The NengoOCL team is jazzed to announce the release of NengoOCL 2.0.0.
What is NengoOCL?
NengoOCL (formerly known as Nengo OpenCL) is a backend for Nengo that uses the OpenCL framework to run large-scale neural models on CPUs, GPUs, and other OpenCL-capable platforms. Using the OpenCL backend can be orders of magnitude faster than the reference backend for large models.
How do I use it?
To use NengoOCL, replace instances of nengo.Simulator
with nengo_ocl.Simulator
.
For example, if you have a network called model
and you run it with
with nengo.Simulator(model) as sim:
sim.run(10)
you would change that to
with nengo_ocl.Simulator(model) as sim:
sim.run(10)
and that’s it!
What’s new?
NengoOCL 2.0.0 is primarily a compatibility release, adding compatibility for Nengo 3.0.0.
This version of NengoOCL adds support for the new nengo.Convolution
and nengo.Sparse
transform types. This replaces the previous support for the NengoExtras processes Conv2d
and Pool2d
, which are no longer supported.
The documentation for NengoOCL is now available online. To see the full list of changes in version 2.0.0, head to the Github release page.
The NengoOCL project now lives at https://github.com/nengo-labs/nengo-ocl. While NengoOCL is still stable and well-tested software, the nengo-labs
designation indicates that this project is less actively maintained by ABR than those in the nengo
organization. Community contributions are still welcome, and we will do our best to review and merge contributions in a timely manner. Special thanks to Alex Tait, whose contributions motivated this release and made it considerably better!
How do I get it?
Installing NengoOCL is more difficult than other parts of the Nengo ecosystem since OpenCL must be properly installed first. See our notes on installing OpenCL for assistance.
Once OpenCL is installed, use pip
.
pip install --upgrade nengo-ocl
If something goes wrong during the installation, which can happen due to differing OpenCL installs, refer to our installation notes for assistance.
Where can I learn more?
Where can I get help?
You’re already there! If you have an issue upgrading or have any other questions, please post them in this forum.