Conference paper · 2019 · Open access
DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis
IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 293–303 · Published 1 March 2019 · DOI 10.1109/ispass.2019.00041
In brief
“DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis” is a 2019 conference paper by Sangkug Lym and 4 co-authors, published in IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). OpenAlex counts 63 citations as of 21 November 2026, which puts it in the top 5% of works published in 2019 by citations. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 63
- Most cited in
- 2023 (13)
- Field-weighted impact
- 3.22
- References
- 34
- Authors
- 5
Abstract
Training convolutional neural networks (CNNs) requires intense compute throughput and high memory bandwidth. Especially, convolution layers account for the majority of execution time of CNN training, and GPUs are commonly used to accelerate these layer workloads. GPU design optimization for efficient CNN training acceleration requires the accurate modeling of how their performance improves when computing and memory resources are increased. We present DeLTA, the first analytical model that accurately estimates the traffic at each GPU memory hierarchy level, while accounting for the complex reuse patterns of a parallel convolution algorithm. We demonstrate that our model is both accurate and robust for different CNNs and GPU architectures. We then show how this model can be used to carefully balance the scaling of different GPU resources for efficient CNN performance improvement.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lym, S., Lee, D., O’Connor, M., Chatterjee, N., & Erez, M. (2019). DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis. IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 293–303. https://doi.org/10.1109/ispass.2019.00041
MLA 9
Lym, Sangkug, et al. “DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis.” IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2019, pp. 293–303. https://doi.org/10.1109/ispass.2019.00041.
Chicago
Lym, Sangkug, Donghyuk Lee, Mike O’Connor, Niladrish Chatterjee, and Mattan Erez. 2019. “DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis.” IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS): 293–303. https://doi.org/10.1109/ispass.2019.00041.
Harvard
Lym, S. et al. (2019) ‘DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis’, IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 293–303. doi:10.1109/ispass.2019.00041.
IEEE
S. Lym, D. Lee, M. O’Connor, N. Chatterjee, and M. Erez, “DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis,” IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 293–303, 2019, doi: 10.1109/ispass.2019.00041.
BibTeX
@inproceedings{lym2019delta,
title = {{DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis}},
author = {Lym, Sangkug and Lee, Donghyuk and O’Connor, Mike and Chatterjee, Niladrish and Erez, Mattan},
booktitle = {IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)},
year = {2019},
pages = {293--303},
doi = {10.1109/ispass.2019.00041},
url = {https://doi.org/10.1109/ispass.2019.00041}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2019 | 3 | |
| 2020 | 5 | |
| 2021 | 6 | |
| 2022 | 9 | |
| 2023 | 13 | |
| 2024 | 7 | |
| 2025 | 11 | |
| 2026 | 9 |
Its field-weighted citation impact is 3.22: it has been cited 3.22 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- GPU performance modeling
- convolutional neural network training
- memory bandwidth
- deep learning acceleration
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Lym, S., Lee, D., O’Connor, M., Chatterjee, N., & Erez, M. (2019). DeLTA: GPU Performance Model for Deep Learning Applications with In-Depth Memory System Traffic Analysis. IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 293–303. https://doi.org/10.1109/ispass.2019.00041
How many times has this paper been cited?
63 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sangkug Lym, Donghyuk Lee, Mike O’Connor, Niladrish Chatterjee, Mattan Erez.
What is the DOI of this paper?
10.1109/ispass.2019.00041, permanently at https://doi.org/10.1109/ispass.2019.00041. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.