Computation and Communication Aware Task Graph Scheduling on Multi-GPU Systems
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
119 | en_US |
dc.citation.spage |
115 | en_US |
dc.citation.woscount |
0 | en_US |
dc.contributor.author |
Wang, Yun-Ting | en_US |
dc.contributor.author |
Lee, Jia-Ying | en_US |
dc.contributor.author |
Lai, Bo-Cheng Charles | en_US |
dc.contributor.department |
電子工程學系及電子研究所 | zh_TW |
dc.contributor.department |
Department of Electronics Engineering and Institute of Electronics | en_US |
dc.date.accessioned |
2017-04-21T06:49:33Z | |
dc.date.available |
2017-04-21T06:49:33Z | |
dc.date.issued |
2015 | en_US |
dc.description.abstract |
GPUs have emerged as popular throughput computing platforms due to the massively parallel computing capability and low cost. To attain further performance enhancement beyond single GPU, there is a growing interest in exploiting systems with multiple GPUs. Attaining superior performance in a multi-GPU system involves three main design challenges, namely load balance, memory utilization, and data transfer. Imbalanced loading across a system could cause idling of GPUs while poor data reuse would trigger excessive memory accesses. The inefficient data transfer between a host and a device becomes a considerable performance overhead during high throughput computing. This paper aims at addressing the above design issues by proposing a Computation and Communication Aware task graph Scheduling (CCAS) for multi-GPU systems. The proposed scheduling approach (CCAS) adopts an effective heuristic algorithm that considers both data reuse and load balance in a multi-GPU system. The data transfer overhead is hidden by extensively overlapping computation and data communication. The experimental results of the proposed CCAS have demonstrated an average of 22.15% performance enhancement when compared with a previous work. | en_US |
dc.identifier.isbn |
978-1-4799-8058-1 | en_US |
dc.identifier.journal |
2015 IEEE INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING (DSP) | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/136316 | |
dc.identifier.wosnumber |
WOS:000380506600023 | en_US |
dc.language.iso |
en_US | en_US |
dc.subject |
GPUs | en_US |
dc.subject |
Scheduling | en_US |
dc.subject |
Task Graph | en_US |
dc.title |
Computation and Communication Aware Task Graph Scheduling on Multi-GPU Systems | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文