Add cuDSS as sparse Cholesky solver

cuDSS could be used as an alternative for SuiteSparse and EigenSparse
in case if CUDA capable GPU is available.

Change-Id: I7a567093ce91363478118153e181134ed5804573

.github/workflows/linux.yml

@@ -82,6 +82,13 @@ jobs:
           apt-get install -y nvidia-cuda-toolkit
           echo "CUDACXX=/usr/lib/nvidia-cuda-toolkit/bin/nvcc" >> $GITHUB_ENV
 
+      - name: Setup cuDSS
+        if: matrix.gpu == 'cuda'
+        run: |
+          wget https://developer.download.nvidia.com/compute/cudss/redist/libcudss/linux-x86_64/libcudss-linux-x86_64-0.3.0.9_cuda12-archive.tar.xz
+          tar -xf libcudss-linux-x86_64-0.3.0.9_cuda12-archive.tar.xz
+          echo "cudss_DIR=${{github.workspace}}/libcudss-linux-x86_64-0.3.0.9_cuda12-archive/lib/cmake/cudss" >> $GITHUB_ENV
+
       - name: Cache Build
         id: cache-build
         uses: actions/cache@v4