Conference paper · 2021

Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs

Sumin Kim, Seunghwan Oh, Youngmin Yi

IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), 57–63 · Published 20 February 2021 · DOI 10.1145/3446382.3448606

View at the publisherCite this paper

In brief

“Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs” is a 2021 conference paper by Sumin Kim and 2 co-authors, published in IEEE Workshop on Mobile Computing Systems and Applications (WMCSA). OpenAlex counts 24 citations as of 19 November 2026, which puts it in the top 8% of works published in 2021 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
24
Most cited in
2022 (10)
Field-weighted impact
2.35
References
8
Authors
3

Abstract

The need for on-device real-time Deep Learning inference is increasing as deep learning on edge devices such as smartphones and robots are becoming popular. Although hardware acceleration on NPU is attracting more attention, the recent mobile GPUs are fast enough to provide the potential to achieve real-time inference of many CNNs. In this paper, we… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kim, S., Oh, S., & Yi, Y. (2021). Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs. IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), 57–63. https://doi.org/10.1145/3446382.3448606

MLA 9

Kim, Sumin, et al. “Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs.” IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), 2021, pp. 57–63. https://doi.org/10.1145/3446382.3448606.

Chicago

Kim, Sumin, Seunghwan Oh, and Youngmin Yi. 2021. “Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs.” IEEE Workshop on Mobile Computing Systems and Applications (WMCSA): 57–63. https://doi.org/10.1145/3446382.3448606.

Harvard

Kim, S., Oh, S. and Yi, Y. (2021) ‘Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs’, IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), pp. 57–63. doi:10.1145/3446382.3448606.

IEEE

S. Kim, S. Oh, and Y. Yi, “Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs,” IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), pp. 57–63, 2021, doi: 10.1145/3446382.3448606.

BibTeX

@inproceedings{kim2021minimizing,
  title     = {{Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs}},
  author    = {Kim, Sumin and Oh, Seunghwan and Yi, Youngmin},
  booktitle = {IEEE Workshop on Mobile Computing Systems and Applications (WMCSA)},
  year      = {2021},
  pages     = {57--63},
  doi       = {10.1145/3446382.3448606},
  url       = {https://doi.org/10.1145/3446382.3448606}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202133
20221010
202322
202433
202522
202644

Its field-weighted citation impact is 2.35: it has been cited 2.35 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

  • mobile GPUs
  • deep learning inference
  • on-device inference
  • edge computing
  • convolutional neural networks
  • performance modeling
  • inference acceleration
  • TensorFlow Lite

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Kim, S., Oh, S., & Yi, Y. (2021). Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs. IEEE Workshop on Mobile Computing Systems and Applications (WMCSA), 57–63. https://doi.org/10.1145/3446382.3448606

How many times has this paper been cited?

24 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Sumin Kim, Seunghwan Oh, Youngmin Yi.

What is the DOI of this paper?

10.1145/3446382.3448606, permanently at https://doi.org/10.1145/3446382.3448606. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.