Merge branch 'branch-24.06' into patch-2

ci/build_docs.sh

@@ -20,24 +20,33 @@ rapids-logger "Downloading artifacts from previous jobs"
 CPP_CHANNEL=$(rapids-download-conda-from-s3 cpp)
 PYTHON_CHANNEL=$(rapids-download-conda-from-s3 python)
 
+if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
+  CONDA_CUDA_VERSION="11.8"
+  DGL_CHANNEL="dglteam/label/cu118"
+else
+  CONDA_CUDA_VERSION="12.1"
+  DGL_CHANNEL="dglteam/label/cu121"
+fi
+
 rapids-mamba-retry install \
   --channel "${CPP_CHANNEL}" \
   --channel "${PYTHON_CHANNEL}" \
+  --channel conda-forge \
+  --channel pyg \
+  --channel nvidia \
+  --channel "${DGL_CHANNEL}" \
   libcugraph \
   pylibcugraph \
   cugraph \
   cugraph-pyg \
+  cugraph-dgl \
   cugraph-service-server \
   cugraph-service-client \
   libcugraph_etl \
   pylibcugraphops \
-  pylibwholegraph
-
-# This command installs `cugraph-dgl` without its dependencies
-# since this package can currently only run in `11.6` CTK environments
-# due to the dependency version specifications in its conda recipe.
-rapids-logger "Install cugraph-dgl"
-rapids-mamba-retry install "${PYTHON_CHANNEL}/linux-64/cugraph-dgl-*.tar.bz2"
+  pylibwholegraph \
+  pytorch \
+  "cuda-version=${CONDA_CUDA_VERSION}"
 
 export RAPIDS_VERSION="$(rapids-version)"
 export RAPIDS_VERSION_MAJOR_MINOR="$(rapids-version-major-minor)"

ci/run_cugraph_pyg_pytests.sh

@@ -7,3 +7,9 @@ set -euo pipefail
 cd "$(dirname "$(realpath "${BASH_SOURCE[0]}")")"/../python/cugraph-pyg/cugraph_pyg
 
 pytest --cache-clear --ignore=tests/mg "$@" .
+
+# Test examples
+for e in "$(pwd)"/examples/*.py; do
+  rapids-logger "running example $e"
+  python $e
+done

ci/test_python.sh

@@ -154,8 +154,7 @@ if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
     rapids-mamba-retry install \
       --channel "${CPP_CHANNEL}" \
       --channel "${PYTHON_CHANNEL}" \
-      --channel pytorch \
-      --channel pytorch-nightly \
+      --channel conda-forge \
       --channel dglteam/label/cu118 \
       --channel nvidia \
       libcugraph \
@@ -165,7 +164,7 @@ if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
       cugraph-dgl \
       'dgl>=1.1.0.cu*,<=2.0.0.cu*' \
       'pytorch>=2.0' \
-      'pytorch-cuda>=11.8'
+      'cuda-version=11.8'
 
     rapids-print-env
 
@@ -191,33 +190,43 @@ fi
 
 if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
   if [[ "${RUNNER_ARCH}" != "ARM64" ]]; then
-    rapids-mamba-retry env create --yes -f env.yaml -n test_cugraph_pyg
+    rapids-mamba-retry env create --force -f env.yaml -n test_cugraph_pyg
 
     # Temporarily allow unbound variables for conda activation.
     set +u
     conda activate test_cugraph_pyg
     set -u
 
+    # TODO re-enable logic once CUDA 12 is testable
+    #if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
+    CONDA_CUDA_VERSION="11.8"
+    PYG_URL="https://data.pyg.org/whl/torch-2.1.0+cu118.html"
+    #else
+    #  CONDA_CUDA_VERSION="12.1"
+    #  PYG_URL="https://data.pyg.org/whl/torch-2.1.0+cu121.html"
+    #fi
+
     # Will automatically install built dependencies of cuGraph-PyG
     rapids-mamba-retry install \
       --channel "${CPP_CHANNEL}" \
       --channel "${PYTHON_CHANNEL}" \
       --channel pytorch \
-      --channel nvidia \
       --channel pyg \
-      --channel rapidsai-nightly \
+      --channel nvidia \
       "cugraph-pyg" \
-      "pytorch>=2.0,<2.1" \
-      "pytorch-cuda=11.8"
+      "pytorch=2.1.0" \
+      "pytorch-cuda=${CONDA_CUDA_VERSION}"
 
