Merge branch 'main' into ksimpson/add_program_options

Author: keenan-simpson

.github/workflows/build-and-test.yml

@@ -76,7 +76,7 @@ jobs:
             REPO_DIR=$(cygpath -w $PWD)
           fi
   
-          echo "PARALLEL_LEVEL=$(nproc)" >> $GITHUB_ENV
+          echo "CUDA_BINDINGS_PARALLEL_LEVEL=$(nproc)" >> $GITHUB_ENV
           CUDA_CORE_ARTIFACT_BASENAME="cuda-core-python${PYTHON_VERSION_FORMATTED}-${{ matrix.host-platform }}"
           echo "CUDA_CORE_ARTIFACT_BASENAME=${CUDA_CORE_ARTIFACT_BASENAME}" >> $GITHUB_ENV
           echo "CUDA_CORE_ARTIFACT_NAME=${CUDA_CORE_ARTIFACT_BASENAME}-${{ github.sha }}" >> $GITHUB_ENV
@@ -139,10 +139,10 @@ jobs:
           # CIBW mounts the host filesystem under /host
           CIBW_ENVIRONMENT_LINUX: >
             CUDA_PATH=/host/${{ env.CUDA_PATH }}
-            PARALLEL_LEVEL=${{ env.PARALLEL_LEVEL }}
+            CUDA_BINDINGS_PARALLEL_LEVEL=${{ env.CUDA_BINDINGS_PARALLEL_LEVEL }}
           CIBW_ENVIRONMENT_WINDOWS: >
             CUDA_HOME="$(cygpath -w ${{ env.CUDA_PATH }})"
-            PARALLEL_LEVEL=${{ env.PARALLEL_LEVEL }}
+            CUDA_BINDINGS_PARALLEL_LEVEL=${{ env.CUDA_BINDINGS_PARALLEL_LEVEL }}
         with:
           package-dir: ./cuda_bindings/
           output-dir: ${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}

cuda_bindings/cuda/bindings/_lib/cyruntime/cyruntime.pyx.in

@@ -4639,7 +4639,7 @@ cdef cudaError_t _cudaGraphExecGetFlags(cudaGraphExec_t graphExec, unsigned long
     err = m_global.lazyInitContextState()
     if err != cudaSuccess:
         return err
-    err = <cudaError_t>cydriver._cuGraphExecGetFlags(<cydriver.CUgraphExec>graphExec, flags)
+    err = <cudaError_t>cydriver._cuGraphExecGetFlags(<cydriver.CUgraphExec>graphExec, <cydriver.cuuint64_t *>flags)
     if err != cudaSuccess:
         _setLastError(err)
     return err

cuda_bindings/docs/source/index.rst

@@ -11,6 +11,7 @@
    release.md
    environment_variables.md
    api.rst
+   tips_and_tricks.rst
 
 
 Indices and tables

cuda_bindings/docs/source/tips_and_tricks.rst

@@ -0,0 +1,9 @@
+Tips and Tricks
+---------------
+
+Getting the address of underlying C objects from the low-level bindings
+=======================================================================
+
+All CUDA C types are exposed to Python as Python classes. For example, the :class:`~cuda.bindings.driver.CUstream` type is exposed as a class with methods :meth:`~cuda.bindings.driver.CUstream.getPtr()` and :meth:`~cuda.bindings.driver.CUstream.__int__()` implemented.
+
+There is an important distinction between the ``getPtr()`` method and the behaviour of ``__int__()``. If you need to get the pointer address *of* the underlying ``CUstream`` C object wrapped in the Python class, you can do so by calling ``int(instance_of_CUstream)``, which returns the address as a Python `int`, while calling ``instance_of_CUstream.getPtr()`` returns the pointer *to* the ``CUstream`` C object (that is, ``&CUstream``) as a Python `int`.