Programming parallel dense matrix factorizations and inversion for new-generation NUMA architectures.
Sandra CatalánFrancisco D. IgualJosé R. HerreroRafael Rodríguez-SánchezEnrique S. Quintana-OrtíPublished in: J. Parallel Distributed Comput. (2023)
Keyphrases
- matrix factorization
- multicore processors
- shared memory
- collaborative filtering
- parallel architectures
- programming language
- high end
- recommender systems
- negative matrix factorization
- low rank
- load balancing
- parallel processing
- multi core processors
- missing data
- factorization methods
- parallel programming
- parallel computers
- parallel computation
- programming environment
- parallel computing
- distributed memory
- nonnegative matrix factorization
- image reconstruction
- stochastic gradient descent
- matrix multiplication
- parallel implementation
- execution model
- data sets