Deep In-Memory Architectures in SRAM: An Analog Approach to Approximate Computing
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
This article provides an overview of recently proposed deep in-memory architectures (DIMAs) in SRAM for energyand latency-efficient hardware realization of machine learning (ML) algorithms. DIMA tackles the data movement problem in von Neumann architectures head-on by deeply embedding mixed-signal computations into a conventional memory array. In doing so, it trades off its computational signal-to-noise ratio (compute SNR) with energy and latency, and therefore, it represents an analog form of approximate computing. DIMA exploits the inherent error immunity of ML algorithms and SNR budgeting methods to operate its analog circuitry in a low-swing/low-compute SNR regime, thereby achieving >100× reduction in the energy-delay product (EDP) over an equivalent von Neumann architecture with no loss in inference accuracy. This article describes DIMA's computational pipeline and provides a Shannon-inspired rationale for its robustness to process, temperature, and voltage variations and design guidelines to manage its analog nonidealities. DIMA's versatility, effectiveness, and practicality demonstrated via multiple silicon IC prototypes in a 65-nm CMOS process are described. A DIMA-based instruction set architecture (ISA) to realize an end-to-end application-toarchitecture mapping for the accelerating diverse ML algorithms is also presented. Finally, DIMA's fundamental tradeoff between energy and accuracy in the low-compute SNR regime is analyzed to determine energy-optimum design parameters.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2616357 · Cited by 3,247
Hubara, I., Soudry, D., & Yaniv, R. E. (2016) · arXiv · doi:10.48550/arxiv.1602.02505 · Cited by 1,667
Deep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · arXiv · doi:10.48550/arxiv.1502.02551 · Cited by 1,364 · cited 1×
“The 8-bit precision is employed for PROMISE to maintain the accuracy close to floating-point implementations [1], [57], [73], [74].”
MethodAnalog Versus Digital: Extrapolating from Electronics to Neurobiology
Sarpeshkar, R. (1998) · Neural Computation · doi:10.1162/089976698300017052 · Cited by 496 · cited 1×
“These trends provide another justification for the use of DIMA to realize DNNs since it has been shown that the analog computations are more energy-efficient than the digital at lower SNRs (SNR < 60 dB) [86] and because the deeper layers tend to be memory bound as the opportunities for weight reuse decrease.”
MethodIn-Memory Computing: Advances and Prospects
Verma, N., Jia, H., Valavi, H., Tang, Y., Ozatay, M., Chen, L.-Y., Zhang, B., & Deaville, P. (2019) · IEEE Solid-State Circuits Magazine · doi:10.1109/mssc.2019.2922889 · Cited by 473
Dong, Q., Sinangil, M. E., Erbagci, B., Sun, D., Khwa, W.-S., Liao, H.-J., Wang, Y., & Chang, J. (2020) · 2020 IEEE International Solid- State Circuits Conference - (ISSCC) · doi:10.1109/isscc19947.2020.9062985 · Cited by 346
Cited by
Khaddam-Aljameh, R., Stanisavljevic, M., Fornt Mas, J., Karunaratne, G., Brändli, M., Liu, F., Singh, A., Müller, S. M., Egger, U., Petropoulos, A., et al. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3140414 · Cited by 144
Jain, S., Tsai, H., Chen, C.-T., Muralidhar, R., Boybat, I., Frank, M. M., Woźniak, S., Stanisavljevic, M., Adusumilli, P., Narayanan, P., et al. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2022.3221390 · Cited by 76
“By exploiting such weight stationarity over a short timespan with volatile memories such as SRAM or DRAM [21], [22], [23], [24], or over longer timespans with slower and finite-endurance nonvolatile memories (NVMs) such as flash [25], [26], [27], resistive RAM (RRAM) [28], [29], [30], magnetic random…”
BackgroundBrain-inspired computing systems: a systematic literature review
Zolfagharinejad, M., Alegre-Ibarra, U., Chen, T., Kinge, S., & van der Wiel, W. G. (2024) · The European Physical Journal B · doi:10.1140/epjb/s10051-024-00703-6 · Cited by 39
Metadata
- Authors
- Kang, M., Gonugondla, S. K., & Shanbhag, N. R.
- Venue
- Proceedings of the IEEE
- Published
- 2020-12
- Volume
- 108
- Issue
- 12
- Pages
- 2251-2275
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W3106780185
- Cited by
- 41
- References
- 14
- FWCI
- 2.11
- Type
- journal article
- Language
- en
- Open access
- closed
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep In-Memory Architectures in SRAM: An Analog Approach to Approximate Computing. https://app.cochat.ai/papers/10.1109/jproc.2020.3034117
- The paper
- Kang, M., Gonugondla, S. K., & Shanbhag, N. R. (2020). Deep In-Memory Architectures in SRAM: An Analog Approach to Approximate Computing. Proceedings of the IEEE. https://doi.org/10.1109/jproc.2020.3034117
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.