Modelling of vertical and ferroelectric junctionless technology for efficient 3D neural network compute cube dedicated to embedded artificial intelligence
Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/Gutachten › Beitrag in Konferenzband › Beigetragen › Begutachtung
Beitragende
Abstract
This paper presents the set of simulation means used to develop the concept of N2C2 (neural network compute cube) based on a vertical transistor technology platform. On the basis of state-of-the-art junctionless nanowire transistors (JLNT), TCAD simulation, compact modeling and EM simulation are leveraged through a Design-Technology Co-Optimization (DTCO) to achieve innovative 3D circuit architectures. Further, System-Technology Co-Optimization (STCO) implications on 3D NN system architecture are explored.
Details
Originalsprache | Englisch |
---|---|
Titel | 2021 IEEE International Electron Devices Meeting, IEDM 2021 |
Herausgeber (Verlag) | IEEE, New York [u. a.] |
Kapitel | 15.6.1-15.6.4 |
ISBN (elektronisch) | 9781665425728 |
Publikationsstatus | Veröffentlicht - 2021 |
Peer-Review-Status | Ja |
Publikationsreihe
Reihe | Technical Digest / International Electron Devices Meeting (IEDM) |
---|---|
Band | 2021-December |
ISSN | 0163-1918 |
Konferenz
Titel | 2021 IEEE International Electron Devices Meeting |
---|---|
Untertitel | Devices for a New Era of Electronics: From 2D Materials to 3D Architectures |
Kurztitel | IEDM 2021 |
Veranstaltungsnummer | 67 |
Dauer | 11 - 16 Dezember 2021 |
Ort | Hilton San Francisco Union Square Hotel & online |
Stadt | San Francisco |
Land | USA/Vereinigte Staaten |
Externe IDs
ORCID | /0000-0003-3814-0378/work/142256165 |
---|