ACM Home Page
Please provide us with feedback. Feedback
Energy-efficient FPGA interconnect architecture design (abstract only)
Source International Symposium on Field Programmable Gate Arrays archive
Proceedings of the 2005 ACM/SIGDA 13th international symposium on Field-programmable gate arrays table of contents
Monterey, California, USA
POSTER SESSION: FPGA architectures and circuits table of contents
Pages: 268 - 268  
Year of Publication: 2005
ISBN:1-59593-029-9
Authors
Rohini Krishnan  Philips Research Laboratories, Eindhoven, The Netherlands
R. I.M.P. Meijer  Philips Research Laboratories, Eindhoven, The Netherlands
Durand Guillaume  Philips Research Laboratories, Eindhoven, The Netherlands
Sponsors
ACM: Association for Computing Machinery
SIGDA: ACM Special Interest Group on Design Automation
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): n/a,   Downloads (12 Months): n/a,   Citation Count: 0
Additional Information:

abstract   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1046192.1046240
What is a DOI?

ABSTRACT

In this work, the design of an energy-efficient FPGA interconnect architecture has been investigated. It concerns a dual-supply solution, where the logic blocks are powered by a nominal voltage supply and the interconnect part is powered by a reduced voltage supply. The behaviour of a fully-buffered, a fully pass-transistor based and a hybrid buffer and pass-transistor architecture has been investigated over a range of power supply voltages. It is found that there exists an optimal ratio between the number of pass-transistor and tri-state buffer switches depending on the load and power supply involved. By reducing the signal voltage swing on the interconnect, the need for a fully tri-state buffer-based interconnect is eliminated, thus saving valuable area and power.Through benchmark studies, it is confirmed that using an optimal composite of pass-transistor and tri-state buffer switches operating at a reduced power supply can meet the same speed as compared to the full-swing scenario at a much lower power consumption. An average reduction in power-delay of 4.4x for low-load critical paths and 2.7x for high-load critical paths is achieved using buffer receivers. Using levelshifter receivers, an average reduction in power-delay of 4.7x for low-load critical paths and 2.8x for high-load critical paths is obtained. It is also found that due to partially replacing tri-state buffers by pass-transistor switches and inspite of using levelshifters, we can save up to a factor of 4x in interconnect area as compared to fully-buffered architectures. The results have been validated over various benchmarks in a 0.13 m CMOS technology.

Collaborative Colleagues:
Rohini Krishnan: colleagues
R. I.M.P. Meijer: colleagues
Durand Guillaume: colleagues