Merge branch 'main' into conda-recipe

.github/CODEOWNERS

@@ -1,14 +1,9 @@
 #python code owners
-nvjitlink/ @rapidsai/nvjitlink-python-codeowners
+pynvjitlink/ @rapidsai/pynvjitlink-write
 
 #cmake code owners
-**/CMakeLists.txt @rapidsai/nvjitlink-cmake-codeowners
-**/cmake/ @rapidsai/nvjitlink-cmake-codeowners
+**/CMakeLists.txt @rapidsai/pynvjitlink-write
+**/cmake/ @rapidsai/pynvjitlink-write
 
 #build/ops code owners
-.github/ @rapidsai/ops-codeowners 
-ci/ @rapidsai/ops-codeowners
-conda/ @rapidsai/ops-codeowners
-**/Dockerfile @rapidsai/ops-codeowners
-**/.dockerignore @rapidsai/ops-codeowners
-docker/ @rapidsai/ops-codeowners
+.github/ @rapidsai/ops-codeowners

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,6 +1,6 @@
 ---
 name: Bug report
-about: Create a bug report to help us improve nvjitlink
+about: Create a bug report to help us improve pynvjitlink
 title: "[BUG]"
 labels: "? - Needs Triage, bug"
 assignees: ''
@@ -18,9 +18,9 @@ A clear and concise description of what you expected to happen.
 
 **Environment details (please complete the following information):**
  - Environment location: [Bare-metal, Docker, Cloud(specify cloud provider)]
- - Method of nvjitlink install: [conda, Docker, or from source]
+ - Method of pynvjitlink install: [conda, Docker, or from source]
  - If method of install is [Docker], provide `docker pull` & `docker run` commands used
- 
+
 
 **Additional context**
 Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature-request.md

@@ -1,14 +1,14 @@
 ---
 name: Feature request
-about: Suggest an idea for nvjitlink
+about: Suggest an idea for pynvjitlink
 title: "[FEA]"
 labels: "? - Needs Triage, feature request"
 assignees: ''
 
 ---
 
 **Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I wish I could use nvjitlink to do [...]
+A clear and concise description of what the problem is. Ex. I wish I could use pynvjitlink to do [...]
 
 **Describe the solution you'd like**
 A clear and concise description of what you want to happen.

.github/ISSUE_TEMPLATE/submit-question.md

@@ -1,6 +1,6 @@
 ---
 name: Submit question
-about: Ask a general question about nvjitlink
+about: Ask a general question about pynvjitlink
 title: "[QST]"
 labels: "? - Needs Triage, question"
 assignees: ''

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,6 +1,6 @@
 <!--
 
-Thank you for contributing to nvjitlink :)
+Thank you for contributing to pynvjitlink :)
 
 Here are some guidelines to help the review process go smoothly.
 

.github/actions/compute-matrix/action.yaml

@@ -0,0 +1,44 @@
+name: Compute matrix
+
+outputs:
+ BUILD_MATRIX:
+ value: ${{ steps.compute-matrix.outputs.BUILD_MATRIX }}
+ TEST_MATRIX:
+ value: ${{ steps.compute-matrix.outputs.TEST_MATRIX }}
+
+runs:
+ using: composite
+ steps:
+ - name: Compute matrix
+ id: compute-matrix
+ shell: bash
+ run: |
+ set -eo pipefail
+
+ export BUILD_MATRIX="
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.9', LINUX_VER: 'centos7' }
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'centos7' }
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'centos7' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.9', LINUX_VER: 'rockylinux8' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.10', LINUX_VER: 'rockylinux8' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.11', LINUX_VER: 'rockylinux8' }
+ "
+
+ export TEST_MATRIX="
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.9', LINUX_VER: 'ubuntu18.04', gpu: 'v100', driver: 'latest' }
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.10', LINUX_VER: 'ubuntu18.04', gpu: 'v100', driver: 'latest' }
+ - { CUDA_VER: '12.0.1', ARCH: 'amd64', PY_VER: '3.11', LINUX_VER: 'ubuntu18.04', gpu: 'v100', driver: 'latest' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.9', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.10', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }
+ - { CUDA_VER: '12.0.1', ARCH: 'arm64', PY_VER: '3.11', LINUX_VER: 'ubuntu20.04', gpu: 'a100', driver: 'latest' }
+ "
+
+ echo "BUILD_MATRIX=$(
+ yq -n -o json 'env(BUILD_MATRIX)' | \
+ jq -c '.' \
+ )" | tee --append "${GITHUB_OUTPUT}"
+
+ echo "TEST_MATRIX=$(
+ yq -n -o json 'env(TEST_MATRIX)' | \
+ jq -c '.' \
+ )" | tee --append "${GITHUB_OUTPUT}"

