This wiki site will be offline Thursday, Oct 5th, 2023, from 0600 to 0830 in order to upgrade Confluence
Child pages
  • JLESC: Collaboration with RIKEN

Versions Compared


  • This line was added.
  • This line was removed.
  • Formatting was changed.

Investigation of heterogeneous platform for deep learning

We are be investigating a heterogeneous platform for deep learning in which GPUs are applied for training and FPGAs are initially used for inference, and later on will be adapted for training with customizable data types. Ultimately, we will be looking at how to utilize both GPUs and FPGAs for training and inference in a tightly coupled system.


Yiyu Tan, RIKEN AICS, research scientist

Volodymyr Kindratenko, NCSA, senior research scientist

  • Janish Yerra, ECE, undergraduate student

Work in progress

Week of September 4th

  • Go over UG1023 and UG1021 tutorials
  • Running tools on iridium:

    Code Block
    sdx &
  • Copy examples to your own space:

    Code Block
    cd ~/project
    cp -r /opt/Xilinx/SDx/2017.1/samples .
    cp -r /opt/Xilinx/SDx/2017.1/examples .

Week of September 11th

  • Continue with UG1023 and UG1021 tutorials