Multiplicação de matrizes: uma comparação entre as abordagens sequencial (CPU) e paralela (GPU).
André G. C. PachecoPublished in: CoRR (2019)
Keyphrases
- graphics processing units
- graphics processors
- gpu implementation
- heterogeneous computing
- general purpose
- real time
- graphics hardware
- parallel processing
- parallel implementation
- compute unified device architecture
- floating point
- efficient implementation
- parallel computing
- parallel computation
- intel xeon
- gpu accelerated
- parallel programming
- data transfer
- memory bandwidth
- cpu implementation
- multithreading
- massively parallel
- computing systems
- processing units
- personal computer
- parallel algorithm
- information systems
- neural network