Experimental Study of Six Different Implementations of Parallel Matrix Multiplication on Heterogeneous Computational Clusters of Multicore Processors.
Pedro AlonsoRavi ReddyAlexey L. LastovetskyPublished in: PDP (2010)
Keyphrases
- experimental study
- matrix multiplication
- multicore processors
- distributed memory
- shared memory
- computing power
- parallel architectures
- parallel programming
- message passing
- operating system
- parallel computers
- highly parallel
- parallel algorithm
- computational power
- parallel processing
- synthetic datasets
- matrix factorization
- parallel implementation
- parallel computing
- high end
- parallel computation
- computing systems
- experimental evaluation
- efficient implementation
- real time
- low power
- single chip
- multi view
- image processing