Communication-Computation Overlapping with Dynamic Loop Scheduling for Preconditioned Parallel Iterative Solvers on Multicore and Manycore Clusters.
Kengo NakajimaToshihiro HanawaPublished in: ICPP Workshops (2017)
Keyphrases
- parallel computation
- iterative methods
- graphics processing units
- scheduling problem
- shared memory
- parallel machines
- clustering algorithm
- real time
- parallel implementation
- dynamic environments
- parallel programming
- interconnection networks
- communication systems
- parallel computing
- feedback loop
- computer systems
- parallel architectures
- identical machines
- parallel computers
- wireless sensor networks
- hierarchical clustering
- scheduling algorithm
- level parallelism
- multiprocessor systems
- parallel processing
- flow control
- parallel processors
- arbitrary shape
- fuzzy clustering