Accelerating sequential programs on commodity multi-core processors

详细信息    查看全文

• 作者：Yuanming Zhang ; Gang Xiao ; Takanobu Baba
• 关键词：Commodity multi-core processors ; Pipeline parallelism ; Clustered communication mechanism
• 刊名：Journal of Parallel and Distributed Computing
• 出版年：April, 2014
• 年：2014
• 卷：74
• 期：4
• 页码：2257-2265
• 全文大小：1103 K

文摘

A recently proposed pipelined multithreading (PMT) technique exhibits wide applicability in parallelizing general sequential programs on multi-core processors. However, significant inter-core communication overhead limits PMT performance and prevents its commercial utilization. A simple and effective clustered pipelined multithreading (CPMT) approach is presented to accelerate sequential programs on commodity multi-core processors. This CPMT technique adopts a clustered communication mechanism that can yield very low average communication overhead by eliminating false sharing as well as reducing communication operation and transit delays in the software-only approach. A single-producer/single-consumer concurrent lock-free clusteredQueue algorithm based on a two-level queue structure is also proposed. The accuracy of CPMT is theoretically demonstrated. The performances of the algorithm and CPMT are evaluated on a commodity AMD Phenom four-core processor. The number of enqueue and dequeue times of the algorithm are 20.8 and 23 cycles given an appropriate parameter, respectively. The speedup of CPMT ranges from 13.1% to 119.8% for typical loops extracted from the SPEC CPU 2000 benchmark suite.