Superlinear Speedup for Matrix Multiplication in GPU Devices.
Leonid DjinevskiSasko RistovMarjan GusevPublished in: ICT Innovations (2012)
Keyphrases
- matrix multiplication
- distributed memory
- message passing
- parallel implementation
- real time
- mobile devices
- orders of magnitude
- graphics hardware
- cpu implementation
- graphics processors
- parallel processing
- parallel computation
- graphics processing units
- gpu implementation
- general purpose
- dynamic programming
- image processing