Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 203

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems

Open access
Gobieski, Graham, Lucia, Brandon, Beckmann, Nathan · 2019 · Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems

Abstract

Energy-harvesting technology provides a promising platform for future IoT applications. However, since communication is very expensive in these devices, applications will require inference "beyond the edge" to avoid wasting precious energy on pointless communication. We show that application performance is highly sensitive to inference accuracy. Unfortunately, accurate inference requires large amounts of computation and memory, and energy-harvesting systems are severely resource-constrained. Moreover, energy-harvesting systems operate intermittently, suffering frequent power failures that corrupt results and impede forward progress. This paper overcomes these challenges to present the first full-scale demonstration of DNN inference on an energy-harvesting system. We design and implement SONIC, an intermittence-aware software system with specialized support for DNN inference. SONIC introduces loop continuation, a new technique that dramatically reduces the cost of guaranteeing correct intermittent execution for loop-heavy code like DNN inference. To build a complete system, we further present GENESIS, a tool that automatically compresses networks to optimally balance inference accuracy and energy, and TAILS, which exploits SIMD hardware available in some microcontrollers to improve energy efficiency. Both SONIC & TAILS guarantee correct intermittent execution without any hand-tuning or performance loss across different power systems. Across three neural networks on a commercially available microcontroller, SONIC & TAILS reduce inference energy by 6.9× and 12.2×, respectively, over the state-of-the-art.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3297858.3304011

