Hybrid CPU/GPU clustering in shared memory on the billion point scale.
Michael GowanlockPublished in: ICS (2019)
Keyphrases
- shared memory
- compute unified device architecture
- graphic processing unit
- parallel computing
- parallel programming
- graphics processing units
- multithreading
- message passing
- parallel computation
- parallel algorithm
- parallel tree search
- gpu implementation
- memory access
- multi processor
- parallel architecture
- distributed memory
- parallel computers
- parallel architectures
- parallel machines
- graphics processors
- parallel execution
- massively parallel
- commodity hardware
- parallel processing
- address space
- high quality
- data partitioning
- heterogeneous platforms
- multi core processors
- high performance computing
- distributed systems
- probabilistic model
- bayesian networks