Investigation of heterogeneous platform for deep learning
Maxeller dataflow platform
We are be investigating a heterogeneous investigating applicability of Maxeller's data flow 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.machine learning applications.
Work in progress
Week of September 4th
- Go over UG1023 and UG1021 tutorials
- Running tools on iridium:
- sdx &
- make sure your workspace is in /home/NetID/project/workspace
- sdx &
Week of September 11th
- TBD
Documentation
xilinxproducts/design-tools/software-zone/sdaccel.html#documentationTutorials: httpsxilinxWork in progress
Week of September 4th
- Get tools, setup development workstation
Week of September 11th
- TBD
Documentation
html_docs/xilinx2017_2/sdaccel_doc/index.html
- UG1023 - SDAccel Environment User Guide (ver2017.2)
- UG1021 - SDAccel Environment Tutorial: Introduction (ver2017.2)
Development documenttion
- UG1207 - SDAccel Environment Optimization Guide (ver2017.2)
- UG1253 - SDx Pragma Reference Guide ( ver2017.2)
Hardware-related