An Efficient Approximate Node Merging with an Error Rate Guarantee
- 18 January 2021
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM) in Proceedings of the 26th Asia and South Pacific Design Automation Conference
Abstract
Approximate computing is an emerging design paradigm for error-tolerant applications. e.g., signal processing and machine learning. In approximate computing, the area, delay, or power consumption of an approximate circuit can be improved by trading off its accuracy. In this paper, we propose an approximate logic synthesis approach based on a node-merging technique with an error rate guarantee. The ideas of our approach are to replace internal nodes by constant values and to merge two similar nodes in the circuit in terms of functionality. We conduct experiments on a set of IWLS 2005 and MCNC benchmarks. The experimental results show that our approach can reduce area by up to 80%, and 31% on average. As compared with the state-of-the-art method, our approach has a speedup of 51 under the same 5% error rate constraint.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (MOST 107-2221-E-155-046, MOST 108-2221-E-155-047, MOST 106-2221-E-007-111-MY3, MOST 108-2218-E-007-061, and MOST 109-2221-E-007-082-MY2)
This publication has 5 references indexed in Scilit:
- Towards Formal Evaluation and Verification of Probabilistic DesignInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018
- Substitute-and-Simplify: A Unified Design Paradigm for Approximate and Quality Configurable CircuitsPublished by EDAA ,2013
- IMPACT: IMPrecise adders for low-power approximate computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Fast detection of node mergers using logic implicationsPublished by Association for Computing Machinery (ACM) ,2009
- Recursive Learning: An attractive alternative to the decision tree for test generation in digital ciPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005