     # Install pyg dependencies (which requires pip)
+
+    pip install ogb
     pip install \
         pyg_lib \
         torch_scatter \
         torch_sparse \
         torch_cluster \
         torch_spline_conv \
-      -f https://data.pyg.org/whl/torch-2.0.0+cu118.html
+      -f ${PYG_URL}
 
     rapids-print-env
 
@@ -235,12 +244,11 @@ if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
     conda deactivate
     conda activate test
     set -u
-
   else
     rapids-logger "skipping cugraph_pyg pytest on ARM64"
   fi
 else
-  rapids-logger "skipping cugraph_pyg pytest on CUDA != 11.8"
+  rapids-logger "skipping cugraph_pyg pytest on CUDA!=11.8"
 fi
 
 # test cugraph-equivariant
@@ -253,7 +261,7 @@ if [[ "${RAPIDS_CUDA_VERSION}" == "11.8.0" ]]; then
     rapids-mamba-retry install \
       --channel "${CPP_CHANNEL}" \
       --channel "${PYTHON_CHANNEL}" \
-      --channel pytorch \
+      --channel conda-forge \
       --channel nvidia \
       cugraph-equivariant
     pip install e3nn==0.5.1

ci/test_wheel_cugraph-pyg.sh

@@ -25,25 +25,33 @@ python -m pip install $(ls ./dist/${python_package_name}*.whl)[test]
 export RAPIDS_DATASET_ROOT_DIR="$(realpath datasets)"
 
 if [[ "${CUDA_VERSION}" == "11.8.0" ]]; then
-  rapids-logger "Installing PyTorch and PyG dependencies"
   PYTORCH_URL="https://download.pytorch.org/whl/cu118"
-  rapids-retry python -m pip install torch==2.1.0 --index-url ${PYTORCH_URL}
-  rapids-retry python -m pip install torch-geometric==2.4.0
-  rapids-retry python -m pip install \
-    pyg_lib \
-    torch_scatter \
-    torch_sparse \
-    torch_cluster \
-    torch_spline_conv \
-    -f https://data.pyg.org/whl/torch-2.1.0+cu118.html
-
-  rapids-logger "pytest cugraph-pyg (single GPU)"
-  pushd python/cugraph-pyg/cugraph_pyg
-  python -m pytest \
-    --cache-clear \
-    --ignore=tests/mg \
-    tests
-  popd
+  PYG_URL="https://data.pyg.org/whl/torch-2.1.0+cu118.html"
 else
-  rapids-logger "skipping cugraph-pyg wheel test on CUDA!=11.8"
+  PYTORCH_URL="https://download.pytorch.org/whl/cu121"
+  PYG_URL="https://data.pyg.org/whl/torch-2.1.0+cu121.html"
 fi
+rapids-logger "Installing PyTorch and PyG dependencies"
+rapids-retry python -m pip install torch==2.1.0 --index-url ${PYTORCH_URL}
+rapids-retry python -m pip install torch-geometric==2.4.0
+rapids-retry python -m pip install \
+  ogb \
+  pyg_lib \
+  torch_scatter \
+  torch_sparse \
+  torch_cluster \
+  torch_spline_conv \
+  -f ${PYG_URL}
+
+rapids-logger "pytest cugraph-pyg (single GPU)"
+pushd python/cugraph-pyg/cugraph_pyg
+python -m pytest \
+  --cache-clear \
+  --ignore=tests/mg \
+  tests
+# Test examples
+for e in "$(pwd)"/examples/*.py; do
+  rapids-logger "running example $e"
+  python $e
+done
+popd

conda/environments/all_cuda-118_arch-x86_64.yaml

@@ -4,7 +4,6 @@ channels:
 - rapidsai
 - rapidsai-nightly
 - dask/label/dev
-- pytorch
 - pyg
 - dglteam/label/cu118
 - conda-forge

conda/environments/all_cuda-122_arch-x86_64.yaml

@@ -4,7 +4,6 @@ channels:
 - rapidsai
 - rapidsai-nightly
 - dask/label/dev
-- pytorch
 - pyg
 - dglteam/label/cu118
 - conda-forge

dependencies.yaml

@@ -285,7 +285,6 @@ channels:
   - rapidsai
   - rapidsai-nightly
   - dask/label/dev
-  - pytorch
   - pyg
   - dglteam/label/cu118
   - conda-forge

docs/cugraph/source/installation/source_build.md

@@ -13,8 +13,8 @@ __Compilers:__
 
 __CUDA:__
 * CUDA 11.2+
-* NVIDIA driver 450.80.02+
-* Pascal architecture or better
+* NVIDIA driver 470.42.01 or newer
+* NVIDIA GPU, Volta architecture or later, with [compute capability](https://developer.nvidia.com/cuda-gpus) 7.0+
 
