Automatic Offloading C++ Expression Templates to CUDA Enabled GPUs.

Jie Chen Bálint Joó William A. Watson III Robert Edwards

Published in: IPDPS Workshops (2012)

Keyphrases

general purpose
gpu implementation
graphics hardware
fully automatic
semi automatic
real world
computer vision
parallel processing
parallel programming
neural network
information systems
feature selection
multiscale
computationally intensive
computational power
parallel architectures