Graber, Markus ; Hofmann, Klaus (2022)
A Versatile & Adjustable 400 Node CMOS Oscillator Based Ising Machine to Investigate and Optimize the Internal Computing Principle.
35th International System-on-Chip Conference. Belfast, United Kingdom (05.09.2022-08.09.2022)
doi: 10.1109/SOCC56010.2022.9908118
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Oscillator-based Ising machines (OIMs) recently grow in interest. These OIMs can solve combinatorial optimization problems formulated as an Ising model. The computation principle is based on the interaction of configurable coupled oscillators, which represent discrete states of the optimization variables by their phase. In contrast to competing implementations like quantum computers or coherent Ising machines, OIMs are based on mature, well-established and therefore highly optimized silicon technologies. This silicon based approach allows close interaction with established electronics, avoiding sophisticated measurement electronics and delicate physical structures. Obtaining a good solution, especially for large problems, is one of the major challenges for the current integrated OIMs. The here proposed system serves as a versatile experimental platform to evaluate how the OIM computation is influenced and how it can be improved. Furthermore, the platform offers new OIM capabilities with up to 6-bit weighted optimization problems, 2 to 4 discrete states partially enabling the Potts model and fast phase readout.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Graber, Markus ; Hofmann, Klaus |
| Art des Eintrags: | Bibliographie |
| Titel: | A Versatile & Adjustable 400 Node CMOS Oscillator Based Ising Machine to Investigate and Optimize the Internal Computing Principle |
| Sprache: | Englisch |
| Publikationsjahr: | 10 Oktober 2022 |
| Verlag: | IEEE |
| Buchtitel: | Proceedings: 2022 IEEE 35th International System-on-Chip Conference (SOCC) |
| Veranstaltungstitel: | 35th International System-on-Chip Conference |
| Veranstaltungsort: | Belfast, United Kingdom |
| Veranstaltungsdatum: | 05.09.2022-08.09.2022 |
| DOI: | 10.1109/SOCC56010.2022.9908118 |
| Kurzbeschreibung (Abstract): | Oscillator-based Ising machines (OIMs) recently grow in interest. These OIMs can solve combinatorial optimization problems formulated as an Ising model. The computation principle is based on the interaction of configurable coupled oscillators, which represent discrete states of the optimization variables by their phase. In contrast to competing implementations like quantum computers or coherent Ising machines, OIMs are based on mature, well-established and therefore highly optimized silicon technologies. This silicon based approach allows close interaction with established electronics, avoiding sophisticated measurement electronics and delicate physical structures. Obtaining a good solution, especially for large problems, is one of the major challenges for the current integrated OIMs. The here proposed system serves as a versatile experimental platform to evaluate how the OIM computation is influenced and how it can be improved. Furthermore, the platform offers new OIM capabilities with up to 6-bit weighted optimization problems, 2 to 4 discrete states partially enabling the Potts model and fast phase readout. |
| Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik > Integrierte Elektronische Systeme (IES) |
| Hinterlegungsdatum: | 10 Mai 2023 13:36 |
| Letzte Änderung: | 15 Aug 2024 09:38 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum