3D IGZO Charge-Coupled Memory DTCO & STCO Analysis for Compute-near-Memory Applications
The demand for high-capacity and energy-efficient memory solutions has surged in the era of data-centric computing, particularly for Artificial Intelligence (AI) and Machine Learning (ML) workloads. This paper introduces a novel memory architecture leveraging Charge-Coupled Device (CCD) technology, engineered in a sequential-access block memory configuration, to enhance Compute-near-Memory (CnM) systems. We propose an optimized 3D IGZO CCD block memory as an on-chip weight buffer for high-capacity CnM systems. Our approach achieves 2.95−131.26× improvement in area efficiency and 1.32−4.33× improvement in energy efficiency compared to SRAM solutions.
Authors
- Subhali Subhechha (ORCID: https://orcid.org/0000-0002-1960-5136)
- Jaydeep P. Kulkarni (ORCID: https://orcid.org/0000-0002-0258-6776)
- Sahan Gamage
- Marian Verhelst (ORCID: https://orcid.org/0000-0003-3495-9263)
- R. Kishore (ORCID: https://orcid.org/0000-0003-3312-2381)
- M. Rosmeulen (ORCID: https://orcid.org/0000-0002-3663-7439)
- Swaraj Bandhu Mahato (ORCID: https://orcid.org/0000-0002-1677-6474)
- Dwaipayan Biswas (ORCID: https://orcid.org/0000-0001-7912-3692)
- Fernando Garćıa-Redondo (ORCID: https://orcid.org/0000-0001-7090-8821)
- Khakim Akhunov (ORCID: https://orcid.org/0000-0001-9585-6722)
- M. Garcia Bardon (ORCID: https://orcid.org/0000-0001-5772-5406)
- Wim Dehaene (ORCID: https://orcid.org/0000-0002-6792-7965)
- Jiacong Sun (ORCID: https://orcid.org/0000-0003-0418-2713)
- Yukai Chen (ORCID: https://orcid.org/0000-0003-3378-887X)
- Arvind Sharma (ORCID: https://orcid.org/0000-0002-9250-9642)
- Bowen Wang (ORCID: https://orcid.org/0000-0003-4946-8432)
- Julien Ryckaert (ORCID: https://orcid.org/0009-0001-0140-3042)
- Hyungrock Oh
Institutions
- IMEC (BE)
- KU Leuven (BE)
Publication Details
- Published
- 2025-05-25
- DOI
- https://doi.org/10.1109/iscas56072.2025.11043541
- Primary Topic
- Advanced Memory and Neural Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00