parSOM: Using Parallelism to Overcome Memory Latency in Self-Organizing Neural Networks.
Philipp TomsichAndreas RauberDieter MerklPublished in: HPCN Europe (2000)
Keyphrases
- memory bandwidth
- level parallelism
- computational power
- processing power
- memory usage
- computing power
- memory space
- parallel processing
- limited memory
- processing elements
- multithreading
- shared memory
- memory requirements
- parallel computing
- floating point
- massively parallel
- memory size
- response time
- real time
- database systems
- memory access
- parallel execution
- low latency
- main memory
- database
- associative memory