Characterizing and understanding deep neural network batching systems on GPUs
Authors:
- Feng YuFYFeng Yu
- Hao ZhangHZHao Zhang
- Ao ChenACAo Chen
- Xueying WangXWXueying Wang
- Xiaoxia LiangXLXiaoxia Liang
- Sheng WangSWSheng Wang
- Guangli LiGLGuangli Li
- Huimin CuiHCHuimin Cui
- Xiaobing FengXFXiaobing Feng
Open Access
- 1 December 2023
- journal article
- research article
- Published by Elsevier in BenchCouncil Transactions on Benchmarks, Standards and Evaluations
- Vol. 3 (4)
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62090024)
- National Natural Science Foundation of China (62232015)
- National Natural Science Foundation of China (62302479)
- China Postdoctoral Science Foundation (2023M733566)
- Institute of Computing Technology, Chinese Academy of Sciences (E361010)
This publication has 16 references indexed in Scilit:
- E2bird: Enhanced Elastic Batch for Improving Responsiveness and Throughput of Deep Learning ServicesIEEE Transactions on Parallel and Distributed Systems, 2020
- MLPerf Inference Benchmark2020
- DyBatch: Efficient Batching and Fair Scheduling for Deep Learning Inference on Time-sharing Devices2020
- Ebird: Elastic Batch for Improving Responsiveness and Throughput of Deep Learning Services2019
- PipeDream2019
- Nanily: A QoS-Aware Scheduling for DNN Inference Workload in Clouds2019
- Deep Residual Learning for Image Recognition2016
- Caffe2014
- Torchvision the machine-vision package of torch2010
- A versatile Markovian point processJournal of Applied Probability, 1979