103 0

Efficient GPU multitasking with latency minimization and cache boosting

Title
Efficient GPU multitasking with latency minimization and cache boosting
Author
박영준
Keywords
GPGPU; multitasking; energy; resource sharing; workload balancing
Issue Date
2017-04
Publisher
IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG
Citation
IEICE ELECTRONICS EXPRESS, v. 14, no. 7, Article no. 20161158
Abstract
GPU spatial multitasking has been proven to be quite effective at executing different applications concurrently using SM partitioning. However, while it maximizes total throughput, latency-critical applications often cannot meet their deadlines due to the increased execution time. Furthermore, SM partitioning cannot allocate the appropriate L1 cache size per kernel. To solve these problems, this paper proposes a new application-aware resource allocation framework called GPU Fine-Tuner, for assigning appropriate resources to GPU kernels. To minimize the execution time of latency-constrained applications, it assigns them more SMs when performance is not affected. It also increases the cache size of SMs for cache-sensitive kernels using resource borrowing from neighbors for cache-insensitive kernels. Experimental results show that the Fine-Tuner outperforms GPU spatial multitasking with up to 15% less average latency without performance degradation.
URI
https://www.jstage.jst.go.jp/article/elex/14/7/14_14.20161158/_articlehttps://repository.hanyang.ac.kr/handle/20.500.11754/113738
ISSN
1349-2543
DOI
10.1587/elex.14.20161158
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE