Designing and optimizing compute kernels on NVIDIA GPUs

@article{Jamsek2009DesigningAO,
  title={Designing and optimizing compute kernels on NVIDIA GPUs},
  author={Damir A. Jamsek},
  journal={2009 Asia and South Pacific Design Automation Conference},
  year={2009},
  pages={224-229}
}
  • Damir A. Jamsek
  • Published 2009 in
    2009 Asia and South Pacific Design Automation…
The availability of high performance compute capability in NVIDIA GPUs has expanded their use in CAD environments. We will describe the basic compute models including host/device programming models, device multi-thread programming models, as well optimization and performance tuning techniques.