Abstract | ||
---|---|---|
Industry is moving towards multi-core designs as we have hit the memory and power walls. Multi-core designs are very effective to exploit thread-level parallelism (TLP) but do not provide benefits when executing serial code (applications with low TLP, serial parts of a parallel application and legacy code). In this paper we propose Anaphase, a novel approach for speculative multithreading to improve single-thread performance in a multi-core design. The proposed technique is based on a graph partitioning technique which performs a decomposition of applications into speculative threads at instruction granularity. Moreover, the proposed technique leverages communications and pre-computation slices to deal with inter-thread dependences. Results presented in this paper show that this approach improves single-thread performance by 32% on average and up to 2.15x for some selected applications of the Spec2006 suite. In addition, the proposed technique outperforms by 21% on average schemes in which thread decomposition is performed at a coarser granularity. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/PACT.2009.27 | Raleigh, NC |
Keywords | Field | DocType |
multi-threading,Anaphase,Spec2006 suite,fine-grain thread decomposition scheme,graph partitioning technique,instruction granularity,multi-core designs,speculative multithreading,thread-level parallelism,Speculative multithreading,automatic parallelization,multicore,single-thread performance,thread-level parallelism | Multithreading,Task parallelism,Computer science,Parallel computing,Speculative multithreading,Real-time computing,Thread (computing),Legacy code,Granularity,Multi-core processor,Serial code | Conference |
ISSN | ISBN | Citations |
1089-795X | 978-0-7695-3771-9 | 6 |
PageRank | References | Authors |
0.72 | 23 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Madriles, C. | 1 | 6 | 0.72 |
Lopez, P. | 2 | 64 | 6.88 |
Codina, J.M. | 3 | 6 | 0.72 |
Gibert, E. | 4 | 6 | 0.72 |