An efficient tensor transpose algorithm for multicore CPU, Intel Xeon Phi, and NVidia Tesla GPU.

Dmitry I. Lyakh

Published in: Comput. Phys. Commun. (2015)

Keyphrases

graphics processing units
times faster
gpu implementation
parallel implementation
learning algorithm
detection algorithm
computational complexity
k means
np hard
real time
optimal solution
dynamic programming
expectation maximization
high order