An All-digital Compute-in-memory FPGA Architecture for Deep Learning Acceleration
The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Field Programmable Gate Array (FPGA) is a versatile and programmable hardware platform, which makes it a promising candidate for accelerating Deep Neural Networks (DNNs). However, FPGA’s computing energy efficiency is low due to the domination of energy consumption by interconnect data movement. In this article, we propose an all-digital Compute-in-memory FPGA architecture for deep learning acceleration. Furthermore, we present a bit-serial computing circuit of the Digital CIM core for accelerating vector-matrix multiplication (VMM) operations. A Network-CIM-deployer ( NCIMD ) is also developed to support automatic deployment and mapping of DNN networks. NCIMD provides a user-friendly API of DNN models in Caffe format. Meanwhile, we introduce a Weight-stationary dataflow and describe the method of mapping a single layer of the network to the CIM array in the architecture. We conduct experimental tests on the proposed FPGA architecture in the field of Deep Learning (DL), as well as in non-DL fields, using different architectural layouts and mapping strategies. We also compare the results with the conventional FPGA architecture. The experimental results show that compared to the conventional FPGA architecture, the energy efficiency can achieve a maximum speedup of 16.1×, while the latency can decrease up to 40% in our proposed CIM FPGA architecture.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 1×
“Several FPGA-based CNN accelerators proposed in References [ 5 , 21 , 22 , 44 ] do not utilize CIM technologies, which suffer a lot from frequent data-transfer.”
MethodISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001139 · Cited by 1,536
Owens, J. D., Houston, M., Luebke, D., Green, S., Stone, J. E., & Phillips, J. C. (2008) · Proceedings of the IEEE · doi:10.1109/jproc.2008.917757 · Cited by 1,495
Chi, P., Li, S., Xu, C., Zhang, T., Zhao, J., Liu, Y., Wang, Y., & Xie, Y. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001140 · Cited by 1,231
PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning
Song, L., Qian, X., Li, H., & Chen, Y. (2017) · 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2017.55 · Cited by 833
In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM Array
Zhang, J., Wang, Z., & Verma, N. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2642198 · Cited by 532
XNOR-SRAM: In-Memory Computing SRAM Macro for Binary/Ternary Deep Neural Networks
Yin, S., Jiang, Z., Seo, J.-S., & Seok, M. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2019.2963616 · Cited by 429
Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks
Eckert, C., Wang, X., Wang, J., Subramaniyan, A., Iyer, R., Sylvester, D., Blaaauw, D., & Das, R. (2018) · 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2018.00040 · Cited by 369
Research works printed but not linked: 3
- Sungmin Cho, Satrajit Chatterjee, Alan Mishchenko, and Robert Brayton. 2007. Efficient FPGA mapping using priority cuts. Proc. FPGA 7 (2007).
- J. Kin M. Gupta and W. H. Mangione Smith. 1997. Application specific integrated circuits. https://ieeexplore.ieee.org/iel5/12/17823/x0263691.pdf
- Jaydeep Kulkarni, Muhammad Khellah, Jim Tschanz, Bibiche Geuskens, Rinkle Jain, Stephen Kim, and Vivek De. 2013. Dual-V CC 8T-bitcell SRAM array in 22nm tri-gate CMOS for energy-efficient operation across wide dynamic voltage range. In Proceedings of the Symposium on VLSI Technology. IEEE, C126–C127.
Cited by
Research on the Security of SRAM-Based FPGAs in the Era of Artificial Intelligence
Zhou, J., Zhao, X., Zhang, S., et al. (2025) · Journal of Low Power Electronics and Applications · doi:10.3390/jlpea15040066 · Cited by 1
A FeFET-Based Compute-in-Memory Architecture on FPGA for Neural Network Inference
Jiang, M. Z., Li, Y., Xiao, R., Shen, H., & Huang, K. (2025) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm62733.2025.00015
“In contrast, the overhaul approach involves redesigning the FPGA architecture to fully optimize it for CIM, leading to higher performance and better utilization of CIM capabilities [23]–[26].”
Self-citationArchitectural Assessment of a CIM-OR hard-block for FPGAs
Choudhary, B., & Rajawat, A. (2026) · IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS) · doi:10.1109/sceecs68810.2026.11430053
“Recent studies have investigated the incorporation of more specialized primitives, such as tensor blocks for machine learning or soft-core processors [10], [11].”
CNM-MNPO: A Compute-Near-Memory FPGA architecture with a mesh NoC placement optimization
Li, Y., Kumar, A., Shen, H., et al. (2026) · Microelectronics Journal · doi:10.1016/j.mejo.2026.107222
Self-citationMachine Learning Systems for High Performance and Dependability: The FPGA Roleplay
Fard, E., Zhang, H., & Ko, S. (2026) · Springer eBooks · doi:10.1007/978-3-032-17948-7_13
Metadata
- Authors
- Li, Y., Li, X., Shen, H., Fan, J., Xu, Y., & Huang, K.
- Affiliations
- Zhejiang University (CN)
- China Electronics Technology Group Corporation (CN)
- Venue
- ACM Transactions on Reconfigurable Technology and Systems
- Published
- 2024-02-12
- Volume
- 17
- Issue
- 1
- Pages
- 1-27
- ISSN
- 1936-7406 (ISSN-L)
- 1936-7414
- OpenAlex
- W4390880248
- Cited by
- 5
- References
- 42
- Citations by year
- 2026: 3 · 2025: 2
- FWCI
- 1.54
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Reconfigurable Technology and Systems (publishedVersion)
- Funders
- National Natural Science Foundation of China (62274142)
- Sino-German Mobility Programme (M-0499)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- in-memory computing, FPGA architecture, deep neural network acceleration, matrix-vector multiplication, energy efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.