Login / Signup
Enabling Highly Efficient Batched Matrix Multiplications on SW26010 Many-core Processor.
Lijuan Jiang
Chao Yang
Wenjing Ma
Published in:
ACM Trans. Archit. Code Optim. (2020)
Keyphrases
</>
highly efficient
factorization methods
low cost
low latency
search algorithm
low complexity
sat solvers
matrix representation
discriminative learning
multithreading
low rank
backtrack search
high classification accuracy
real time
singular value decomposition
search space
search engine