar
- C. Creveuil. Implementation of gamma on the connection machine. In Research Directions in High-Level Parallel Programming Languages, pages 219--230, 1992. Google ScholarDigital Library
- R. H. P. de Almeida. Uma derivação do paradigma de reescrita de multiconjuntos gamma para a arquitetura gpu. M.Sc. Thesis, PESC, Universidade Federal do Rio de Janeiro, Rio de Janeiro, RJ, Brazil, 2015.Google Scholar
- R. R. de Mello Junior. Fusão de dados em gamma. MSc. Thesis, PESC, Universidade Federal do Rio de Janeiro, Rio de Janeiro, RJ, Brazil, 2015.Google Scholar
- F. Franca, J. Muylaert Filho, and G. Paillard. Uma proposta de um escalonador para gamma. In II Workshop em Sistemas Computacionais de Alto Desempenho, pages 47--54, Pirenópolis, Brazil, 2001.Google Scholar
- H. Lin, J. Kemp, and P. Gilbert. Computing gamma calculus on computer cluster. Int. J. Technol. Diffus., 1(4):42--52, Oct. 2010. Google ScholarDigital Library
- G. Paillard, F. Franca, and J. Muylaert Filho. A distributed implementation of structured gamma. In Parallel and Distributed Systems. ICPADS 2001. Proceedings. Eighth International Conference on, pages 445--450, 2001. Google ScholarDigital Library
Index Terms
- A GPU-based implementation for the gamma multiset rewriting paradigm
Recommendations
On the Efficacy of a Fused CPU+GPU Processor (or APU) for Parallel Computing
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance ComputingThe graphics processing unit (GPU) has made significant strides as an accelerator in parallel computing. However, because the GPU has resided out on PCIe as a discrete device, the performance of GPU applications can be bottlenecked by data transfers ...
Divide and Conquer on Hybrid GPU-Accelerated Multicore Systems
With the raw computing power of graphics processing units (GPUs) being more widely available in commodity multicore systems, there is an imminent need to harness their power for important numerical libraries such as LAPACK. In this paper, we consider ...
PIPSEA: A Practical IPsec Gateway on Embedded APUs
CCS '16: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications SecurityAccelerated Processing Unit (APU) is a heterogeneous multicore processor that contains general-purpose CPU cores and a GPU in a single chip. It also supports Heterogeneous System Architecture (HSA) that provides coherent physically-shared memory between ...
Comments