 Further details and download links for these prerequisites are available on the
 [RAPIDS System Requirements page](https://docs.rapids.ai/install#system-req).
@@ -42,6 +42,10 @@ files](https://github.com/rapidsai/cugraph/blob/main/conda/environments).
 # for CUDA 11.x
 conda env create --name cugraph_dev --file $CUGRAPH_HOME/conda/environments/all_cuda-118_arch-x86_64.yaml
 
+# for CUDA 12.x
+conda env create --name cugraph_dev --file $CUGRAPH_HOME/conda/environments/all_cuda-12.2_arch-x86_64.yaml
+
+
 # activate the environment
 conda activate cugraph_dev
 
@@ -55,6 +59,13 @@ The environment can be updated as cugraph adds/removes/updates its dependencies.
 # for CUDA 11.x
 conda env update --name cugraph_dev --file $CUGRAPH_HOME/conda/environments/all_cuda-118_arch-x86_64.yaml
 conda activate cugraph_dev
+
+# for CUDA 12.x
+conda env update --name cugraph_dev --file $CUGRAPH_HOME/conda/environments/all_cuda-122_arch-x86_64.yaml
+conda activate cugraph_dev
+
+
+
 ```
 
 ### Build and Install
@@ -167,7 +178,7 @@ Run either the C++ or the Python tests with datasets
    make test
    ```
 
-Note: This conda installation only applies to Linux and Python versions 3.8/3.10.
+Note: This conda installation only applies to Linux and Python versions 3.8/3.11.
 
 ### (OPTIONAL) Set environment variable on activation
 

notebooks/algorithms/centrality/Betweenness.ipynb

@@ -37,7 +37,7 @@
    "source": [
     "Betweenness centrality of a node 𝑣 is the sum of the fraction of all-pairs shortest paths that pass through 𝑣\n",
     "\n",
-    "<img src=\"https://latex.codecogs.com/png.latex?c_B(v)&space;=\\sum_{s,t&space;\\in&space;V}&space;\\frac{\\sigma(s,&space;t|v)}{\\sigma(s,&space;t)}\" title=\"c_B(v) =\\sum_{s,t \\in V} \\frac{\\sigma(s, t|v)}{\\sigma(s, t)}\" />\n"
+    "$c_B(v) =\\sum_{s,t \\in V} \\frac{\\sigma(s, t|v)}{\\sigma(s, t)}$"
    ]
   },
   {

notebooks/algorithms/centrality/Eigenvector.ipynb

@@ -34,13 +34,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The eigenvector centrality for node i is the\n",
-    "i-th element of the vector x defined by the eigenvector equation.\n",
+    "For a graph with V vertices where $A = (A_v,t)$ is the adjacency matrix, the Eigenvector centrality score of vertex $v$ is defined as\n",
     "\n",
-    "<img src=\"https://wikimedia.org/api/rest_v1/media/math/render/svg/51c506ef0f23db1086b00ff6e5da847ff53cf5e9\" />\n",
     "\n",
+    "$x_v = \\frac{1}{\\lambda}{\\sum_{t \\in M(v)}}x_t = \\frac{1}{\\lambda}{\\sum_{t \\in V}{a_v,x_t}}$\n",
     "\n",
-    "Where M(v) is the adjacency list for the set of vertices(v) and λ is a constant.\n",
+    "Where $M(v)$ is the neighbor set for $v$ and λ is a constant.\n",
     "\n",
     "[Learn more about EigenVector Centrality](https://www.sci.unich.it/~francesc/teaching/network/eigenvector.html)\n"
    ]
@@ -314,7 +313,7 @@
    "metadata": {},
    "source": [
     "___\n",
-    "Copyright (c) 2022-2023, NVIDIA CORPORATION.\n",
+    "Copyright (c) 2022-2024, NVIDIA CORPORATION.\n",
     "\n",
     "Licensed under the Apache License, Version 2.0 (the \"License\");  you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0\n",
     "\n",

notebooks/algorithms/centrality/Katz.ipynb

@@ -35,14 +35,14 @@
     "\n",
     "    G: cugraph.Graph object\n",
     "    alpha: float, Attenuation factor. default is 0.1\n",
-    "    max_iter: int, The maximum number of iterations before an answer is returned. \n",
-    "            This can be used to limit the execution time and do an early exit \n",
-    "            before the solver reaches the convergence tolerance. If this value \n",
+    "    max_iter: int, The maximum number of iterations before an answer is returned.\n",
+    "            This can be used to limit the execution time and do an early exit\n",
+    "            before the solver reaches the convergence tolerance. If this value\n",
     "            is lower or equal to 0 cuGraph will use the default value, which is 100\n",
-    "    tol: float, Set the tolerance the approximation, this parameter should be a small \n",
