Live Demonstration: A Scalable CNN Accelerator SoC With a Cost-Effective Chip-to-Chip Adapter
In this demonstration, we present a system-on-chip (SoC) designed to support scalable CNN acceleration at a low cost. The SoC features a cost-effective chip-to-chip adapter that enables scalable performance improvements with minimal design costs. This adapter manages chip-to-chip synchronization and data scheduling, effectively reducing chip-to-chip latency overhead. The SoC is implemented using the Silterra 130-nm CMOS technology with a chip size of 6.3×6.3 mm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>.
Authors
- Xuan Truong Nguyen (ORCID: https://orcid.org/0000-0002-7527-6971)
- Hyuk‐Jae Lee (ORCID: https://orcid.org/0000-0001-6811-9647)
- Chunmyung Park (ORCID: https://orcid.org/0009-0005-0033-7302)
- Jicheon Kim (ORCID: https://orcid.org/0009-0007-3010-7668)
- Eunjae Hyun (ORCID: https://orcid.org/0009-0003-6928-4320)
Institutions
- Seoul National University (KR)
Publication Details
- Published
- 2025-05-25
- DOI
- https://doi.org/10.1109/iscas56072.2025.11043327
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00