[Build] v2.4.0 with Cuda 11.0 about amgx HOT 4 OPEN

Then, errors during example builds:

VERBOSE=1 make
cd /ccc/scratch/cont002/den/ledacp/trust/amgx_openmp_int64/ThirdPart/src/LIBAMGX/AmgX/build/examples && /ccc/products2/cmake-3.22.2/Rhel_8__x86_64/system/default/bin/cmake -E cmake_link_script CMakeFiles/amgx_mpi_capi_agg.dir/link.txt --verbose=1
/ccc/products/gcc-8.3.0/system/default/bin/gcc -DRAPIDJSON_DEFINED -DAMGX_WITH_MPI -O3 -DNDEBUG -L/ccc/products2/openmpi-4.1.4.6/Rhel_8__x86_64/gcc--8.3.0/default/lib -L/ccc/products2/hwloc-2.5.0/Rhel_8__x86_64/system/cuda-11.6/lib -L/ccc/products2/openmpi-4.1.4.6/Rhel_8__x86_64/gcc--8.3.0/default/lib -L/ccc/products2/hwloc-2.5.0/Rhel_8__x86_64/system/cuda-11.6/lib CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o -o amgx_mpi_capi_agg /ccc/products/openmpi-4.1.4/gcc--8.3.0/default/lib/libmpi.so ../libamgxsh.so -lrt -ldl /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/lib64/libcudart_static.a /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/../../math_libs/11.0/lib64/libcublas.so /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/../../math_libs/11.0/lib64/libcusolver.so /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/../../math_libs/11.0/lib64/libcublas.so /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/../../math_libs/11.0/lib64/libcusparse.so /ccc/products/nvhpc-22.7/system/default/Linux_x86_64/22.7/cuda/11.0/lib64/libnvToolsExt.so -lm -lpthread /ccc/products/openmpi-4.1.4/gcc--8.3.0/default/lib/libmpi_cxx.so /ccc/products/openmpi-4.1.4/gcc--8.3.0/default/lib/libmpi.so -ldl -lpthread /usr/lib64/librt.so
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaMallocAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaMallocAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaMallocAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaMallocAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaFreeAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaFreeAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaFreeAsync'
CMakeFiles/amgx_mpi_capi_agg.dir/amgx_mpi_capi_agg.c.o:amgx_mpi_capi_agg.c:function main: error: undefined reference to 'cudaFreeAsync'

cudaMallocAsync & cudaFreeAsync appears with Cuda 11.2. So probably, that's the reason there. AmgX v2.4.0 don't build with Cuda<11.2

from amgx.

Thanks for reporting this. I changed our internal testing to include CUDA 11.0 (we previously had just 11.2, 11.8). I'll push a fix to main shortly.

from amgx.

Hopefully should be fixed in main.

from amgx.

Thanks Matt.

from amgx.