EXX FFT decomposition

This merge request intends to fix two things:

• -pd .true. or .false. was not honored in exx.f90 and exx_band.f90, where pencil decomposition is always used.
• A GPU to CPU memory transfer was at a wrong place in vexx_gamma_gpu.

For a number of test cases, this merge request leads to a performance improvement from 20% to 50%.

Example: SiC supercell containing 256 atoms.

• Input files

  • pw.in
  • C_ONCV_PBE-1.2.upf
  • Si_ONCV_PBE-1.2.upf

• Using two Cori Haswell nodes, using slab instead of pencil decomposition speeds up vexx by ~30%.

  • pw.out.cori.haswell.pencil
  • pw.out.cori.haswell.slab

• Using one Summit node, getting rid of the redundant memcpy improves the performance of vexx by ~20%. Using slab decomposition improves another ~20%. Overall the time spent on vexx is reduced from 715 to 446 seconds.

  • pw.out.summit.original
  • pw.out.summit.fixed.pencil
  • pw.out.summit.fixed.slab

Results are not affected in any way as far as I can tell.