Parallel external sorting for CUDA-enabled GPUs with load balancing and low transfer overhead.
Hagen PetersOle Schulz-HildebrandtNorbert LuttenbergerPublished in: IPDPS Workshops (2010)
Keyphrases
- load balancing
- parallel programming
- dynamic load balancing
- low overhead
- parallel query processing
- load balancing strategy
- load balance
- shared memory
- parallel database systems
- parallel implementation
- parallel algorithm
- general purpose
- graphics processing units
- inter processor communication
- parallel processing
- parallel computing
- data skew
- gpu implementation
- parallel computation
- distributed systems
- fault tolerant
- compute unified device architecture
- fault tolerance
- grid computing
- load balancing strategies
- pc cluster
- peer to peer
- mobile agents
- parallel architectures
- graphics processors
- round robin
- resource utilization
- distributed memory
- data replication
- load distribution
- cloud computing
- multi agent systems
- proxy servers
- high reliability