Login / Signup
Accelerating small matrix multiplications by adaptive batching strategy on GPU.
Yaqing Zhang
Yaobin Wang
Zhangbin Mo
Yong Zhou
Tao Sun
Guang Xu
Chaojun Xing
Liang Yang
Published in:
HPCC/DSS/SmartCity/DependSys (2022)
Keyphrases
</>
adaptive strategies
real time
small number
image processing
gpu implementation
information systems
general purpose
e learning
reinforcement learning
special case
genetic algorithm
covariance matrix
singular value decomposition
parallel processing
low rank
optimal strategy
neural network