Demystifying Tensor Cores to Optimize Half-Precision Matrix Multiply.
Da YanWei WangXiaowen ChuPublished in: IPDPS (2020)
Keyphrases
- trace norm
- projection matrices
- structure tensor
- tensor decomposition
- tensor factorization
- high order
- low rank
- high precision
- higher order
- frobenius norm
- symmetric positive definite
- precision and recall
- floating point
- average precision
- diffusion tensor
- dt mri
- matrix representation
- rows and columns
- lie group
- kullback leibler divergence
- real time
- data representation
- operating system
- genetic algorithm
- neural network