AMPT-GA: automatic mixed precision floating point tuning for GPU applications.
Pradeep V. KotipalliRanvijay SinghPaul WoodIgnacio LagunaSaurabh BagchiPublished in: ICS (2019)
Keyphrases
- floating point
- graphics processing units
- genetic algorithm ga
- square root
- fixed point
- genetic algorithm
- real time
- instruction set
- parallel processing
- memory bandwidth
- sparse matrices
- graphics hardware
- interval arithmetic
- data processing
- parallel computation
- fast fourier transform
- parallel computing
- simulated annealing
- data structure