TENSILE: A Tensor Granularity Dynamic GPU Memory Scheduling Method Toward Multiple Dynamic Workloads System

Kaixin Zhang, Hongzhi Wang 0001, Han Hu, Songling Zou, Jiye Qiu, Tongxin Li, Zhishun Wang. TENSILE: A Tensor Granularity Dynamic GPU Memory Scheduling Method Toward Multiple Dynamic Workloads System. IEEE Trans. Knowl. Data Eng., 35(8):8630-8643, August 2023. [doi]

Abstract

Abstract is missing.