I’d like to have a better understanding of the solvers implemented in the library. For example, I’ll be using BiCGStab and I’d like to know whether the solver is simply build upon BLAS-routines, or whether the method has been reformulated into algorithmic-specific kernels such that communication overhead can be minimized? Is there somewhere where I can find this info?
since PARALUTION is released under the terms of the GPLv3 license, you can find all implementation details directly in the source code! The BiCGStab method for example is implemented in the solvers/krylov/bicgstab.cpp file.