Deep learning applications have become increasingly popular in recent years, leading to the development of specialized hardware accelerators such as fpgas and gpus. These accelerators provide significant performance g...
详细信息
ISBN:
(纸本)9783031503849;9783031503856
Deep learning applications have become increasingly popular in recent years, leading to the development of specialized hardware accelerators such as fpgas and gpus. These accelerators provide significant performance gains over traditional CPUs, but their efficient utilization requires careful scheduling configuration for given DL requests. In this paper, we propose a SLO-aware DL job scheduling model for efficient fpga-gpu edge cloud computing. The proposed model takes into account variant service-level objectives of the DL job and periodically updates the accelerator configuration of DL processing while minimizing computation costs accordingly. We first analyze the impact of various DL-related parameters on the performance of fpga-gpu computing. We then propose a novel scheduling algorithm that considers the timevariant latency SLO constraints and periodically updates the scheduling configuration. We evaluated our scheduler using several DL workloads on a fpga-gpu cluster. Our results demonstrated that our scheduler achieves improvements in terms of both energy consumption and SLO compliance compared to the traditional DL scheduling approach.
暂无评论