For large matrices, I’d use C and OpenMP - SSE/AVX - MPI.
http://perimeterinstitute.ca/personal/wcunningham/parallel.pdf
GNU Octave is another option.
For large matrices, I’d use C and OpenMP - SSE/AVX - MPI.
http://perimeterinstitute.ca/personal/wcunningham/parallel.pdf
GNU Octave is another option.