Efficient and accurate Word2Vec implementations in GPU and shared-memory multicore architectures.
Trevor M. SimontonGita AlaghbandPublished in: HPEC (2017)
Keyphrases
- shared memory
- parallel architectures
- parallel computing
- parallel programming
- parallel algorithm
- parallel computation
- low overhead
- message passing
- distributed memory
- parallel execution
- parallel computers
- multi processor
- single processor
- graphics processors
- multi core processors
- parallel processing
- graphic processing unit
- compute unified device architecture
- parallel architecture
- efficient implementation
- multithreading
- graphics processing units
- massively parallel
- commodity hardware
- multi core systems
- heterogeneous platforms
- real time
- high end
- probabilistic model
- database systems