SpongeFiles: mitigating data skew in mapreduce using distributed memory.
Khaled ElmeleegyChristopher OlstonBenjamin ReedPublished in: SIGMOD Conference (2014)
Keyphrases
- data skew
- parallel processing
- ibm sp
- distributed memory
- data parallelism
- data distribution
- data partitioning
- load balancing
- shared memory
- sort merge
- parallel programming
- parallel computers
- parallel implementation
- join algorithms
- parallel computing
- single processor
- cloud computing
- multi processor
- skewed data
- join operations
- multi dimensional
- distributed computing