Interfacing Hardware Accelerators to a Time-Division Multiplexing Network-on-Chip

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

1 Downloads (Pure)

Abstract

This paper addresses the integration of stateless hardware accelerators into time-predictable multi-core platforms based on time-division multiplexing networks-on-chip. Stateless hardware accelerators, like floating-point units, are typically attached as co-processors to individual processors in the platform. Our design takes a different approach and connects the hardware accelerators to the network-on-chip in the same way as processor cores. Each processor that uses a hardware accelerator is assigned a virtual channel for sending instructions to the hardware accelerator and a virtual channel for receiving results. This allows a stateless and possibly pipelined hardware accelerator to be shared in an interleaved fashion without any form of reservation, and this opens for interesting area-performance trade-offs. The design is developed with a focus on time-predictability, areaefficiency, and FPGA implementation. The design evaluation is carried out using the open source T-CREST multi-core platform implemented on an Altera Cyclone IV FPGA. The size of the proposed design, including a floating-point accelerator, is about two-thirds of a processor.
Original languageEnglish
Title of host publicationProceedings of the 1st Nordic Circuits and Systems Conference (NORCAS 2015)
Number of pages4
PublisherIEEE
Publication date2015
DOIs
Publication statusPublished - 2015
Event2015 IEEE Nordic Circuits and Systems Conference - Oslo, Norway
Duration: 26 Oct 201528 Oct 2015
Conference number: 1
https://ieeexplore.ieee.org/xpl/conhome/7360269/proceeding

Conference

Conference2015 IEEE Nordic Circuits and Systems Conference
Number1
Country/TerritoryNorway
CityOslo
Period26/10/201528/10/2015
OtherA merge of NORCHIP and the International Symposium on System-on-Chip (SoC)
Internet address

Fingerprint

Dive into the research topics of 'Interfacing Hardware Accelerators to a Time-Division Multiplexing Network-on-Chip'. Together they form a unique fingerprint.

Cite this