1. 24 Jun, 2019 1 commit
  2. 08 May, 2019 1 commit
    • Pavel Kus's avatar
      adding test which splits communicator at the beginning · 5ad06a95
      Pavel Kus authored
      and runs several elpas (still mpi-based) in parallel. Each elpa
      "instance" then splits its communicator to row and column communicator,
      as it is always done. This is actually often done in FHI-aims and was
      previously leading to issues when using OmniPath. Hopefully was solved
      by Intel MPI 2019.3. Keeping the test for future reference.
      5ad06a95
  3. 18 Apr, 2019 1 commit
  4. 03 Dec, 2018 1 commit
  5. 28 Nov, 2018 1 commit
  6. 23 Nov, 2018 1 commit
  7. 21 Nov, 2018 1 commit
    • Pavel Kus's avatar
      changed logic of setting mpi communicators · f3144dd9
      Pavel Kus authored
      mpi_comm_parent is allways requred (it was not required before, but
      actually the code internals expected it to be supplied, at least for
      ELPA 2 calculation OR whenever GPU was used)
      f3144dd9
  8. 20 Nov, 2018 2 commits
  9. 15 Nov, 2018 1 commit
  10. 13 Nov, 2018 1 commit
  11. 27 Aug, 2018 3 commits
  12. 14 Aug, 2018 3 commits
  13. 13 Aug, 2018 1 commit
  14. 10 Aug, 2018 1 commit
  15. 08 Aug, 2018 1 commit
  16. 01 Aug, 2018 1 commit
    • Pavel Kus's avatar
      integration of C implementation of Cannon algorithm to ELPA · 3eb37776
      Pavel Kus authored
      this commit does not work, the generalized EVP problems fail from 2
      reasons:
      - Cannons algorithm does not work for the processor grid shape we use at
        the moment in tests (It only works if num. of process columns is a
        multiple of num. of process rows, which is not true in ELPA for 2 mpi
        tasks)
      - Cannons algorithm does not work as integrated to ELPA for larger
        matrices (not clear why at the moment)
      
      There are 2 new tests, which should work
      - test_cannon.c: it tests the new algorithm without going through
        Fortran, as it has been delivered
      - test_c_bindings: it tests transfering a 2D fortran matrix to C and
        back, as it is done with the cannons algorithm in the normal ELPA
        tests
      3eb37776
  17. 15 Jun, 2018 1 commit
  18. 12 Jun, 2018 1 commit
  19. 25 May, 2018 1 commit
  20. 24 May, 2018 1 commit
  21. 22 May, 2018 1 commit
  22. 11 May, 2018 2 commits
  23. 18 Apr, 2018 3 commits
  24. 05 Feb, 2018 5 commits
  25. 31 Jan, 2018 1 commit
  26. 03 Jan, 2018 1 commit
  27. 01 Dec, 2017 1 commit
  28. 28 Nov, 2017 1 commit