Processor affinity and MPI performance on SMP-CMP clusters.
Chi ZhangXin YuanAshok SrinivasanPublished in: IPDPS Workshops (2010)
Keyphrases
- shared memory
- distributed memory
- parallel algorithm
- parallel architectures
- parallel computing
- message passing interface
- massively parallel
- parallel architecture
- affinity measure
- computer architecture
- parallel computers
- clustering algorithm
- multithreading
- cluster analysis
- message passing
- general purpose
- parallel processing
- high speed
- high performance computing
- parallel programming
- overlapping clusters
- single chip
- neural network
- parallelization strategy
- fuzzy clustering
- hierarchical clustering
- data clustering
- document clustering
- fine grained
- parallel implementation
- memory management
- multi core processors
- hierarchical structure
- operating system
- data points