.github/copy-pr-bot.yaml

@@ -0,0 +1,6 @@
+# Copyright (c) 2023, NVIDIA CORPORATION.
+
+# Configuration file for `copy-pr-bot` GitHub App
+# https://docs.gha-runners.nvidia.com/apps/copy-pr-bot/
+
+enabled: true

.github/workflows/build.yaml

@@ -0,0 +1,41 @@
+# Copyright (c) 2023, NVIDIA CORPORATION.
+name: build
+
+on:
+ push:
+ tags:
+ - 'v*'
+
+concurrency:
+ group: ${{ github.workflow }}-${{ github.ref }}-release
+ cancel-in-progress: true
+
+jobs:
+ compute-matrix:
+ runs-on: ubuntu-latest
+ outputs:
+ BUILD_MATRIX: ${{ steps.compute-matrix.outputs.BUILD_MATRIX }}
+ steps:
+ - uses: actions/checkout@v4
+ - name: Compute Build Matrix
+ id: compute-matrix
+ uses: ./.github/actions/compute-matrix
+ build-wheels:
+ needs:
+ - compute-matrix
+ uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.02
+ with:
+ build_type: branch
+ script: "ci/build_wheel.sh"
+ matrix_filter: ${{ needs.compute-matrix.outputs.BUILD_MATRIX }}
+ publish-wheels:
+ needs:
+ - build-wheels
+ secrets: inherit
+ uses: rapidsai/shared-workflows/.github/workflows/wheels-publish.yaml@branch-24.02
+ with:
+ build_type: ${{ inputs.build_type || 'branch' }}
+ branch: ${{ inputs.branch }}
+ sha: ${{ inputs.sha }}
+ date: ${{ inputs.date }}
+ package-name: pynvjitlink

.github/workflows/pr.yaml

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, NVIDIA CORPORATION.
+name: pr
+
+on:
+ push:
+ branches:
+ - "pull-request/[0-9]+"
+
+concurrency:
+ group: ${{ github.workflow }}-${{ github.ref }}-${{ github.event_name }}
+ cancel-in-progress: true
+
+jobs:
+ pr-builder:
+ needs:
+ - checks
+ - compute-matrix
+ - build-wheels
+ - test-wheels
+ secrets: inherit
+ uses: rapidsai/shared-workflows/.github/workflows/pr-builder.yaml@branch-24.02
+ checks:
+ secrets: inherit
+ uses: rapidsai/shared-workflows/.github/workflows/checks.yaml@branch-24.02
+ with:
+ enable_check_generated_files: false
+ compute-matrix:
+ runs-on: ubuntu-latest
+ outputs:
+ BUILD_MATRIX: ${{ steps.compute-matrix.outputs.BUILD_MATRIX }}
+ TEST_MATRIX: ${{ steps.compute-matrix.outputs.TEST_MATRIX }}
+ steps:
+ - uses: actions/checkout@v4
+ - name: Compute Build Matrix
+ id: compute-matrix
+ uses: ./.github/actions/compute-matrix
+ build-wheels:
+ needs:
+ - compute-matrix
+ uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.02
+ with:
+ build_type: pull-request
+ script: "ci/build_wheel.sh"
+ matrix_filter: ${{ needs.compute-matrix.outputs.BUILD_MATRIX }}
+ test-wheels:
+ needs:
+ - build-wheels
+ - compute-matrix
+ uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.02
+ with:
+ build_type: pull-request
+ script: "ci/test_wheel.sh"
+ matrix_filter: ${{ needs.compute-matrix.outputs.TEST_MATRIX }}

