Fix a bug in elpa_multiply_a_b

Merged Wenzhe Yu requested to merge vwzyu/elpa:fix_mult_at_b_gpu into master_pre_stage

In elpa_multiply_a_b I wanted to call mpi_comm_rank but accidentally called mpi_comm_size. This only affects the GPU initialization where GPUs are assigned to CPU cores based on their MPI ranks. Should be a trivial fix.

Merge request reports