add first version of python wrapper

- depends on python, cython, mpi4py and numpy
- currently only dependency check on python
- should be done optionally
- converts wrapper.pyx to wrapper.c using cython, then compiles this to
  a python extension
- installs the files such that they can be imported with `import pyelpa`
  in python

Makefile.am

@@ -612,6 +612,17 @@ endif
 #test_c_cannon@SUFFIX@_LDADD = $(test_program_ldadd) $(FCLIBS)
 #test_c_cannon@SUFFIX@_CFLAGS = $(test_program_cflags)
 
+# python wrapper
+pyelpadir = $(pythondir)/pyelpa
+pyelpa_PYTHON = python/__init__.py python/distributedmatrix.py
+pyelpa_LTLIBRARIES = wrapper.la
+wrapper_la_SOURCES = python/wrapper.c
+wrapper_la_LDFLAGS = -module -avoid-version -shared $(AM_LDFLAGS)
+wrapper_la_LIBADD = libelpa@SUFFIX@.la
+wrapper_la_CFLAGS = -I$(PYTHON_INCLUDE) $(AM_CFLAGS)
+
+python/wrapper.c: python/wrapper.pyx
+	cython $<
 
 
 # test scripts

configure.ac

@@ -1275,6 +1275,22 @@ else
         AC_MSG_RESULT([no])
 fi
 
+AM_PATH_PYTHON([3.6])
+AC_ARG_VAR([PYTHON_INCLUDE], [Include flags for python, bypassing python-config])
+AC_ARG_VAR([PYTHON_CONFIG], [Path to python-config])
+AS_IF([test -z "$PYTHON_INCLUDE"], [
+  AS_IF([test -z "$PYTHON_CONFIG"], [
+    AC_PATH_PROGS([PYTHON_CONFIG],
+                  [python$PYTHON_VERSION-config python-config],
+                  [no],
+                  [`dirname $PYTHON`])
+    AS_IF([test "$PYTHON_CONFIG" = no], [AC_MSG_ERROR([cannot find python-config for $PYTHON.])])
+  ])
+  AC_MSG_CHECKING([python include flags])
+  PYTHON_INCLUDE=`$PYTHON_CONFIG --includes`
+  AC_MSG_RESULT([$PYTHON_INCLUDE])
+])
+
 
 AC_OUTPUT
 

python/__init__.py

+"""pyelpa -- python wrapper for ELPA
+
+This wrapper uses cython to wrap the C API of ELPA (Eigenvalue SoLvers for
+Petaflop-Applications) so that it can be called from python.
+
+Examples:
+
+1. Use the Elpa object to access the eigenvectors/eigenvalues wrapper:
+
+>>> import numpy as np
+... from pyelpa import ProcessorLayout, DistributedMatrix, Elpa
+... from mpi4py import MPI
+... import sys
+... 
+... # set some parameters for matrix layout
+... na = 1000
+... nev = 200
+... nblk = 16
+... 
+... # initialize processor layout, needed for calling ELPA
+... comm = MPI.COMM_WORLD
+... layout_p = ProcessorLayout(comm)
+... 
+... # create arrays
+... a = DistributedMatrix(layout_p, na, nev, nblk)
+... eigenvectors = DistributedMatrix(layout_p, na, nev, nblk)
+... eigenvalues = np.zeros(na, dtype=np.float64)
+... 
+... # initialize elpa
+... e = Elpa.from_distributed_matrix(a)
+... 
+... # set input matrix (a.data) on this core (a is stored in a block-cyclic
+... # distributed layout; local size: a.na_rows x a.na_cols)
+... # Caution: using this, the global matrix will not be symmetric; this is just
+... # and example to show how to access the data
+... a.data[:, :] = np.random.rand(a.na_rows, a.na_cols).astype(np.float64)
+... 
+... # now compute nev of na eigenvectors and eigenvalues
+... e.eigenvectors(a.data, eigenvalues, eigenvectors.data)
+... 
+... # now eigenvectors.data contains the local part of the eigenvector matrix
+... # which is stored in a block-cyclic distributed layout
+... 
+... # now eigenvalues contains all computed eigenvalues on all cores
+... 
+... # now compute nev of na eigenvalues
+... e.eigenvalues(a.data, eigenvalues)
+... 
+... # now eigenvalues contains all computed eigenvalues on all cores
+
+
+2. Use the functions provided by the DistributedMatrix object:
+
+>>> import numpy as np
+... from pyelpa import DistributedMatrix
+... 
+... # set some parameters for matrix layout
+... na = 1000
+... nev = 200
+... nblk = 16
+... 
+... a = DistributedMatrix.from_comm_world(na, nev, nblk)
+... # use a diagonal matrix as input
+... matrix = np.diagflat(np.arange(na)**2)
+... # set from global matrix
+... a.set_data_from_global_matrix(matrix)
+... 
+... data = a.compute_eigenvectors()
+... eigenvalues = data['eigenvalues']
+... eigenvectors = data['eigenvectors']
+... # now eigenvectors.data contains the local part of the eigenvector matrix
+... # which is stored in a block-cyclic distributed layout
+... 
+... # now eigenvalues contains all computed eigenvalues on all cores
+"""
+from .wrapper import Elpa
+from .distributedmatrix import ProcessorLayout, DistributedMatrix
+
+__all__ = ['ProcessorLayout', 'DistributedMatrix', 'Elpa']