paper-with-me

Papers

PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Units

2019-09-06 · Yujeong Choi, Minsoo Rhu

To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a "preemptible" neural processing unit (NPU) and a "predictive" multi-task scheduler to meet the latency demands of high-priority inference while maintaining high throughput. We evaluate both the mechanisms that enable NPUs to be preemptible and the policies that utilize them to meet scheduling objectives. We show that preemptive NPU multi-tasking can achieve an average 7.8x, 1.4x, and 4.8x improvement in latency, throughput, and SLA satisfaction, respectively.

📄 PDF Abstract BibTeX arXiv:1909.04548

Code (1)

agongee/prema_sim pytorch

Tasks

Scheduling

Similar Papers 제목 키워드 기반

Improving TAS Adaptability with a Variable Temperature Threshold

2024-04-25 · Anthony Dowling, Ming-Cheng Cheng, Yu Liu

Thermal-Aware Scheduling (TAS) provides methods to manage the thermal dissipation of a computing chip during task execution. These methods aim to avoid issues such as accelerated aging of the device, premature failure an…

Scheduling

Genetic Algorithm-based Routing and Scheduling for Wildfire Suppression using a Team of UAVs

2024-07-27 · Josy John, Suresh Sundaram

This paper addresses early wildfire management using a team of UAVs for the mitigation of fires. The early detection and mitigation systems help in alleviating the destruction with reduced resource utilization. A Genetic…

DiversityManagementScheduling

Regulating CPU Temperature With Thermal-Aware Scheduling Using a Reduced Order Learning Thermal Model

2023-10-02 · Anthony Dowling, Lin Jiang, Ming-Cheng Cheng, Yu Liu

Modern real-time systems utilize considerable amounts of power while executing computation-intensive tasks. The execution of these tasks leads to significant power dissipation and heating of the device. It therefore resu…

CPUScheduling

Renewable energy management in smart home environment via forecast embedded scheduling based on Recurrent Trend Predictive Neural Network

2023-07-04 · Applied Energy 2023 3 · Mert Nakıp, Onur Çopur, Emrah Biyik, Cüneyt Güzeliş

Smart home energy management systems help the distribution grid operate more efficiently and reliably, and enable effective penetration of distributed renewable energy sources. These systems rely on robust forecasting, o…

energy managementManagementScheduling

Dynamic Measurement Scheduling for Adverse Event Forecasting using Deep RL

2018-12-01 · Chun-Hao Chang, Mingjie Mai, Anna Goldenberg

Current clinical practice to monitor patients' health follows either regular or heuristic-based lab test (e.g. blood test) scheduling. Such practice not only gives rise to redundant measurements accruing cost, but may ev…

Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Scheduling