4.2 GPU example

The code discussed here shows how to set up a program exploiting the combined GPU capabilities of PSBLAS and AMG4PSBLAS. The code example is available in the source distribution directory amg4psblas/examples/gpu.

First of all, we need to include the appropriate modules and declare some auxiliary variables:

In this particular example we are choosing to employ a HLG data structure for sparse matrices on GPUs; for more information please refer to the PSBLAS-EXT users’ guide.

We then have to initialize the GPU environment, and pass the appropriate MOLD variables to the build methods (see also the PSBLAS and PSBLAS-EXT users’ guides).

Finally, we convert the input matrix, the descriptor and the vectors to use a GPU-enabled internal storage format. We then preallocate the preconditioner workspace before entering the Krylov method. At the end of the code, we close the GPU environment

It is very important to employ smoothers and coarsest solvers that are suited to the GPU, i.e. methods that do NOT employ triangular system solve kernels. Methods that satisfy this constraint include:

• JACOBI
• BJAC with the following methods on the local blocks:
  • INVK
  • INVT
  • AINV

and their ℓ₁ variants.