Performance tuning and sparse traversal technique for a cell-based fetch length algorithm on a GPU.
Mika MurtojärviOlli S. NevalainenVille LeppänenPublished in: Concurr. Comput. Pract. Exp. (2015)
Keyphrases
- dynamic programming
- significant improvement
- high accuracy
- worst case
- times faster
- optimal solution
- matching algorithm
- detection algorithm
- optimization algorithm
- k means
- recognition algorithm
- computational cost
- general purpose
- experimental evaluation
- segmentation algorithm
- input data
- cost function
- preprocessing
- computational complexity
- data structure
- gpu accelerated
- parallel implementation
- convergence rate
- ray casting
- real time
- particle swarm optimization
- linear programming
- search space
- high dimensional
- learning algorithm