Topology-aware GPU scheduling for learning workloads in cloud environments

Marcelo Amaral
Marcelo Amaral
Jordà Polo
Jordà Polo

SC '17: The International Conference for High Performance Computing, Networking, Storage and Analysis Denver Colorado November, 2017, pp. 1-12, 2017.

被引用18|浏览24
EI

摘要

Recent advances in hardware, such as systems with multiple GPUs and their availability in the cloud, are enabling deep learning in various domains including health care, autonomous vehicles, and Internet of Things. Multi-GPU systems exhibit complex connectivity among GPUs and between GPUs and CPUs. Workload schedulers must consider hardwa...更多

代码

数据

ZH
24小时获取PDF
引用
您的评分 :
0

 

标签
评论