Abstract | ||
---|---|---|
Stochastic computing (SC) is an approximate computing technique that processes data in the form of long pseudo-random bit-streams which can be interpreted as probabilities. Its key advantages are low-complexity hardware and high error tolerance. SC has recently been finding application in several important areas, including image processing, artificial neural networks, and LDPC decoding. Despite a long history, SC still lacks a comprehensive design methodology, so existing designs tend to be either ad hoc or based on specialized design methods. In this work, we demonstrate a fundamental relation between stochastic circuits and spectral transforms. Based on this, we propose a general, transform-based approach to the analysis and synthesis of SC circuits. We implemented this approach in a program STRAUSS (Spectral transform use in stochastic circuit synthesis), which also includes a method of optimizing stochastic numbergeneration circuitry. Finally, we show that the area cost of the circuits generated by STRAUSS is significantly smaller than that of previous work. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/TCAD.2015.2432138 | IEEE Trans. on CAD of Integrated Circuits and Systems |
Keywords | Field | DocType |
logic synthesis,design methodology,probabilistic methods,stochastic circuit optimization,stochastic computing | Logic synthesis,Parity bit,Stochastic optimization,Computer science,Algorithm,Electronic engineering,Fourier transform,Decoding methods,Artificial neural network,Stochastic computing,Pseudorandom number generator | Journal |
Volume | Issue | ISSN |
PP | 99 | 0278-0070 |
Citations | PageRank | References |
9 | 0.53 | 12 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Armin Alaghi | 1 | 381 | 29.52 |
J. P. Hayes | 2 | 3592 | 501.80 |