AccFFT: A library for distributed-memory FFT on CPU and GPU architectures.
Amir GholamiJudith HillDhairya MalhotraGeorge BirosPublished in: CoRR (2015)
Keyphrases
- distributed memory
- multithreading
- parallel implementation
- graphics processing units
- shared memory
- graphic processing unit
- heterogeneous computing
- parallel computers
- ibm sp
- parallel architectures
- parallel computing
- parallel processing
- graphics processors
- gpu implementation
- multi core processors
- parallel architecture
- multiprocessor systems
- fine grain
- data transfer
- floating point
- parallel computation
- data parallelism
- scientific computing
- frequency domain
- parallel machines
- fast fourier transform
- message passing
- general purpose
- parallel algorithm
- matrix multiplication
- memory access
- high performance computing
- memory bandwidth
- single instruction multiple data
- signal processing
- pairwise
- intel xeon
- massively parallel