-    "            magnitude value. The lower the tolerance the better the approximation. If \n",
-    "            this value is 0.0f, cuGraph will use the default value which is 0.00001. \n",
-    "            Setting too small a tolerance can lead to non-convergence due to numerical \n",
+    "    tol: float, Set the tolerance the approximation, this parameter should be a small\n",
+    "            magnitude value. The lower the tolerance the better the approximation. If\n",
+    "            this value is 0.0f, cuGraph will use the default value which is 0.00001.\n",
+    "            Setting too small a tolerance can lead to non-convergence due to numerical\n",
     "            roundoff. Usually values between 0.01 and 0.00001 are acceptable.\n",
     "    nstart: cuDataFrame, GPU Dataframe containing the initial guess for katz centrality. \n",
     "            Default is None\n",
@@ -58,8 +58,8 @@
     "\n",
     "\n",
     "The value of _alpha_ should be<br>\n",
-    "<img src=\"https://latex.codecogs.com/gif.latex?\\alpha&space;<&space;\\frac{1}{\\lambda&space;_{max}&space;}\" title=\"\\alpha < \\frac{1}{\\lambda _{max} }\" />\n",
-    "currently the user is responsible for setting alpha appropiatly.  \n",
+    "$\\alpha < \\frac{1}{\\lambda _{max} }$\n",
+    "currently the user is responsible for setting alpha appropriately.\n",
     "\n",
     "### _NOTICE_\n",
     "There is a difference between how cuGraph and how NetworkX computes the Katz centrality score.  That difference leads to the scores not matching.  cuGraph does not currently support the 'beta' and 'weight' parameters as seen in the corresponding networkX call. The cuGraph implementation is based on a relaxed version of Katz defined by Foster with a reduced computational complexity of O(n+m)\n",

notebooks/algorithms/link_analysis/Pagerank.ipynb

@@ -44,6 +44,22 @@
     "  * For more advanced renumbering support, see the examples in `structure/renumber.ipynb` and `structure/renumber-2.ipynb`\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The formula for Pagerank is:\n",
+    "\n",
+    "$PR(A) = \\frac{1 - d}{N} + d \\times \\left( \\sum_{i=1}^{N} \\frac{PR(T_i)}{C(T_i)} \\right)$\n",
+    "\n",
+    "In the formula:\n",
+    "* $PR(A)$ is the pagerank of A\n",
+    "* $d$ is damping factor which represents the probability of following an outgoing edge. A common default is 0.85\n",
+    "* $N$ is the total number of webpages\n",
+    "* $T_i$ are pages containing links to page A\n",
+    "* $C(T_i)$ is the number of links from node $T_i$"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -306,7 +322,7 @@
    "source": [
     "----\n",
     "\n",
-    "a PageRank score of _0.10047_ is very low, which can be an indication that there is no more central vertex than any other.  Rather than just looking at the top score, let's look at the top three vertices and see if there are any insights that can be inferred.  \n",
+    "a PageRank score of _0.100917324_ is very low, which can be an indication that there is no more central vertex than any other.  Rather than just looking at the top score, let's look at the top three vertices and see if there are any insights that can be inferred.  \n",
     "\n",
     "Since this is a very small graph, let's just sort and get the first three records"
    ]
@@ -353,6 +369,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# this started the vertices with 1 instead of 0 to coincide with the diagram\n",
+    "d['vertex'] = d['vertex']+1\n",
+    "\n",
     "d.sort_values('out_degree', ascending=False).head(3)"
    ]
   },
@@ -428,7 +447,7 @@
    "metadata": {},
    "source": [
     "___\n",
-    "Copyright (c) 2019-2023, NVIDIA CORPORATION.\n",
+    "Copyright (c) 2019-2024, NVIDIA CORPORATION.\n",
     "\n",
     "Licensed under the Apache License, Version 2.0 (the \"License\");  you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0\n",
     "\n",
@@ -453,7 +472,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.11.8"
   },
   "vscode": {
    "interpreter": {