d2o: a distributed data object for parallel high-performance computing in Python.
Theo SteiningerMaksim GreinerFrederik BeaujeanTorsten A. EnßlinPublished in: J. Big Data (2016)
Keyphrases
- distributed data
- high performance computing
- massively parallel
- parallel computing
- message passing interface
- scientific computing
- data sharing
- computational science
- file system
- computing systems
- data distribution
- communication cost
- computing resources
- shared memory
- data mining algorithms
- grid computing
- fault tolerance
- energy efficiency
- distributed memory
- computing environments
- data objects
- load balancing
- parallel implementation
- fine grained
- multi dimensional
- parallel machines
- case study
- data mining
- databases
- data sets
- database