Latency-Optimized Parallelization of the FMM Near-Field Computations.

Ivo Kabadshow Bruno Lang

Published in: International Conference on Computational Science (1) (2007)

Keyphrases

matrix multiplication
parallel processing
parallel computation
shape from shading
prefetching
long range
distributed memory
data sets
low latency
response time
edge preserving
heterogeneous computing
single image
least squares
evolutionary algorithm
search algorithm
neural network