A High-Throughput, Low-Power Asynchronous Mesh-of-Trees Interconnection Network for the Explicit Multi-Threading (XMT) Parallel Architecture

Loading...
Thumbnail Image

Files

umi-umd-5670.pdf (945.91 KB)
No. of downloads: 2061

Publication or External Link

Date

2008-08-04

Citation

DRUM DOI

Abstract

This thesis presents an asynchronous (clockless) Mesh-of-Trees network that consumes less power and area than the synchronous Mesh-of-Trees network, while maintaining high throughput and low latency. Two new asynchronous designs are proposed for the fundamental pipelined components of the network (routing and arbitration), which are optimized for power, area, latency and throughput. Mixed-timing interfaces are added to create a mixed-timing network which provides communication between synchronous and asynchronous domains.

Two issues top the agenda of CPU design in the emerging many-core era: programmers' productivity and power consumption. Through its reliance on the richest available theory of parallel algorithms, the eXplicit Multi-Threading (XMT) parallel architecture addresses programmers' productivity. The motivation for this work is to provide an effective interconnection network for the XMT architecture in terms of both performance and power consumption. Performance of the XMT processor with the mixed-timing network is measured for several applications.

Notes

Rights