Fully CMOS‐Based p‐Bits with a Bistable Resistor for Probabilistic Computing
Source abstract
Abstract
Abstract Probabilistic computing can solve complex combinatorial optimization problems more efficiently than conventional deterministic computing. A probabilistic bit (p‐bit) with an n‐p‐n bistable resistor (biristor) is demonstrated for probabilistic computing. It is fabricated on an 8‐inch wafer with complementary metal–oxide–semiconductor (CMOS) compatible technologies. Its stochastic behavior of threshold switching, which is based on the phenomenon of a single transistor latch, provides output with a Boltzmann distribution. The p‐bit is composed of a biristor, a serial resistor, and a comparator. The output probability of the biristor‐based p‐bits shows a sigmoidal relationship with the input voltage, showing typical p‐bit characteristics. Invertible Boolean logic operations with p‐bits are demonstrated, and weighted maximum Boolean satisfiability problems are solved with high energy efficiency and accuracy. The biristor‐based p‐bits with perfect CMOS compatibility show sufficient device stability, demonstrating the possibility of large‐scale integration with a p‐bit array for complex optimization solvers.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Quantum Computing Algorithms and Architecture · Ferroelectric and Negative Capacitance Devices
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Materials Science and Engineering and Inter‐University Semiconductor Research Center Seoul National University Gwanak‐ro 1, Daehagdong, Gwanak‐gu Seoul 08826 Republic of Korea
School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) 291 Daehak‐ro, Yuseong‐gu Daejeon 34141 Republic of Korea
References (38)
Show source-provided references
1. Patterson D. · arXiv Prepr. arXiv2104.10350 · 2021
2. 10.1109/JXCDC.2023.325698110.1109/JXCDC.2023.3256981 ↗
3. Papadimitriou C. H. · 1998
4. 10.1002/net.1975.5.1.4510.1002/net.1975.5.1.45 ↗
5. Marques‐Silva J. · 2021 · 133
6. 10.1145/1217856.121785910.1145/1217856.1217859 ↗
7. 10.1016/0009-2614(94)00117-010.1016/0009-2614(94)00117-0 ↗
8. 10.1103/PhysRevE.58.535510.1103/PhysRevE.58.5355 ↗
9. Gibney E. · Nature · 2017 · 541 · 7638
10. 10.1038/s41586-019-1557-910.1038/s41586-019-1557-9 ↗
11. 10.1038/s41467-022-33455-x10.1038/s41467-022-33455-x ↗
12. 10.1038/s41578-019-0159-310.1038/s41578-019-0159-3 ↗
13. 10.1002/adma.20170472910.1002/adma.201704729 ↗
14. 10.1002/adma.20090037510.1002/adma.200900375 ↗
15. 10.1038/s41586-021-04182-y10.1038/s41586-021-04182-y ↗
16. 10.1038/s41586-021-04292-710.1038/s41586-021-04292-7 ↗
17. 10.1109/55.2042010.1109/55.20420 ↗
18. 10.1063/1.134219010.1063/1.1342190 ↗
19. 10.1063/1.35584910.1063/1.355849 ↗
20. Mitin V. · Noise and fluctuations in electronic · 2002 · 11
21. 10.1109/T-ED.1960.1458810.1109/T-ED.1960.14588 ↗
22. 10.1109/IEDM.2007.441887810.1109/IEDM.2007.4418878 ↗
23. 10.1109/55.98131410.1109/55.981314 ↗
24. 10.1080/00029890.1987.1200074210.1080/00029890.1987.12000742 ↗
25. J. J.Hopfield Scholarpedia2007 2 1977.10.4249/scholarpedia.1977 ↗
26. 10.1207/s15516709cog0901_710.1207/s15516709cog0901_7 ↗
27. 10.1002/advs.20210507610.1002/advs.202105076 ↗
28. 10.1109/LED.2010.205140510.1109/LED.2010.2051405 ↗
29. 10.1109/16.13732010.1109/16.137320 ↗
30. 2016
31. 10.1063/1.507991710.1063/1.5079917 ↗
32. Luo Q. · 2015 · 7409667
33. Moon D.‐I. · 2012 · 31
34. 10.1109/JEDS.2014.238451810.1109/JEDS.2014.2384518 ↗
35. 10.1109/TED.2013.228827210.1109/TED.2013.2288272 ↗
36. 10.1109/IEDM.1982.19039510.1109/IEDM.1982.190395 ↗
37. J.Berg M.Järvisalo in2013 IEEE 13th Int. Conf. Data Min. Workshops IEEE Dallas TX USA 2013 pp.750.10.1109/ICDMW.2013.99 ↗
38. Cussens J. · arXiv Prepr. arXiv1206.3244 · 2012