@article{M2D6E0A76,
title = "GPU Resource Contention Management Technique for Simultaneous GPU 
Tasks in the Container Environments with Share the GPU",
journal = "The Transactions of the Korea Information Processing Society",
year = "2022",
issn = "null",
doi = "https://doi.org/10.3745/KTCCS.2022.11.10.333",
author = "Jihun Kang",
keywords = "HPC Cloud, Container, GPU Computing, GPU Sharing, Resource Race",
abstract = "In a container-based cloud environment, multiple containers can share a graphical processing unit (GPU), and GPU sharing can minimize 
idle time of GPU resources and improve resource utilization. However, in a cloud environment, GPUs, unlike CPU or memory, cannot 
logically multiplex computing resources to provide users with some of the resources in an isolated form. In addition, containers occupy 
GPU resources only when performing GPU operations, and resource usage is also unknown because the timing or size of each container's 
GPU operations is not known in advance. Containers unrestricted use of GPU resources at any given point in time makes managing resource 
contention very difficult owing to where multiple containers run GPU tasks simultaneously, and GPU tasks are handled in black box form 
inside the GPU. In this paper, we propose a container management technique to prevent performance degradation caused by resource 
competition when multiple containers execute GPU tasks simultaneously. Also, this paper demonstrates the efficiency of container 
management techniques that analyze and propose the problem of degradation due to resource competition when multiple containers 
execute GPU tasks simultaneously through experiments."
}