Optimizing GPU Kernels for Irregular Batch Workloads: A Case Study for Cholesky Factorization.
Ahmad AbdelfattahAzzam HaidarStanimire TomovJack J. DongarraPublished in: HPEC (2018)
Keyphrases
- gram matrix
- image pyramids
- kernel methods
- kernel function
- case study
- graphics hardware
- kernel matrix
- irregularly shaped
- database systems
- real time
- positive definite
- computer systems
- singular value decomposition
- test bed
- feature space
- support vector
- matrix factorization
- multiple kernel
- access patterns
- pairwise
- non rigid structure from motion
- gpu implementation
- arbitrarily shaped
- parallel computing
- low rank
- feature vectors
- multiple kernel learning
- kernel learning
- least squares
- parallel implementation
- batch mode
- sparse matrix
- gaussian processes
- high dimensional
- kronecker product
- linear combination
- general purpose