Latency-Based Inter-Operator Scheduling for CNN Inference Acceleration on GPU.
Yukai PingHe JiangXingxiang LiuZhenyang ZhaoZhide ZhouXin ChenPublished in: IEEE Trans. Serv. Comput. (2024)
Keyphrases
- heterogeneous computing
- scheduling problem
- resource utilization
- cellular neural networks
- scheduling algorithm
- compute intensive
- round robin
- bayesian networks
- data transfer
- inference process
- response time
- real time
- parallel computing
- parallel implementation
- resource allocation
- wireless broadcast
- dynamic bayesian networks
- graphics processing units
- bayesian inference
- graphics hardware
- parallel processors
- real time database systems
- flexible manufacturing systems
- memory bandwidth