CoChat

Neural inference at the frontier of energy, space, and time

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Abstract

Computing, since its inception, has been processor-centric, with memory separated from compute. Inspired by the organic brain and optimized for inorganic silicon, NorthPole is a neural inference architecture that blurs this boundary by eliminating off-chip memory, intertwining compute with memory on-chip, and appearing externally as an active memory chip. NorthPole is a low-precision, massively parallel, densely interconnected, energy-efficient, and spatial computing architecture with a co-optimized, high-utilization programming model. On the ResNet50 benchmark image classification network, relative to a graphics processing unit (GPU) that uses a comparable 12-nanometer technology process, NorthPole achieves a 25 times higher energy metric of frames per second (FPS) per watt, a 5 times higher space metric of FPS per transistor, and a 22 times lower time metric of latency. Similar results are reported for the Yolo-v4 detection network. NorthPole outperforms all prevalent architectures, even those that use more-advanced technology processes.

Overview

Integrity signals

Registry

Crossref · 10.1126/science.adh1174

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Research works printed but not linked: 8

  1. T. J. Sejnowski P. S. Churchland The Computational Brain (MIT Press 1994).
  2. N. C. Thompson K. Greenewald K. Lee G. F. Manso The computational limits of deep learning. arXiv:2007.05558 [cs.LG] (2020). · arXiv
  3. S. K. Esser J. L. McKinstry D. Bablani R. Appuswamy D. S. Modha “Learned step size quantization” in Eighth International Conference on Learning Representations (ICLR) (ICLR 2020).
  4. D. Bablani J. L. McKinstry S. K. Esser R. Appuswamy D. S. Modha Efficient and effective methods for mixed precision neural network quantization for faster energy-efficient inference. arXiv:2301.13330 [cs.LG] (2023). · arXiv
  5. G. Hinton O. Vinyals J. Dean Distilling the knowledge in a neural network. arXiv:1503.02531 [stat.ML] (2015). · arXiv
  6. A. Bochkovskiy C. Y. Wang H. Y. Liao YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.13934 [cs.CV] (2020). · arXiv
  7. R. Zhan X. Fan “NeuralScale: A RISC-V based neural processor boosting AI inference in clouds” in Fifth Workshop on Computer Architecture Research with RISC-V (CARRV 2021) (2021).
  8. M. Ditty A. Karandikar D. Reed “Nvidia’s Xavier SOC” in 2018 Hot Chips 30 Symposium (HCS) (2018).

Cited by

See all 115

Metadata

Authors
Modha, D. S., Akopyan, F., Andreopoulos, A., Appuswamy, R., Arthur, J. V., Cassidy, A. S., Datta, P., DeBole, M. V., Esser, S. K., Otero, C. O., Sawada, J., Taba, B., Amir, A., Bablani, D., Carlson, P. J., Flickner, M. D., Gandhasri, R., Garreau, G. J., Ito, M., Klamo, J. L., Kusnitz, J. A., McClatchey, N. J., McKinstry, J. L., Nakamura, Y., Nayak, T. K., Risk, W. P., Schleupen, K., Shaw, B., Sivagnaname, J., Smith, D. F., Terrizzano, I., & Ueda, T.
Affiliations
IBM (United States) (US)
Corresponding author
  • Modha, Dharmendra S.
  • Akopyan, Filipp
  • Andreopoulos, Alexander
  • Appuswamy, Rathinakumar
  • Arthur, John V.
  • Cassidy, Andrew S.
  • Datta, Pallab
  • DeBole, Michael V.
  • Esser, Steven K.
  • Otero, Carlos Ortega
  • Sawada, Jun
  • Taba, Brian
Venue
Science
Published
2023-10-20
Volume
382
Issue
6668
Pages
329-335
ISSN
  • 0036-8075 (ISSN-L)
  • 1095-9203
OpenAlex
W4387772271
Cited by
115
References
47
Citations by year
2026: 33 · 2025: 34 · 2024: 44 · 2023: 4
FWCI
8.56
Type
journal article
Language
en
Open access
closed
Locations
  • Science (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
  • Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
in-memory computing, memory-centric computing, low-precision arithmetic, energy efficiency, spatial computing, image classification, object detection, ResNet50, YOLOv4, programming models, neuromorphic hardware

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.