aidge-backend-cuda 0.9.0

Core algorithms for operators and graph of the AIDGE framework

Aidge CUDA library

You can find in this folder the library that implements the CUDA operators.

[TOC]

Quick Start

ℹ️ First, make sure to go through installation instructions required for every module.

Dependencies

Make sure to install the following tools:

• CUDA ToolKit 12.6
  • 12.4.1 is the strict minimum, but 12.6+ is recommended.
• CUDnn9
  • make sure to install the CUDA 12 compatible version

[!TIP] On Windows at least, CUDnn9 headers and libraries needs to be findable. One way is to add files from CUDnn to CUDA in their respective bin/, lib/ and include/. Or you could add these folders to your path.

Aidge dependencies

• aidge_core
• aidge_backend_cpu
  • Only needed for tests.

# On Windows, from aidge/
# ----------[ C++ development]----------
setup.ps1 -Modules core, backend_cpu -Clean -Tests

# ----------[ Python development]----------
setup.ps1 -Modules core, backend_cpu -Clean -Tests -Python

# On Unix, from aidge/
# ----------[ C++ development]----------
./setup.sh -m core -m backend_cpu --clean --tests

# ----------[ Python development]----------
./setup.sh -m core -mbackend_cpu --clean --tests --python

Using setup.ps1

[!NOTE] Windows only* *Unless you installed powershell on your system

# ----------[ C++ development]----------
# From aidge/
setup.ps1 -Modules backend_cuda -Clean -Tests

# ----------[ Python development]----------
# From aidge/
setup.ps1 -Modules backend_cuda -Clean -Tests -Python

[!TIP] Run Get-Help setup.ps1 --Full to display documentation

Using setup.sh

[!NOTE] Unix only*

# ----------[ C++ development]----------
# From aidge/
./setup.sh -m backend_cuda --clean --tests

# ----------[ Python development]----------
# From aidge/
./setup.sh -m backend_cuda --clean --tests --python

[!TIP] Run setup.sh -h to display documentation

Using pip

[!NOTE] If using virtual environment, make sure to use the same for every installation !

# ----------[ Python development]----------
# only in aidge/aidge/aidge_backend_cuda/
pip install . -v

# If you want to install test, do this instead
pip install .[test] -v

# Launch tests using pytest
pytest

[!TIP] -v is to enable verbose mode !

Development mode install

[!WARNING] Experimental Untested & experimental feature, see https://scikit-build-core.readthedocs.io/en/latest/configuration/index.html#editable-installs.

pip install --no-build-isolation --config-settings=editable.rebuild=true -Cbuild-dir=build -ve.

Using CMake

[!NOTE] Only for C++ development Don't use this method, if you wish to create a pip package Use pip instead.

A CMakePreset.json is available.

# Configure
cmake --preset clang-debug
# Build
cmake --build --preset clang-debug
# Install
cmake --install
# Test
ctest --test-dir build/

Feel free to create your own presets in CMakeUsersPresets.json by inheriting the ones available in CMakePresets.json.