.gitignore

@@ -3,3 +3,7 @@ build
 *.so
 *.egg-info
 .*.swp
+
+# compiled test files
+pynvjitlink/tests/test_device_functions.*
+pynvjitlink/tests/undefined_extern.cubin

.pre-commit-config.yaml

@@ -1,9 +1,15 @@
 repos:
-- repo: https://github.com/PyCQA/flake8
- rev: 3.7.8
- hooks:
- - id: flake8
-- repo: https://github.com/pre-commit/mirrors-clang-format
- rev: v11.1.0
- hooks:
- - id: clang-format
+ - repo: https://github.com/pre-commit/pre-commit-hooks
+ rev: v4.5.0
+ hooks:
+ - id: trailing-whitespace
+ - id: end-of-file-fixer
+ - repo: https://github.com/pre-commit/mirrors-clang-format
+ rev: v16.0.6
+ hooks:
+ - id: clang-format
+ - repo: https://github.com/astral-sh/ruff-pre-commit
+ rev: v0.1.6
+ hooks:
+ - id: ruff
+ - id: ruff-format

.ycm_extra_conf.py

@@ -3,28 +3,28 @@
 
 from pathlib import Path
 
-CONDA_PREFIX = os.environ['CONDA_PREFIX']
+CONDA_PREFIX = os.environ["CONDA_PREFIX"]
 NVJITLINK_DIR = Path(__file__).parent
 VER = sys.version_info
-PYTHON_INCLUDE_NAME = 'python3.10' # Not ideal
+PYTHON_INCLUDE_NAME = "python3.10" # Not ideal
 
-CONDA_INCLUDE_DIR = Path(CONDA_PREFIX, 'include')
+CONDA_INCLUDE_DIR = Path(CONDA_PREFIX, "include")
 PYTHON_INCLUDE_DIR = Path(CONDA_INCLUDE_DIR, PYTHON_INCLUDE_NAME)
-NVJITLINK_INCLUDE_DIR = Path(NVJITLINK_DIR, 'include')
-CUDA_INCLUDE_DIR = '/usr/local/cuda-12.0/include'
+NVJITLINK_INCLUDE_DIR = Path(NVJITLINK_DIR, "include")
+CUDA_INCLUDE_DIR = "/usr/local/cuda-12.0/include"
 
 flags = [
- '--cuda-gpu-arch=sm_50',
- f'-I{CONDA_INCLUDE_DIR}',
- f'-I{CUDA_INCLUDE_DIR}',
- f'-I{NVJITLINK_INCLUDE_DIR}',
- f'-I{PYTHON_INCLUDE_DIR}',
+ "--cuda-gpu-arch=sm_50",
+ f"-I{CONDA_INCLUDE_DIR}",
+ f"-I{CUDA_INCLUDE_DIR}",
+ f"-I{NVJITLINK_INCLUDE_DIR}",
+ f"-I{PYTHON_INCLUDE_DIR}",
 ]
 
 
 def Settings(**kwargs):
- return {'flags': flags}
+ return {"flags": flags}
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
  print(Settings())

CHANGELOG.md

@@ -1,4 +1,4 @@
-# nvjitlink 0.0.0 (DD Mon YYYY)
+# pynvjitlink 0.0.0 (DD Mon YYYY)
 
