Unbalanced tree search on a manycore system using the GPI programming model

• Autor(a) principal: Machado, Rui
• Data de Publicação: 2011
• Outros Autores: Lojewski, Carsten, Abreu, Salvador, Pfreundt, Franz-Josef
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10174/4645
• topic: Distributed Computing; UTS

The recent developments in computer architectures progress towards systems with large core count (Manycore) which expose more parallelism to applications. Some applications named irregular and unbalanced applications demand a dynamic and asynchronous load balance implementation to utilize the full performance a Manycore system. For example, the recently established Graph500 benchmark aims at such applications. The UTS benchmark characterizes the performance of such irregular and unbalanced computations with a tree-structured search space that requires continuous dynamic load balancing. GPI is a PGAS API that delivers the full performance of RDMA-enabled networks directly to the application. Its programming model focuses the use of one-sided asynchronous communication, overlapping computation and communication. In this paper we address the dynamic load balancing requirements of unbalanced applications using the GPI programming model. Using the UTS benchmark, we detail the implementation of a work stealing algorithm using GPI and present the performance results. Our performance evaluation shows significant improvements when compared with the optimized MPI version with a maximum performance of 9.5 billion nodes per second on 3072 cores.