Skip to content

Commit

Permalink
add docs
Browse files Browse the repository at this point in the history
  • Loading branch information
cathalmccabe authored and skalade committed Dec 15, 2023
1 parent dc3f312 commit 5e5e519
Show file tree
Hide file tree
Showing 483 changed files with 702,187 additions and 343 deletions.
54 changes: 22 additions & 32 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,53 +1,43 @@
# Riallto
# Riallto documentation

Riallto is an open source project that aims to bridge the gap between newcomers and performance ninjas in AMD's latest AI Engine technology. If you have a machine with an AMD processor with Ryzen AI, you have access to an NPU (Neural Processing Unit), a dedicated neural network accelerator.
This branch contains source and the build for the Riallto documentation.

The educational examples and software in this repository will enable you to interact with the NPU and learn how to write custom applications with this novel accelerator.
Docs are built offline on a Ryzen AI laptop. Generated html docs can be found in the ./docs folder on this branch.

Note that NPUs can also be referred to as Inference Processing Units, or IPUs. You may see the NPU referred to as an "IPU" in some Ryzen AI documentation. Once the Ryzen AI driver is installed on your computer, you will see a device named "IPU" in the Windows Device Manager."
To rebuild, pull the main branch, copy the source dir, and make.bat to the docs folder in the main main repo.

## Quick Start

The Riallto installer is separated into 'Lite' and 'Full' installation versions. The 'Lite' version has all the essential packages required for the Riallto and ONNX runtimes on the NPU to get started with prebuilt vision applications. The 'Full' version enables developers to write their own custom applications, which requires additional tools.

The steps below will allow you to get quickly started using the 'Lite' version of Riallto. For details on requirements and installation for the 'Full' version, follow the instructions in the [Install Riallto](https://riallto.ai/install-riallto.html) guide.

* [Download and unzip the the v10.1109.8.100 IPU driver](https://account.amd.com/en/forms/downloads/ryzen-ai-software-platform-xef.html?filename=ipu_stack_rel_silicon_1.0.zip). You will need to create an AMD account if you do not have one.
* Open a Windows Command Prompt, or Powershell, as administrator.
* Change directory to the unzipped IPU driver directory, then run the `amd_install_kipudrv.bat` file. Press Enter if prompted.
* Confirm the IPU driver has installed correctly by running the following command in a Powershell terminal and checking the output matches that of the figure below:
In the Riallto venv run:

```
(Get-WmiObject -Class Win32_PnPSignedDriver | Where-Object { $_.DeviceName -eq "AMD IPU Device" }).DriverVersion
.\make.bat html
```

![IPU driver dialog](docs/images/ipu_driver.png)
Copy contents of build/html to he docs folder

* [Download and unzip the Riallto installer]().
* Navigate to the `installer.exe` using the File Explorer and run as administrator, making sure the 'Lite' install option is selected when prompted, as shown in the figure below.
## Prerequisites for the venv

![Riallto installer options](docs/images/installer.png)
Install Sphinx on Windows, then in the venv:

Once the installation process has finished a Jupyter Lab session will open in your web browser, allowing you to start running the Riallto notebooks immediately. The notebooks can be opened by selecting them from the file browser pane on the left hand side of the Jupyter Lab session.

The installer places a shortcut on the desktop, which allows you to launch Riallto anytime after the installation process.
```
pip install recommonmark
pip install sphinx_markdown_tables
pip install nbsphinx
pip install nbsphinx-link
pip install pandoc
pip install sphinx_copybutton
```

Note that the notebooks from sections 1, 2, 3, and 5 can be run using the 'Lite' install option. A 'Full' install is required to run the notebooks from section 4. See instructions in the [Install Riallto](https://riallto.ai/install-riallto.html) guide for more details.
## Steps to reproduce webpages from scratch:

## Contribute
* In the docs directory; run: sphinx-quickstart to setup the Sphinx config (version number can be set here)
* Copy the conf.py settings from this directory (edit as required)
* Run sphinx-apidoc -o source/ ./ipu to auto generate the tempaltes for the source code
* Edit the index.rst to change the homapage and to include/exclude notebook/rst files.

Contributions to this repository are welcome. Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for how to improve Riallto.

## Support

For support, feel free to ask questions on the [GitHub discussions page](https://github.com/AMDResearch/Riallto/discussions).

## Licenses

[MIT License](LICENSE)

## Open Source Components

**License and Copyrights Info** [TAR/GZIP](https://www.xilinx.com/bin/public/openDownload?filename=riallto-v1.0-licenses.tar.gz)

**Open Components Source Code** [TAR/GZIP](https://www.xilinx.com/bin/public/openDownload?filename=riallto-v1.0-open_components.tar.gz)
4 changes: 4 additions & 0 deletions docs/.buildinfo
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: efd3fe0cf256529adfb168111be94282
tags: 645f666f9bcd5a90fca523b33c5a78b7
Empty file added docs/.nojekyll
Empty file.
Loading

0 comments on commit 5e5e519

Please sign in to comment.