Is the input to AMGX_matrix_upload_distributed() assumed to be assembled?

[stgeke]

To be more precise: Does it add to values on other processors?

[marsaev]

You can see example of this API usage here: https://github.com/NVIDIA/AMGX/blob/main/examples/amgx_mpi_capi_cla.c#L513 And how input data is set up: https://github.com/NVIDIA/AMGX/blob/main/examples/amgx_mpi_capi_cla.c#L395-L436