MIX-ACIM: A 28-nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication
A mixed-precision analog compute-in-memory (Mix-ACIM) is presented for mixed-precision vector-matrix multiplication (VMM). The design features an all-analog current-domain fixed-point VMM with floating-point conversion and feature restoration. A 28nm CMOS test chip shows 41 TOPS/W and 24 TOPS/mm for fixed-point (8-bit input/weight and 12-bit output) and 24.18 TFLOPS/W and 3.3 TFLOPS/mm for 16-bit floating-point equivalent operation.
Authors
- Saibal Mukhopadhyay (ORCID: https://orcid.org/0000-0002-8894-3390)
- Narasimha Vasishta Kidambi
- Shida Zhang (ORCID: https://orcid.org/0000-0003-4187-4428)
- Laith A. Shamieh
- Wei-Chun Wang
- Isha Chakraborty
Institutions
- Georgia Institute of Technology (US)
Publication Details
- Journal
- IEEE Solid-State Circuits Letters
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1109/lssc.2025.3590757
- Citations
- 1
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Semiconductor Research Corporation
- Defense Advanced Research Projects Agency