Abstract
Self-timed circuits present an attractive solution to the problem of process varia tion. However, implementing self- timed combinational logic can be complex and expensive. This paper presents a complete synthesis flow that generates self-timed combinational networks from conventional Boolean networks. The Boolean network is partitioned into small function blocks which are then synthesised using self-timed techniques. The procedure employs relaxation optimisations to distribute the overheads associated with self-timed networks between function-blocks. Relaxation is incorporated into the function block synthesis procedures, meaning the optimisations can be applied at a much finer granularity than previously possible. The new techniques are demonstrated on a range of benchmarks showing average reduction of 5% in area, 26% in latency and 48% in energy over gate-level relaxation techniques and 17% in area, 8% in latency and 20% in energy consumption over other block-level relaxation techniques. © 2010 IEEE.
Original language | English |
---|---|
Title of host publication | Proceedings - International Conference on Application of Concurrency to System Design, ACSD|Proc. Int. Conf. Appl. Concurrency Syst. Des. ACSD |
Place of Publication | USA |
Publisher | IEEE Computer Society |
Pages | 24-34 |
Number of pages | 10 |
ISBN (Print) | 9780769540665 |
DOIs | |
Publication status | Published - 2010 |
Event | 10th International Conference on Application of Concurrency to System Design, ACSD 2010 - Braga Duration: 1 Jul 2010 → … |
Conference
Conference | 10th International Conference on Application of Concurrency to System Design, ACSD 2010 |
---|---|
City | Braga |
Period | 1/07/10 → … |
Keywords
- combinational circuits , multivalued logic circuits , relaxation , synchronisation