Optimized Selection of Runtime Mode for the Reconfigurable PRAM-NUMA Architecture REPLICA Using Machine-Learning.
Erik HanssonChristoph W. KeßlerPublished in: Euro-Par Workshops (2) (2014)
Keyphrases
- machine learning
- load balancing
- selection mechanism
- management system
- storage devices
- learning algorithm
- mixed mode
- real time
- parallel algorithm
- machine learning algorithms
- low cost
- general purpose
- hardware implementation
- knowledge acquisition
- information extraction
- active learning
- machine learning methods
- dynamic reconfiguration
- computer vision
- text mining
- natural language processing
- support vector machine
- pattern recognition
- software architecture
- memory access
- information retrieval
- data mining
- heterogeneous computing
- systolic array
- reconfigurable hardware
- random access
- shared memory
- fault tolerance
- text classification
- peer to peer
- supervised learning
- feature selection