journal article·2024

Low-Cost and Highly-Efficient Bit-Stream Generator for Stochastic Computing Division

Mehran Shoushtari Moghadam, Sercan Aygun, Sina Asadi, M. Hassan Najafi

Publisher page

Abstract

Stochastic computing (SC) division circuits have gained importance in recent years compared to other arithmetic circuits due to their low complexity as a result of an accuracy tradeoff. Designing a division circuit is already complex in conventional binary-based hardware systems. Developing an accurate and efficient SC division circuit is an open research problem. Prior work proposed different SC division circuits by using multiplexers and JK-flip-flop units, which may require correlated or uncorrelated input bit-streams. This study is primarily centered on exploring a cost-effective and highly efficient bit-stream generator specifically designed for SC division circuits. In conjunction with this objective, we assess the performance of multiple bit-stream generators and analyze the impact of correlation on SC division. We compare different designs in terms of accuracy and hardware cost. Moreover, we discuss a low-cost and energy-efficient bit-stream generator via powers-of-2 Van der Corput (VDC) sequences. Among the tested sequence generators, our best results were achieved with VDC sequences. Our evaluation results demonstrate that the novel VDC-based design yields promising outputs, resulting in a 15.5% reduction in the area-delay product and an 18.05% saving in energy consumption for the same accuracy level compared to conventional bit-stream generators. Significantly, our investigation reveals that employing the proposed generator improves the precision compared to the state-of-the-art. We validate the proposed architecture with an image processing case study, achieving high PSNR and structural similarity values.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Error Correcting Code Techniques · Quantum Computing Algorithms and Architecture · Low-power high-performance VLSI design

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA

Funding

National Science Foundation · Louisiana Board of Regents Support Fund · Generous Gifts from Cisco, Xilinx, and Nvidia

References (44)

Show source-provided references
1. 10.1007/978-1-4899-5841-9_210.1007/978-1-4899-5841-9_2 ↗
2. 10.1109/TCAD.2017.277810710.1109/TCAD.2017.2778107 ↗
3. 10.23919/DATE.2018.834223410.23919/DATE.2018.8342234 ↗
4. 10.1109/TVLSI.2018.282230010.1109/TVLSI.2018.2822300 ↗
5. 10.1007/978-3-642-31869-6_2510.1007/978-3-642-31869-6_25 ↗
6. 10.1109/ISMVL.2007.5310.1109/ISMVL.2007.53 ↗
7. 10.1109/ISVLSI.2016.4810.1109/ISVLSI.2016.48 ↗
8. 10.1109/TCSII.2019.290638510.1109/TCSII.2019.2906385 ↗
9. 10.1002/cta.321910.1002/cta.3219 ↗
10. 10.1561/060000001910.1561/0600000019 ↗
11. 10.1109/NANOARCH53687.2021.964225110.1109/NANOARCH53687.2021.9642251 ↗
12. Effect of LFSR seeding, scrambling and feedback polynomial on stochastic computing accuracy
13. 10.23919/DATE51398.2021.947414310.23919/DATE51398.2021.9474143 ↗
14. 10.1016/0041-5553(67)90144-910.1016/0041-5553(67)90144-9 ↗
15. Verteilungsfunktionen I
16. 10.1145/3240765.324079710.1145/3240765.3240797 ↗
17. 10.23919/DATE.2017.792706910.23919/DATE.2017.7927069 ↗
18. 10.1109/TVLSI.2018.281221410.1109/TVLSI.2018.2812214 ↗
19. 10.1109/TVLSI.2019.292935410.1109/TVLSI.2019.2929354 ↗
20. P2LSG: Powers-of-2 low-discrepancy sequence generator for stochastic computing
21. 10.1109/ICCAD51958.2021.964345010.1109/ICCAD51958.2021.9643450 ↗
22. 10.1109/TVLSI.2013.224742910.1109/TVLSI.2013.2247429 ↗
23. 10.1109/TCAD.2018.285275210.1109/TCAD.2018.2852752 ↗
24. 10.1109/ICCD.2013.665702310.1109/ICCD.2013.6657023 ↗
25. 10.1145/349121310.1145/3491213 ↗
26. Programmable supervisory circuit and applications thereof
27. 10.4018/IJSSCI.201707010310.4018/IJSSCI.2017070103 ↗
28. 10.1145/3611315.363326510.1145/3611315.3633265 ↗
29. 10.1109/TC.2010.20210.1109/TC.2010.202 ↗
30. Szeliski · 201110.1007/978-1-84882-935-0 ↗
31. 10.1109/TPAMI.2007.117710.1109/TPAMI.2007.1177 ↗
32. 10.1109/TCAD.2023.324313610.1109/TCAD.2023.3243136 ↗
33. 10.1109/ASPDAC.2017.785836910.1109/ASPDAC.2017.7858369 ↗
34. 10.1109/IranianCEE.2015.714630810.1109/IranianCEE.2015.7146308 ↗
35. 10.1109/TVLSI.2016.253531310.1109/TVLSI.2016.2535313 ↗
36. 10.1109/SIU.2017.796047910.1109/SIU.2017.7960479 ↗
37. 10.1109/LSP.2015.239212310.1109/LSP.2015.2392123 ↗
38. 10.1109/JETCAS.2018.284432910.1109/JETCAS.2018.2844329 ↗
39. 10.1109/SiPS.2015.734498210.1109/SiPS.2015.7344982 ↗
40. 10.3906/elk-1805-19510.3906/elk-1805-195 ↗
41. 10.1109/CVPR.2007.38302810.1109/CVPR.2007.383028 ↗
42. 10.1109/CVPR.2007.38300610.1109/CVPR.2007.383006 ↗
43. 10.1109/CVPR.2011.599549510.1109/CVPR.2011.5995495 ↗
44. 10.1109/TPAMI.2016.260639710.1109/TPAMI.2016.2606397 ↗