KAWS: Coordinate Kernel-Aware Warp Scheduling and Warp Sharing Mechanism for Advanced GPUsopen accessKAWS: Coordinate Kernel-Aware Warp Scheduling and Warp Sharing Mechanism for Advanced GPUs
- Other Titles
- KAWS: Coordinate Kernel-Aware Warp Scheduling and Warp Sharing Mechanism for Advanced GPUs
- Authors
- Viet Tan Vo; 김철홍
- Issue Date
- Dec-2021
- Publisher
- 한국정보처리학회
- Keywords
- GPU; Multiple Warp Schedulers; Resource Underutilization; Warp Scheduling
- Citation
- JIPS(Journal of Information Processing Systems), v.17, no.9, pp.1157 - 1169
- Journal Title
- JIPS(Journal of Information Processing Systems)
- Volume
- 17
- Number
- 9
- Start Page
- 1157
- End Page
- 1169
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/41734
- DOI
- 10.3745/JIPS.01.0084
- ISSN
- 1976-913X
- Abstract
- Modern graphics processor unit (GPU) architectures offer significant hardware resource enhancements for parallel computing. However, without software optimization, GPUs continuously exhibit hardware resource underutilization. In this paper, we indicate the need to alter different warp scheduler schemes during different kernel execution periods to improve resource utilization. Existing warp schedulers cannot be aware of the kernelprogress to provide an effective scheduling policy. In addition, we identified the potential for improving resource utilization for multiple-warp-scheduler GPUs by sharing stalling warps with selected warp schedulers.
To address the efficiency issue of the present GPU, we coordinated the kernel-aware warp scheduler and warp sharing mechanism (KAWS). The proposed warp scheduler acknowledges the execution progress of the running kernel to adapt to a more effective scheduling policy when the kernel progress attains a point of resource underutilization. Meanwhile, the warp-sharing mechanism distributes stalling warps to different warpschedulers wherein the execution pipeline unit is ready. Our design achieves performance that is on an average higher than that of the traditional warp scheduler by 7.97% and employs marginal additional hardware overhead.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Information Technology > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.