Performance Traps in OpenCL for CPUs.
Jie ShenJianbin FangHenk J. SipsAna Lucia VarbanescuPublished in: PDP (2013)
Keyphrases
- graphics processing units
- general purpose
- parallel processing
- parallel computation
- parallel computing
- parallel implementation
- parallel programming
- shared memory
- parallel algorithm
- efficient implementation
- processing units
- graphics processors
- commodity hardware
- floating point
- memory access
- parallel architectures
- multi core systems
- database
- massively parallel
- computing systems
- databases
- real time
- artificial neural networks
- bayesian networks
- image sequences
- information retrieval