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

Zhao-Wei Qiu, Kun-Sheng Liu, Ya-Shu Chen. BARM: A Batch-Aware Resource Manager for Boosting Multiple Neural Networks Inference on GPUs With Memory Oversubscription. IEEE Trans. Parallel Distrib. Syst., 33(12):4612-4624, 2022. [doi]

Authors

Zhao-Wei Qiu

This author has not been identified. Look up 'Zhao-Wei Qiu' in Google

Kun-Sheng Liu

This author has not been identified. Look up 'Kun-Sheng Liu' in Google

Ya-Shu Chen

This author has not been identified. Look up 'Ya-Shu Chen' in Google