Compressed Sensing With Approximate Message Passing Using In-Memory Computing
Open accessAbstract
In-memory computing is a promising non-von Neumann approach where certain computational tasks are performed within resistive memory units by exploiting their physical attributes. In this paper, we propose a new method for fast and robust compressed sensing (CS) of sparse signals with approximate message passing recovery using in-memory computing. The measurement matrix for CS is encoded in the conductance states of resistive memory devices organized in a crossbar array. In this way, the matrix-vector multiplications associated with both the compression and recovery tasks can be performed by the same crossbar array without intermediate data movements at potential O(1) time complexity. For a signal of size N, the proposed method achieves a potential O(N)-fold recovery complexity reduction compared with a standard software approach. We show the array-level robustness of the scheme through large-scale experimental demonstrations using more than 256k phase-change memory devices.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
For all programmed levels, the standard deviation of conductance distributions is less than 1.2 μS, which is more than two times lower than that reported in previous works on nanoscale PCM arrays for a similar conductance range.
“For all levels, we achieve a standard deviation less than 1.2 μS, which is more than two times lower than that reported in previous works on nanoscale PCM arrays for a similar conductance range40,41.”
From Accurate deep neural network inference using computational phase-change memory (2020) · cites this paper as [40]
The Physical Implementation section describes PCM conductance distributions across a 0–50 μS range, and the Fig. 2 caption says it shows standard deviations for five programmed levels (page unavailable). Our copy does not give numerical standard deviations for those levels, so it cannot establish the claimed more-than-twofold comparison with 1.2 μS. (LLM, conf=0.78)
Experimental — accuracy not yet measuredTraining with 4-bit digital weights improves performance after transfer to PCM with respect to FP32, but accuracy decreases by more than 1% after transferring the 4-bit weights to PCM.
“Training with 4-bit digital weights (using the method described in the ref. 33), which is roughly the effective precision of our PCM devices40, improves the performance after transfer with respect to FP32, but nevertheless the accuracy decreases by more than 1% after transferring the 4-bit weights to PCM.”
From Accurate deep neural network inference using computational phase-change memory (2020) · cites this paper as [40]
For evaluation times long after NVM programming, conductance drift can be compensated in the digital domain without expensive re-programming.
“For evaluation times teval long after NVM programming, the conductance drift Eq. (8) can be compensated in the digital domain without any expensive re-programming36,73.”
From Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators (2023) · cites this paper as [73]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Single-pixel imaging via compressive sampling
Duarte, M. F., Davenport, M. A., Takhar, D., Laska, J. N., Sun, T., Kelly, K. F., & Baraniuk, R. G. (2008) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.914730 · Cited by 3,596 · see citing works
Message-passing algorithms for compressed sensing
Donoho, D. L., Maleki, A., & Andrea Montanari, A. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0909892106 · Cited by 2,524 · see citing works
The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
Bayati, M., & Andrea Montanari, A. (2011) · IEEE Transactions on Information Theory · doi:10.1109/tit.2010.2094817 · Cited by 779 · see citing works
Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product Engine
Hu, M., Graves, C. E., Li, C., Li, Y., Ge, N., Montgomery, E., Davila, N., Jiang, H., Williams, R. S., Yang, J. J., et al. (2018) · Advanced Materials · doi:10.1002/adma.201705914 · Cited by 751 · cited 2× · see citing works
“In a memristive crossbar, it has been argued that the matrix-vector multiplications can be performed with constant time complexity O(γ ), where γ is independent of the crossbar size [3].”
Background1From Denoising to Compressed SensingPreprint
Metzler, C. A., Maleki, A., & Baraniuk, R. G. (2016) · Cited by 661 · see citing works
Sparse coding with memristor networks
Sheridan, P. M., Cai, F., Du, C., Ma, W., Zhang, Z., & Lu, W. D. (2017) · Nature Nanotechnology · doi:10.1038/nnano.2017.83 · Cited by 619 · see citing works
Mixed-precision in-memory computing
Le Gallo, M., Sebastian, A., Mathis, R., Manica, M., Giefers, H., Tuma, T., Bekas, C., Curioni, A., & Eleftheriou, E. (2018) · Nature Electronics · doi:10.1038/s41928-018-0054-8 · Cited by 485 · see citing works
Self-citationBiswas, A., & Chandrakasan, A. P. (2018) · 2018 IEEE International Solid - State Circuits Conference - (ISSCC) · doi:10.1109/isscc.2018.8310397 · Cited by 337 · see citing works
CMOS Image Sensor With Per-Column ΣΔ ADC and Programmable Compressed Sensing
Oike, Y., & Gamal, A. E. (2012) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2012.2214851 · Cited by 214 · see citing works
Guo, X., Bayat, F. M., Bavandpour, M., Klachko, M., Mahmoodi, M. R., Prezioso, M., Likharev, K. K., & Strukov, D. B. (2017) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm.2017.8268341 · Cited by 196 · see citing works
Projected phase-change memory devices
Koelmans, W. W., Sebastian, A., Jonnalagadda, V. P., Krebs, D., Dellmann, L., & Eleftheriou, E. S. (2015) · Nature Communications · doi:10.1038/ncomms9181 · Cited by 169 · see citing works
