A Comparative Study for Efficient Synchronization of Parallel ACO on Multi-core Processors in Solving QAPs
A Comparative Study for Efficient Synchronization of Parallel ACO on Multi-core Processors in Solving QAPs
复制标题
多核处理器上并行 ACO 高效同步求解 QAP 的比较研究
DOI：
10.1109/ssci.2015.160
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Noriyuki Fujimoto
中科院分区：
文献类型：
--
作者：
Shigeyoshi Tsutsui;Noriyuki Fujimoto
本文描述了三种多核处理器上蚁群优化并行同步模型在求解二次分配问题（qap）中的应用。这三种模型包括：(1)同步并行（SP），(2)异步并行（AP）和分布式异步并行（DAP）。并行执行研究最多可达16核。在三个模型中，DAP在各种大小的QAP实例上显示出最有希望的结果。它还显示出良好的扩展能力，可扩展到16核。
This paper describe three types of parallel synchronization models of ant colony optimization (ACO) on multi-core processors in solving quadratic assignment problems (QAPs). These three models include (1) Synchronous Parallel (SP), (2) Asynchronous Parallel (AP), and Distributed Asynchronous Parallel (DAP). Parallel executions are studied up to 16-core. Among three models, the DAP shows the most promising results over various sizes of QAP instances. It also shows a good scaleup capability up to 16-core.