Cites

8 of 8 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 8 references

Research works printed but not linked: 67

  1. 10.1109/ISCA.2016.11 · DOI · Paper page
  2. 10.5555/3195638.3195664 · doi:10.5555/3195638.3195664
  3. 10.1145/2994551.2994564 · DOI · Paper page
  4. 10.5555/1972457.1972478 · doi:10.5555/1972457.1972478
  5. 10.1145/2541940.2541967 · DOI · Paper page
  6. 10.1109/MICRO.2014.58 · DOI · Paper page
  7. 10.1109/ISCA.2016.40 · DOI · Paper page
  8. 10.1145/2872362.2872409 · doi:10.1145/2872362.2872409
  9. 10.1145/2983990.2983995 · DOI · Paper page
  10. Alexei Colin Emily Ruppel and Brandon Lucia. 2018. A Reconfigurable Energy Storage Architecture for Energy-harvesting Devices. In ASPLOS . 10.1145/3173162.3173210 · doi:10.1145/3173162.3173210
  11. Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or-1. arXiv preprint arXiv:1602.02830 (2016). · arXiv
  12. 10.1145/633625.52417 · doi:10.1145/633625.52417
  13. 10.1109/MC.2008.224 · doi:10.1109/mc.2008.224
  14. 10.1137/S0895479896305696 · DOI · Paper page
  15. 10.1137/S0895479898346995 · DOI · Paper page
  16. 10.1145/3079856.3080248 · DOI
  17. 10.1145/3123939.3124552 · DOI · Paper page
  18. 10.1109/PERCOMW.2017.7917625 · DOI
  19. 10.1145/2749469.2750389 · DOI · Paper page
  20. 10.1109/PACT.2017.58 · DOI
  21. L. Fick, D. Blaauw, D. Sylvester, S. Skrzyniarz, M. Parikh, and D. Fick. 2017. Analog in-memory subthreshold deep neural network accelerator. In 2017 IEEE Custom Integrated Circuits Conference (CICC). 1--4.
  22. 10.1145/3097983.3098043 · DOI · Paper page
  23. 10.1109/MM.2012.51 · doi:10.1109/mm.2012.51
  24. 10.5555/3305381.3305519 · doi:10.5555/3305381.3305519
  25. 10.1145/1816038.1815968 · DOI
  26. Song Han, Huizi Mao, and William J. Dally. 2016b. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization, and Huffman Coding. In Proc. of the 5th Intl. Conf. on Learning Representationas (Proc. ICLR'16) .
  27. 10.1145/2994551.2994554 · DOI
  28. 10.1145/2809695.2809707 · doi:10.1145/2809695.2809707
  29. 10.1145/3131672.3131674 · DOI
  30. 10.1145/3131672.3131673 · doi:10.1145/3131672.3131673
  31. 10.1145/3079856.3080238 · doi:10.1145/3079856.3080238
  32. 10.1109/ISSCC.2014.6757323 · DOI · Paper page
  33. Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015). · arXiv
  34. H. Jayakumar A. Raha and V. Raghunathan. 2014. QuickRecall: A Low Overhead HW/SW Approach for Enabling Computations across Power Cycles in Transiently Powered Computers. In Int'l Conf. on VLSI Design and Int'l Conf. on Embedded Systems . 10.1109/VLSID.2014.63 · doi:10.1109/vlsid.2014.63
  35. Norman P Jouppi, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, et almbox. 2017. In-datacenter performance analysis of a tensor processing unit. arXiv preprint arXiv:1704.04760 (2017). · arXiv
  36. 10.1145/3173162.3173176 · DOI · Paper page
  37. 10.1145/2737924.2737978 · DOI
  38. 10.1145/3123939.3124533 · doi:10.1145/3123939.3124533
  39. 10.1109/HPCA.2015.7056060 · DOI · Paper page
  40. 10.1145/3133920 · DOI · Paper page
  41. 10.5555/3291168.3291178 · doi:10.5555/3291168.3291178
  42. 10.1109/LCA.2017.2777834 · doi:10.1109/lca.2017.2777834
  43. A. Mirhoseini, E. M. Songhori, and F. Koushanfar. 2013. Idetic: A High-level Synthesis Approach for Enabling Long Computations on Transiently-powered ASICs. In IEEE Pervasive Computing and Communication Conference (PerCom). http://aceslab.org/sites/default/files/Idetic.pdf
  44. 10.5555/541177 · doi:10.5555/541177
  45. 10.5555/3291168.3291210 · doi:10.5555/3291168.3291210
  46. 10.1016/0893-6080(94)90058-2 · DOI
  47. 10.1145/2996884.2996888 · DOI
  48. Preetum Nakkiran, Raziel Alvarez, Rohit Prabhavalkar, and Carolina Parada. 2015. Compressing deep neural networks using a rank-constrained topology.. In Sixteenth Annual Conference of the International Speech Communication Association .
  49. 10.1145/2749469.2750380 · DOI
  50. 10.1145/3079856.3080254 · DOI · Paper page
  51. 10.1145/3079856.3080256 · DOI · Paper page
  52. 10.1109/JSSC.2017.2752838 · DOI
  53. 10.1145/1950365.1950386 · doi:10.1145/1950365.1950386
  54. 10.1145/3037697.3037746 · DOI
  55. Tara N Sainath and Carolina Parada. 2015. Convolutional neural networks for small-footprint keyword spotting. In 16th Annual Conference of the International Speech Communication Association .
  56. 10.1109/TIM.2008.925019 · DOI · Paper page
  57. 10.1145/859618.859667 · doi:10.1145/859618.859667
  58. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014). · arXiv
  59. M. Song, K. Zhong, J. Zhang, Y. Hu, D. Liu, W. Zhang, J. Wang, and T. Li. 2018. In-Situ AI: Towards Autonomous and Incremental Deep Learning for IoT Systems. In 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). 92--103.
  60. 10.5555/3298023.3298188 · doi:10.5555/3298023.3298188
  61. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  62. Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, et almbox. 2015b. Going deeper with convolutions. Cvpr.
  63. 10.1109/CVPR.2016.308 · DOI · Paper page
  64. TI Inc. 2014. Overview for MSP430FRxx FRAM. http://ti.com/wolverine. Visited July 28, 2014.
  65. 10.1007/BF02289464 · DOI · Paper page
  66. 10.5555/3026877.3026880 · doi:10.5555/3026877.3026880
  67. 10.5555/3195638.3195662 · doi:10.5555/3195638.3195662

Cited by

See all 203

Metadata

Authors
Gobieski, G., Lucia, B., & Beckmann, N.
Venue
Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems
Publisher
ACM
Published
2019-04-04
Pages
199-213
OpenAlex
W2897303255
Cited by
203
References
8
FWCI
24.47
Type
conference paper
Language
en
Open access
bronze
Funders
National Science Foundation (CCF-1815882,CCF-1751029)

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: Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems. https://app.cochat.ai/papers/10.1145/3297858.3304011
The paper
Gobieski, G., Lucia, B., & Beckmann, N. (2019). Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems. Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems. https://doi.org/10.1145/3297858.3304011

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.