Skip to content

GitLab

elpa
elpa
Commit 08ad69dd authored by Andreas Marek's avatar Andreas Marek
3 Browse files
Options

Update a bit the documentation from doxygen

parent 5d359402
Show whitespace changes
Inline Side-by-side
Showing with 93 additions and 4 deletions
src/elpa.F90
View file @ 08ad69dd
......@@ -109,7 +109,7 @@
!> class(elpa_t), pointer :: elpa
!> integer :: success
!>
!> if (elpa_init(20171201) /= ELPA_OK) then
!> if (elpa_init(20181112) /= ELPA_OK) then
!> print *, "ELPA API version not supported"
!> stop
!> endif
......@@ -125,18 +125,26 @@
!> call elpa%set("process_row", my_prow, success)
!> call elpa%set("process_col", my_pcol, success)
!>
!> ! set up the elpa object
!> succes = elpa%setup()
!>
!> ! if desired, set tunable run-time options
!> call e%set("solver", ELPA_SOLVER_2STAGE, success)
!> ! here we want to use the 2-stage solver
!> call elpa%set("solver", ELPA_SOLVER_2STAGE, success)
!>
!> ! and set a specific kernel (must be supported on the machine)
!> call elpa%set("real_kernel", ELPA_2STAGE_REAL_AVX_BLOCK2)
!> \endcode
!> ... set and get all other options that are desired
!> \code{.f90}
!>
!> ! if wanted you can store the settings and load them in another program
!> call elpa%store_settings("save_to_disk.txt")
!>
!> ! use method solve to solve the eigenvalue problem to obtain eigenvalues
!> ! and eigenvectors
!> ! other possible methods are desribed in \ref elpa_api::elpa_t derived type
!> call e%eigenvectors(a, ev, z, success)
!> call elpa%eigenvectors(a, ev, z, success)
!>
!> ! cleanup
!> call elpa_deallocate(e)
......@@ -153,11 +161,12 @@
!> elpa_t handle;
!> int error;
!>
!> if (elpa_init(20171201) != ELPA_OK) {
!> if (elpa_init(20181113) != ELPA_OK) {
!> fprintf(stderr, "Error: ELPA API version not supported");
!> exit(1);
!> }
!>
!>
!> handle = elpa_allocate(&error);
!>
!> /* Set parameters the matrix and it's MPI distribution */
......@@ -174,11 +183,17 @@
!> elpa_setup(handle);
!>
!> /* if desired, set tunable run-time options */
!> /* here we want to use the 2-stage solver
!> elpa_set(handle, "solver", ELPA_SOLVER_2STAGE, &error);
!>
!> elpa_set(handle,"real_kernel", ELPA_2STAGE_REAL_AVX_BLOCK2, &error);
!> \endcode
!> ... set and get all other options that are desired
!> \code{.c}
!>
!> // if you want you can store the settings and load them in another program
!> elpa_store_settings(handle, "save_to_disk.txt")
!>
!> /* use method solve to solve the eigenvalue problem */
!> /* other possible methods are desribed in \ref elpa_api::elpa_t derived type */
!> elpa_eigenvectors(handle, a, ev, z, &error);
......@@ -188,6 +203,80 @@
!> elpa_uninit();
!> \endcode
!>
!> the autotuning could be used like this:
!>
!> Fortran synopsis
!>
!> \code{.f90}
!> use elpa
!> class(elpa_t), pointer :: elpa
!> class(elpa_autotune_t), pointer :: tune_state
!> integer :: success
!>
!> if (elpa_init(20181112) /= ELPA_OK) then
!> print *, "ELPA API version not supported"
!> stop
!> endif
!> elpa => elpa_allocate()
!>
!> ! set parameters decribing the matrix and it's MPI distribution
!> call elpa%set("na", na, success)
!> call elpa%set("nev", nev, success)
!> call elpa%set("local_nrows", na_rows, success)
!> call elpa%set("local_ncols", na_cols, success)
!> call elpa%set("nblk", nblk, success)
!> call elpa%set("mpi_comm_parent", MPI_COMM_WORLD, success)
!> call elpa%set("process_row", my_prow, success)
!> call elpa%set("process_col", my_pcol, success)
!>
!> ! set up the elpa object
!> succes = elpa%setup()
!>
!> ! create autotune object
!> tune_state => elpa%autotune_setup(ELPA_AUTOTUNE_FAST, ELPA_AUTOTUNE_DOMAIN_REAL, error)
!>
!> ! you can set some options, these will be then FIXED for the autotuning step
!> ! if desired, set tunable run-time options
!> ! here we want to use the 2-stage solver
!> call e%set("solver", ELPA_SOLVER_2STAGE, success)
Please register or sign in to reply
!>
!> ! and set a specific kernel (must be supported on the machine)
!> call e%set("real_kernel", ELPA_2STAGE_REAL_AVX_BLOCK2)
Please register or sign in to reply
!> \endcode
!> ... set and get all other options that are desired
!> \code{.f90}
!>
!> iter = 0
!> do while (elpa%autotune_step(tune_state))
!> iter = iter + 1
!> call e%eigenvectors(a, ev, z, success)
Please register or sign in to reply
!>
!> ! if needed you can save the autotune state at any point
!> ! and resume it
!> if (iter > MAX_ITER) then
!> call elpa%autotune_save_state(tune_state,"autotune_checkpoint.txt")
!> exit
!> endif
!> enddo
!>
!> !set and print the finished autotuning
!> call elpa%autotune_set_best(tune_state)
!>
!> ! store _TUNED_ ELPA object, if needed
!> call elpa%store("autotuned_object.txt")
!>
!> !deallocate autotune object
!> call elpa_autotune_deallocate(tune_state)
!>
!> ! cleanup
!> call elpa_deallocate(e)
!>
!> call elpa_uninit()
!> \endcode
!>
!> More examples can be found in the folder "test", where Fortran and C example programs
!> are stored
!> \brief Fortran module to use the ELPA library. No other module shoule be used
#include "config-f90.h"
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment