[FEA]: Introduce Python module with CCCL headers

python/cuda_cccl/.gitignore

@@ -0,0 +1,2 @@
+cuda/_include
+*egg-info

python/cuda_cccl/README.md

@@ -0,0 +1,11 @@
+# `cuda.cccl`: Experimental CUDA Core Compute Library Python module with CCCL headers
+
+## Documentation
+
+Please visit the documentation here: https://nvidia.github.io/cccl/python.html.
+
+## Local development
+
+```bash
+pip3 install .
+```

python/cuda_cccl/pyproject.toml

@@ -0,0 +1,7 @@
+# Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
+#
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+[build-system]
+requires = ["packaging", "setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"

python/cuda_cccl/setup.py

@@ -0,0 +1,75 @@
+# Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. ALL RIGHTS RESERVED.
+#
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+import os
+import shutil
+
+from setuptools import Command, setup, find_namespace_packages
+from setuptools.command.build_py import build_py
+from wheel.bdist_wheel import bdist_wheel
+
+
+project_path = os.path.abspath(os.path.dirname(__file__))
+cccl_path = os.path.abspath(os.path.join(project_path, "..", ".."))
+cccl_headers = [["cub", "cub"], ["libcudacxx", "include"], ["thrust", "thrust"]]
+ver = "0.1.2.8.0"
+
+
+with open("README.md") as f:
+    long_description = f.read()
+
+
+class CustomBuildCommand(build_py):
+    def run(self):
+        self.run_command("package_cccl")
+        build_py.run(self)
+
+
+class CustomWheelBuild(bdist_wheel):
+    def run(self):
+        self.run_command("package_cccl")
+        super().run()
+
+
+class PackageCCCLCommand(Command):
+    description = "Generate additional files"
+    user_options = []
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        for proj_dir, header_dir in cccl_headers:
+            src_path = os.path.abspath(os.path.join(cccl_path, proj_dir, header_dir))
+            dst_path = os.path.join(project_path, "cuda", "_include", proj_dir)
+            if os.path.exists(dst_path):
+                shutil.rmtree(dst_path)
+            shutil.copytree(src_path, dst_path)
+
+
+setup(
+    name="cuda-cccl",
+    version=ver,
+    description="Experimental Package with CCCL headers to support JIT compilation",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    author="NVIDIA Corporation",
+    classifiers=[
+        "Programming Language :: Python :: 3 :: Only",
+        "Environment :: GPU :: NVIDIA CUDA",
+    ],
+    packages=find_namespace_packages(include=["cuda.*"]),
+    python_requires=">=3.9",
+    cmdclass={
+        "package_cccl": PackageCCCLCommand,
+        "build_py": CustomBuildCommand,
+        "bdist_wheel": CustomWheelBuild,
+    },
+    include_package_data=True,
+    license="Apache-2.0 with LLVM exception",
+    license_files=("../../LICENSE",),
+)

python/cuda_cooperative/.gitignore

@@ -1,3 +1,2 @@
-cuda/_include
 env
 *egg-info

python/cuda_cooperative/README.md

@@ -6,7 +6,16 @@ Please visit the documentation here: https://nvidia.github.io/cccl/python.html.
 
 ## Local development
 
+First-time installation:
+
+```bash
+pip3 install ./cuda_cccl
+pip3 install ./cuda_cooperative[test]
+pytest -v ./cuda_cooperative/tests/
+```
+
+For faster iterative development:
+
 ```bash
-pip3 install -e .[test]
-pytest -v ./tests/
+pip3 install -e ./cuda_cooperative[test]
 ```

python/cuda_cooperative/setup.py

@@ -3,9 +3,8 @@
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 import os
-import shutil
 
-from setuptools import Command, setup, find_namespace_packages
+from setuptools import setup, find_namespace_packages
 from setuptools.command.build_py import build_py
 from wheel.bdist_wheel import bdist_wheel
 
@@ -27,35 +26,14 @@
 
 class CustomBuildCommand(build_py):
     def run(self):
-        self.run_command("package_cccl")
         build_py.run(self)
 
 
 class CustomWheelBuild(bdist_wheel):
     def run(self):
-        self.run_command("package_cccl")
         super().run()
 
 
-class PackageCCCLCommand(Command):
-    description = "Generate additional files"
-    user_options = []
-
-    def initialize_options(self):
-        pass
-
-    def finalize_options(self):
-        pass
-
-    def run(self):
-        for proj_dir, header_dir in cccl_headers:
-            src_path = os.path.abspath(os.path.join(cccl_path, proj_dir, header_dir))
-            dst_path = os.path.join(project_path, "cuda", "_include", proj_dir)
-            if os.path.exists(dst_path):
-                shutil.rmtree(dst_path)
-            shutil.copytree(src_path, dst_path)
-
-
 setup(
     name="cuda-cooperative",
     version=ver,
@@ -70,6 +48,7 @@ def run(self):
     packages=find_namespace_packages(include=["cuda.*"]),
     python_requires=">=3.9",
     install_requires=[
+        "cuda-cccl",
         "numba>=0.60.0",
         "pynvjitlink-cu12>=0.2.4",
         "cuda-python",
@@ -82,7 +61,6 @@ def run(self):
         ]
     },
     cmdclass={
-        "package_cccl": PackageCCCLCommand,
         "build_py": CustomBuildCommand,
         "bdist_wheel": CustomWheelBuild,
     },

python/cuda_parallel/.gitignore

@@ -1,4 +1,3 @@
-cuda/_include
 env
 *egg-info
 *so

python/cuda_parallel/README.md

@@ -6,7 +6,16 @@ Please visit the documentation here: https://nvidia.github.io/cccl/python.html.
 
 ## Local development
 
+First-time installation:
+
+```bash
+pip3 install ./cuda_cccl
+pip3 install ./cuda_parallel[test]
+pytest -v ./cuda_parallel/tests/
+```
+
+For faster iterative development:
+
 ```bash
-pip3 install -e .[test]
-pytest -v ./tests/
+pip3 install -e ./cuda_parallel[test]
 ```

python/cuda_parallel/setup.py

@@ -3,10 +3,9 @@
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 import os
-import shutil
 import subprocess
 
-from setuptools import Command, Extension, setup, find_namespace_packages
+from setuptools import Extension, setup, find_namespace_packages
 from setuptools.command.build_py import build_py
 from setuptools.command.build_ext import build_ext
 from wheel.bdist_wheel import bdist_wheel
@@ -29,36 +28,14 @@
 
 class CustomBuildCommand(build_py):
     def run(self):
-        self.run_command("package_cccl")
         build_py.run(self)
 
 
 class CustomWheelBuild(bdist_wheel):
     def run(self):
-        self.run_command("package_cccl")
         super().run()
 
 
-class PackageCCCLCommand(Command):
-    description = "Generate additional files"
-    user_options = []
-
-    def initialize_options(self):
-        pass
-
-    def finalize_options(self):
-        pass
-
-    def run(self):
-        for proj_dir, header_dir in cccl_headers:
-            src_path = os.path.abspath(os.path.join(cccl_path, proj_dir, header_dir))
-            # TODO Extract cccl headers into a standalone package
-            dst_path = os.path.join(project_path, "cuda", "_include", proj_dir)
-            if os.path.exists(dst_path):
-                shutil.rmtree(dst_path)
-            shutil.copytree(src_path, dst_path)
-
-
 class CMakeExtension(Extension):
     def __init__(self, name):
         super().__init__(name, sources=[])
@@ -100,7 +77,12 @@ def build_extension(self, ext):
     ],
     packages=find_namespace_packages(include=["cuda.*"]),
     python_requires=">=3.9",
-    install_requires=["numba>=0.60.0", "cuda-python", "jinja2"],
+    install_requires=[
+        "cuda-cccl",
+        "numba>=0.60.0",
+        "cuda-python",
+        "jinja2",
+    ],
     extras_require={
         "test": [
             "pytest",
@@ -109,7 +91,6 @@ def build_extension(self, ext):
         ]
     },
     cmdclass={
-        "package_cccl": PackageCCCLCommand,
         "build_py": CustomBuildCommand,
         "bdist_wheel": CustomWheelBuild,
         "build_ext": BuildCMakeExtension,