Login / Signup

BARM: A Batch-Aware Resource Manager for Boosting Multiple Neural Networks Inference on GPUs With Memory Oversubscription.

Zhao-Wei QiuKun-Sheng LiuYa-Shu Chen
Published in: IEEE Trans. Parallel Distributed Syst. (2022)
Keyphrases
  • resource manager
  • resource utilization
  • general purpose
  • resource management
  • main memory
  • parallel processing