Characterization and prediction of deep learning workloads in large-scale GPU datacenters
| Autor: | Tianwei Zhang, Shengen Yan, Peng Sun, Yonggang Wen, Qinghao Hu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Service (systems architecture) Computer science business.industry Deep learning Distributed computing Machine Learning (cs.LG) Scheduling (computing) Energy conservation Computer Science - Distributed Parallel and Cluster Computing Scale (social sciences) Cluster (physics) Resource management Distributed Parallel and Cluster Computing (cs.DC) Artificial intelligence Time series business |
| Zdroj: | SC |
| DOI: | 10.1145/3458817.3476223 |
| Popis: | Modern GPU datacenters are critical for delivering Deep Learning (DL) models and services in both the research community and industry. When operating a datacenter, optimization of resource scheduling and management can bring significant financial benefits. Achieving this goal requires a deep understanding of the job features and user behaviors. We present a comprehensive study about the characteristics of DL jobs and resource management. First, we perform a large-scale analysis of real-world job traces from SenseTime. We uncover some interesting conclusions from the perspectives of clusters, jobs and users, which can facilitate the cluster system designs. Second, we introduce a general-purpose framework, which manages resources based on historical data. As case studies, we design: a Quasi-Shortest-Service-First scheduling service, which can minimize the cluster-wide average job completion time by up to 6.5x; and a Cluster Energy Saving service, which improves overall cluster utilization by up to 13%. Comment: This paper has been accepted by the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC21), Nov 14-19, 2021, St. Louis, USA |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|