A Charge Domain P-8T SRAM Compute-In-Memory with Low-Cost DAC/ADC Operation for 4-bit Input Processing
The work
| Authors | Joonhyung Kim; Kyeongho Lee; Jongsun Park |
|---|---|
| Editors | |
| Type | inproceedings |
| Year | 2022 |
| Citekey | kim2022charge |
Where it appeared
| Published in | Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design |
|---|---|
| Publisher | Association for Computing Machinery |
| Volume | 55 |
| Pages | 1--6 |
Identifiers
| arXiv | 2211.16008 from its oa_pdf_url |
|---|---|
| DOI | 10.1145/3531437.3539718 |
| OpenAlex | W4285676410 |
Access
| Landing page | https://doi.org/10.1145/3531437.3539718 |
|---|---|
| Free full text | https://arxiv.org/pdf/2211.16008 |
Related
| Distinct from | dai2024verifying |
|---|---|
| Distinct from | jouppi2017indatacenter |
| Distinct from | masakowski2023mitigating |
| Distinct from | shalf2019interconnects |
Abstract
This paper presents a low cost PMOS-based 8T (P-8T) SRAM Compute-In-Memory (CIM) architecture that efficiently per-forms the multiply-accumulate (MAC) operations between 4-bit input activations and 8-bit weights. First, bit-line (BL) charge-sharing technique is employed to design the low-cost and reliable digital-to-analog conversion of 4-bit input activations in the pro-posed SRAM CIM, where the charge domain analog computing provides variation tolerant and linear MAC outputs. The 16 local arrays are also effectively exploited to implement the analog mul-tiplication unit (AMU) that simultaneously produces 16 multipli-cation results between 4-bit input activations and 1-bit weights. For the hardware cost reduction of analog-to-digital converter (ADC) without sacrificing DNN accuracy, hardware aware system simulations are performed to decide the ADC bit-resolutions and the number of activated rows in the proposed CIM macro. In addition, for the ADC operation, the AMU-based reference col-umns are utilized for generating ADC reference voltages, with which low-cost 4-bit coarse-fine flash ADC has been designed. The 256×80 P-8T SRAM CIM macro implementation using 28nm CMOS process shows that the proposed CIM shows the accuracies of 91.46% and 66.67% with CIFAR-10 and CIFAR-100 dataset, respectively, with the energy efficiency of 50.07-TOPS/W.
A copy is held
pdf, 926.3 kB. Not published — it may be under copyright. The facts and links here are.
How it got here
| How it got here | agent via openalex |
|---|---|
| Added | 2026-08-04 00:00 UTC |
| Approved by | a person 2026-08-08 15:00 UTC |
Filed under
Cite it as
@inproceedings{kim2022charge,
title = {A Charge Domain P-8T SRAM Compute-In-Memory with Low-Cost DAC/ADC Operation for 4-bit Input Processing},
author = {Joonhyung Kim and Kyeongho Lee and Jongsun Park},
year = {2022},
booktitle = {Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design},
publisher = {Association for Computing Machinery},
volume = {55},
pages = {1--6},
doi = {10.1145/3531437.3539718},
}
This record lives at https://refs.drheap.org/kim2022charge/ and will keep doing so.