Accelerating Machine Learning on Sparse Datasets with a Distributed Memory Vector Architecture.
Takuya ArakiPublished in: ISPDC (2017)
Keyphrases
- distributed memory
- machine learning
- parallel architecture
- multi processor
- shared memory
- parallel computers
- sparse matrix
- scientific computing
- parallel implementation
- multiprocessor systems
- multithreading
- ibm sp
- fine grain
- single processor
- reinforcement learning
- computer vision
- artificial intelligence
- computer science
- feature selection
- parallel machines
- parallel computing
- data flow
- hardware implementation
- high resolution
- program execution
- matrix multiplication
- bayesian networks