Authors: Yanhua Li; Youhui Zhang; Cihang Jiang; Weiming Zheng
Addresses: Department of Computer Science, Tsinghua University, Beijing, China ' Department of Computer Science, Tsinghua University, Beijing, China ' Department of Computer Science, Tsinghua University, Beijing, China ' Department of Computer Science, Tsinghua University, Beijing, China
Abstract: Compared with the traditional shared-memory programming model, message passing models for chip multiprocessors (CMPs) have distinct advantages due to the relative ease of validation and the fact that they are more portable. This paper proposes a design of integrating a message-passing engine into each router of the network-on-chip as well as the programming-friendly message passing interface for these engines. Combined with the DMA mechanism, the proposed design applies the on-chip RAM as intermediary message buffer, and frees the CPU core from message-passing operations to a large extent. The detailed design and implementation, including the register-transfer-level (RTL) descriptions of the engine, are presented. Evaluations show that: compared with the software-based solution, it can decrease the message passing latency by one or two orders of magnitude. Co-simulation also demonstrates that the proposed designs effectively boost the performance of point-to-point communications on-chip, while the consumptions of power and chip-area are both limited.
Keywords: message-passing; chip-multiprocessor; network-on-chip; NoC; hardware support.
International Journal of High Performance Computing and Networking, 2017 Vol.10 No.4/5, pp.391 - 402
Received: 19 Oct 2015
Accepted: 10 Apr 2016
Published online: 18 Aug 2017 *