Evaluation of SYCL’s Different Data Parallel Kernels
Article No.: 10, Pages 1 - 4
Abstract
SYCL provides programmers with four, and in the case of AdaptiveCpp even five, ways for calling and writing a device kernel. This paper analyzes the performance of these diverse kernel invocation types for DPC++ and AdaptiveCpp as SYCL implementations on an NVIDIA A100 GPU, an AMD Instinct MI210 GPU, and a dual-socket AMD EPYC 9274F CPU. Using the example of a kernel matrix assembly, we show why the performance can differ by a factor of 100 in the worst case on the same hardware for the same problem using different SYCL implementations and kernel invocation types.
References
[1]
Aksel Alpay, Bálint Soproni, Holger Wünsche, and Vincent Heuveline. 2022. Exploring the Possibility of a HipSYCL-Based Implementation of OneAPI. In International Workshop on OpenCL (Bristol, United Kingdom, United Kingdom) (IWOCL’22). Association for Computing Machinery, New York, NY, USA, Article 10, 12 pages.
[2]
Marcel Breyer, Alexander Van Craen, and Dirk Pflüger. 2022. A Comparison of SYCL, OpenCL, CUDA, and OpenMP for Massively Parallel Support Vector Machine Classification on Multi-Vendor Hardware. In International Workshop on OpenCL (Bristol, United Kingdom, United Kingdom) (IWOCL’22). Association for Computing Machinery.
[3]
Marcel Breyer, Alexander Van Craen, and Dirk Pflüger. 2023. Performance Evolution of Different SYCL Implementations based on the Parallel Least Squares Support Vector Machine Library. In IWOCL ’23: Proceedings of the 2023 International Workshop on OpenCL (cambridge, United Kingdom, United Kingdom) (IWOCL & SYCLcon ’23). Association for Computing Machinery.
[4]
Wei Chu, Chong Jin Ong, and S Sathiya Keerthi. 2005. An Improved Conjugate Gradient Scheme to the Solution of Least Squares SVM. IEEE Transactions on Neural Networks 16, 2 (2005), 498–501. https://doi.org/10.1109/tnn.2004.841785
[5]
Tom Deakin, Simon McIntosh-Smith, Aksel Alpay, and Vincent Heuveline. 2021. Benchmarking and Extending SYCL Hierarchical Parallelism. In 2021 IEEE/ACM International Workshop on Hierarchical Parallelism for Exascale Computing.
[6]
Khronos®-SYCL™-Working-Group. 2023. SYCL™ 2020 Specification (revision 8). https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html
[7]
Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading Digits in Natural Images with Unsupervised Feature Learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011. Scientific Research, Granada, 12–17.
[8]
James Reinders, Ben Ashbaugh, James Brodman, Michael Kinsner, John Pennycook, and Xinmin Tian. 2021. Data Parallel C++: Mastering DPC++ for Programming of Heterogeneous Systems using C++ and SYCL. Springer Nature.
[9]
Johan A. K. Suykens and Joos Vandewalle. 1999. Least Squares Support Vector Machine Classifiers. Neural Processing Letters 9, 3 (1999), 293–300.
[10]
Alexander Van Craen, Marcel Breyer, and Dirk Pflüger. 2022. PLSSVM: A (multi-) GPGPU-accelerated Least Squares Support Vector Machine. IPVS - Scientific Computing - University of Stuttgart. https://github.com/SC-SGS/PLSSVM
[11]
Alexander Van Craen, Marcel Breyer, and Dirk Pflüger. 2022. PLSSVM: A (multi-)GPGPU-accelerated Least Squares Support Vector Machine. In 2022 IPDPSW. IEEE, New York, NY, USA, 818–827.
[12]
Alexander Van Craen, Marcel Breyer, and Dirk Pflüger. 2022. PLSSVM—Parallel Least Squares Support Vector Machine. Software Impacts 14 (2022), 100343.
Index Terms
- Evaluation of SYCL’s Different Data Parallel Kernels
Recommendations
Performance Evolution of Different SYCL Implementations based on the Parallel Least Squares Support Vector Machine Library
IWOCL '23: Proceedings of the 2023 International Workshop on OpenCLIn machine learning and scientific computing, some of the biggest challenges are efficient and performant portable computing. With our Parallel Least Squares Support Vector Machine (PLSSVM) library, we have not only developed an unrivaled Support ...
A Comparison of SYCL, OpenCL, CUDA, and OpenMP for Massively Parallel Support Vector Machine Classification on Multi-Vendor Hardware
IWOCL '22: Proceedings of the 10th International Workshop on OpenCLIn scientific computing and Artificial Intelligence (AI), which both rely on massively parallel tasks, frameworks like the Compute Unified Device Architecture (CUDA) and the Open Computing Language (OpenCL) are widely used to harvest the computational ...
Evaluating the performance portability of SYCL across CPUs and GPUs on bandwidth-bound applications
SC-W '23: Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and AnalysisIn this paper, we evaluate the portability of the SYCL programming model on some of the latest CPUs and GPUs from a wide range of vendors, utilizing the two main compilers: DPC++ and hipSYCL/OpenSYCL. Both compilers currently support GPUs from all three ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
April 2024
124 pages
ISBN:9798400717901
DOI:10.1145/3648115
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 April 2024
Check for updates
Badges
Best Short Paper
Author Tags
Qualifiers
- Short-paper
- Research
- Refereed limited
Funding Sources
- EXC2075
- AISA
Conference
IWOCL '24
Acceptance Rates
Overall Acceptance Rate 84 of 152 submissions, 55%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 47Total Downloads
- Downloads (Last 12 months)47
- Downloads (Last 6 weeks)5
Reflects downloads up to 12 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format