 ## New Features
 

CMakeLists.txt

@@ -1,24 +1,22 @@
 cmake_minimum_required(VERSION 3.26.4 FATAL_ERROR)
 
 project(
- nvjitlink
- VERSION 0.1.0
- LANGUAGES CXX
+ pynvjitlink
+ VERSION 0.1.6
+ LANGUAGES CXX CUDA
 )
 
 find_package(Python COMPONENTS Interpreter Development REQUIRED)
 
-Python_add_library(_nvjitlinklib MODULE nvjitlink/_nvjitlinklib.cpp WITH_SOABI)
+Python_add_library(_nvjitlinklib MODULE pynvjitlink/_nvjitlinklib.cpp WITH_SOABI)
 
 find_package(
- CUDAToolkit 12.0 REQUIRED
+ CUDAToolkit 12.3 REQUIRED
 )
 target_link_libraries(_nvjitlinklib PRIVATE CUDA::nvJitLink_static CUDA::nvptxcompiler_static)
 
-set(opt_option -O0)
-if(WIN32)
- set(opt_option -/Od)
-endif()
-target_compile_options(_nvjitlinklib PRIVATE -Werror -Wall ${opt_option})
+target_compile_options(_nvjitlinklib PRIVATE -Werror -Wall)
 
-install(TARGETS _nvjitlinklib LIBRARY DESTINATION nvjitlink)
+target_compile_features(_nvjitlinklib PRIVATE cxx_std_11)
+
+install(TARGETS _nvjitlinklib LIBRARY DESTINATION pynvjitlink)

README.md

@@ -1,25 +1,26 @@
-# <div align="left"><img src="https://rapids.ai/assets/images/rapids_logo.png" width="90px"/>&nbsp;nvjitlink</div>
+# <div align="left"><img src="https://rapids.ai/assets/images/rapids_logo.png" width="90px"/>&nbsp;pynvjitlink</div>
 
-The [RAPIDS](https://rapids.ai) nvjitlink library provides a Python binding for the 
+The [RAPIDS](https://rapids.ai) pynvjitlink library provides a Python binding for the
 [nvJitLink library](https://docs.nvidia.com/cuda/nvJitLink/index.html). It is presently a
 work-in-progress.
 
-**NOTE:** For the latest stable [README.md](https://github.com/rapidsai/nvjitlink/blob/main/README.md) ensure you are on the `main` branch.
+**NOTE:** For the latest stable [README.md](https://github.com/rapidsai/pynvjitlink/blob/main/README.md) ensure you are on the `main` branch.
 
 ## Quick Start
 TODO
 
-## Install nvjitlink
+## Install pynvjitlink
+
 Install with either:
 
-```
-python setup.py develop
+```shell
+python -m pip install -e .
 ```
 
 or
 
-```
-python setup.py install
+```shell
+python -m pip install .
 ```
 
 ### Conda
@@ -30,4 +31,4 @@ TODO
 
 ## Contributing Guide
 
-Review the [CONTRIBUTING.md](https://github.com/rapidsai/nvjitlink/blob/main/CONTRIBUTING.md) file for information on how to contribute code and issues to the project.
+Review the [CONTRIBUTING.md](https://github.com/rapidsai/pynvjitlink/blob/main/CONTRIBUTING.md) file for information on how to contribute code and issues to the project.

ci/build_wheel.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+# Copyright (c) 2023-2024, NVIDIA CORPORATION
+
+set -euo pipefail
+
+rapids-logger "Install CUDA Toolkit"
+source "$(dirname "$0")/install_latest_cuda_toolkit.sh"
+
+rapids-logger "Build wheel"
+mkdir -p ./wheel-build
+pip wheel . --wheel-dir=./wheel-build -vvv
+
+rapids-logger "Upload Wheel"
+RAPIDS_PY_WHEEL_NAME="pynvjitlink-cu12" rapids-upload-wheels-to-s3 ./wheel-build

ci/check_style.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+# Copyright (c) 2023, NVIDIA CORPORATION
+
+set -euo pipefail
+
+pip install pre-commit
+
+# Run pre-commit checks
+pre-commit run --all-files --show-diff-on-failure