How to obtain efficient GPU kernels: An illustration using FMM & FGT algorithms.
Felipe A. CruzSimon K. LaytonLorena A. BarbaPublished in: Comput. Phys. Commun. (2011)
Keyphrases
- parallel architectures
- computationally efficient
- learning algorithm
- computationally expensive
- real time
- efficient solutions
- significant improvement
- orders of magnitude
- data mining
- algorithmic solutions
- highly efficient
- efficient implementation
- benchmark datasets
- theoretical analysis
- optimization problems
- computational complexity
- data structure
- data mining techniques
- general purpose
- computational cost
- massively parallel
- graphics hardware
- graphics processors
- machine learning
- computationally complex
- computation intensive