Energy-Performance Tradeoffs in Software Transactional Memory
Resumo
Transactional memory (TM) is a new synchronization mechanism devised to simplify parallel programming, thereby helping programmers to unleash the power of current multicore processors. Although software implementations of TM (STM) have been extensively analyzed in terms of runtime performance, little attention has been paid to an equally important constraint faced by nearly all computer systems: energy consumption. In this work we conduct a comprehensive study of energy and runtime tradeoff sin software transactional memory systems. We characterize the behavior of three state-of-the-art lock-based STM algorithms, along with three different conflict resolution schemes. As a result of this characterization, we propose a DVFS-based technique that can be integrated into the resolution policies so as to improve the energy-delay product (EDP). Experimental results show that our DVFS-enhanced policies are indeed beneficial for applications with high contention levels. Improvements of up to 59% in EDP can be observed in this scenario, with an average EDP reduction of 16% across the STAMP workloads.
Palavras-chave:
Delay, Algorithm design and analysis, Genomics, Bioinformatics, Program processors, Energy consumption, Energy Consumption, Transactional Memory, Parallel Computing
Publicado
24/10/2012
Como Citar
BALDASSIN, Alexandro; CARVALHO, João P. L. de; GARCIA, Leonardo A. G.; AZEVEDO, Rodolfo.
Energy-Performance Tradeoffs in Software Transactional Memory. In: INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD), 24. , 2012, Nova Iorque/EUA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2012
.
p. 147-154.
