Abstract

AbstractWith Moore’s law supplying billions of transistors, and uniprocessor architectures delivering diminishing performance, multicore chips are emerging as the prevailing architecture in both general-purpose and application-specific markets. As the core count increases, the need for a scalable on-chip communication fabric that can deliver high bandwidth is gaining in importance, leading to recent multicore chips interconnected with sophisticated on-chip networks. In this chapter, we first present a tutorial on on-chip network architecture fundamentals including on-chip network interfaces, topologies, routing, flow control, and router microarchitectures. Next, we detail case studies on two recent prototypes of on-chip networks: the UT-Austin TRIPS operand network and the Intel TeraFLOPS on-chip network. This chapter organization seeks to provide the foundations of on-chip networks so that readers can appreciate the different design choices faced in the two case studies. Finally, this chapter concludes with an outline of the challenges facing research into on-chip network architectures.KeywordsOutput PortVirtual ChannelMulticore SystemVery Long Instruction WordSleep TransistorThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.