Self-citationProgramming algorithms for multilevel phase-change memory
Papandreou, N., Pozidis, H., Pantazi, A., Sebastian, A., Breitwisch, M., Lam, C., & Eleftheriou, E. (2011) · 2011 IEEE International Symposium of Circuits and Systems (ISCAS) · doi:10.1109/iscas.2011.5937569 · Cited by 124 · see citing works
Self-citationNovel Lithography-Independent Pore Phase Change Memory
Breitwisch, M., Nirschl, T., Chen, C. F., Zhu, Y., Lee, M. H., Lamorey, M., Burr, G. W., Joseph, E. A., Schrott, A. G., Philipp, J. B., et al. (2007) · Symposium on VLSI Technology · doi:10.1109/vlsit.2007.4339743 · Cited by 116 · see citing works
High-speed compressed sensing reconstruction on FPGA using OMP and AMP
Bai, L., Maechler, P., Muehlberghuber, M., et al. (2012) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs.2012.6463559 · Cited by 101 · see citing works
VLSI Design of Approximate Message Passing for Signal Restoration and Compressive Sensing
Maechler, P., Studer, C., Bellasi, D. E., et al. (2012) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2012.2214636 · Cited by 73 · see citing works
Subthreshold electrical transport in amorphous phase-change materials
Gallo, M. L., Kaes, M., Sebastian, A., & Krebs, D. (2015) · New Journal of Physics · doi:10.1088/1367-2630/17/9/093035 · Cited by 59 · see citing works
Self-citationCMOS compressed imaging by Random Convolution
Jacques, L., Vandergheynst, P., Bibet, A., et al. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4959783 · Cited by 58 · see citing works
From Denoising to Compressed Sensing
Metzler, C. A., Maleki, A., & Baraniuk, R. G. (2016) · IEEE Transactions on Information Theory · doi:10.1109/tit.2016.2556683 · Cited by 44 · see citing works
Implementation of greedy algorithms for LTE sparse channel estimation
Maechler, P., Greisen, P., Sporrer, B., et al. (2010) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2010.5757587 · Cited by 34 · see citing works
Compressed sensing recovery using computational memory
Le Gallo, M., Sebastian, A., Cherubini, G., Giefers, H., & Eleftheriou, E. (2017) · 2017 IEEE International Electron Devices Meeting (IEDM) · doi:10.1109/iedm.2017.8268469 · Cited by 28 · see citing works
Self-citationUltra-fast robust compressive sensing based on memristor crossbars
Liu, S., Ren, A., Wang, Y., et al. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952333 · Cited by 5 · see citing works
Imaging in radio interferometry by iterative subset scanning using a modified AMP algorithm
Cherubini, G., Hurley, P., Simeoni, M., et al. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472293 · Cited by 1 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Memory devices and applications for in-memory computing
Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R., & Eleftheriou, E. (2020) · Nature Nanotechnology · doi:10.1038/s41565-020-0655-z · Cited by 2,289 · see citing works
Self-citationAccurate deep neural network inference using computational phase-change memory
Joshi, V., Le Gallo, M., Haefeli, S., Boybat, I., Nandakumar, S. R., Piveteau, C., Dazzi, M., Rajendran, B., Sebastian, A., & Eleftheriou, E. (2020) · Nature Communications · doi:10.1038/s41467-020-16108-9 · Cited by 490 · see citing works
Self-citationAn overview of phase-change memory device physics
Le Gallo, M., & Sebastian, A. (2020) · Journal of Physics D: Applied Physics · doi:10.1088/1361-6463/ab7794 · Cited by 460 · see citing works
Self-citationLe Gallo, M., Khaddam-Aljameh, R., Stanisavljevic, M., Vasilopoulos, A., Kersting, B., Dazzi, M., Karunaratne, G., Brändli, M., Singh, A., Müller, S. M., et al. (2023) · Nature Electronics · doi:10.1038/s41928-023-01010-1 · Cited by 310 · see citing works
Self-citationRasch, M. J., Mackin, C., Le Gallo, M., Chen, A., Fasoli, A., Odermatt, F., Li, N., Nandakumar, S. R., Narayanan, P., Tsai, H., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-40770-4 · Cited by 178 · see citing works
“8 can be compensated in the digital domain without any expensive re-programming [46, 4].”
BackgroundSelf-citationMixed-Precision Deep Learning Based on Computational Memory
Nandakumar, S. R., Le Gallo, M., Piveteau, C., Joshi, V., Mariani, G., Boybat, I., Karunaratne, G., Khaddam-Aljameh, R., Egger, U., Petropoulos, A., et al. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00406 · Cited by 120 · see citing works
Self-citation
- Authors
- Le Gallo, M., Sebastian, A., Cherubini, G., Giefers, H., & Eleftheriou, E.
- Affiliations
- IBM Research - Zurich (CH)
- Venue
- IEEE Transactions on Electron Devices
- Published
- 2018-10
- Volume
- 65
- Issue
- 10
- Pages
- 4304-4312
- ISSN
- 0018-9383 (ISSN-L)
- 1557-9646
- OpenAlex
- W2889448077
- Cited by
- 99
- References
- 22
- Citations by year
- 2026: 2 · 2025: 10 · 2024: 9 · 2023: 18 · 2022: 14 · 2021: 15 · 2020: 19 · 2019: 10 · 2018: 2
- FWCI
- 8.47
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- IEEE Transactions on Electron Devices (publishedVersion)
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by-nc-nd)
- Funders
- H2020 European Research Council (682675)
- H2020 LEIT Information and Communication Technologies (780215)
- Topics
- Physical Sciences › Engineering › Computational Mechanics › Sparse and Compressive Sensing Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Low-power high-performance VLSI design
- Keywords
- compressed sensing, approximate message passing, in-memory computing, resistive random access memory, crossbar arrays, phase-change memory, sparse signal recovery, matrix-vector multiplication, non-von Neumann architecture
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
