Managing contamination delay to improve Timing Speculation architectures
- Published
- Accepted
- Subject Areas
- Algorithms and Analysis of Algorithms, Computer Architecture, Embedded Computing, Emerging Technologies
- Keywords
- timing speculation, timing errors, PVT variation, overclocking, delay insertion, timing constraints, reliable and aggressive systems, contamination delay
- Copyright
- © 2016 Avirneni et al.
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2016. Managing contamination delay to improve Timing Speculation architectures. PeerJ Preprints 4:e1412v2 https://doi.org/10.7287/peerj.preprints.1412v2
Abstract
Timing Speculation (TS) is a widely known method for realizing better-than-worst-case systems. Aggressive clocking, realizable by TS, enable systems to operate beyond specified safe frequency limits to effectively exploit the data dependent circuit delay. However, the range of aggressive clocking for performance enhancement under TS is restricted by short paths. In this paper, we show that increasing the lengths of short paths of the circuit increases the effectiveness of TS, leading to performance improvement. Also, we propose an algorithm to efficiently add delay buffers to selected short paths while keeping down the area penalty. We present our algorithm results for ISCAS-85 suite and show that it is possible to increase the circuit contamination delay by up to 30% without affecting the propagation delay. We also explore the possibility of increasing short path delays further by relaxing the constraint on propagation delay and analyze the performance impact.
Author Comment
In this version, we added more clarification to the experiment results presented in Section 5. More analysis of the results is also presented in Section 5 (highlighted in the attached manuscript).