import cython
cimport cython

ctypedef fused real:
    cython.short
    cython.ushort
    cython.int
    cython.uint
    cython.long
    cython.ulong
    cython.longlong
    cython.ulonglong
    cython.float
    cython.double


cdef extern from "<parallel/algorithm>" namespace "__gnu_parallel":
    cdef void sort[T](T first, T last) nogil


@cython.boundscheck(False) # turn off bounds-checking for entire function
@cython.wraparound(False)  # turn off negative index wrapping for entire function
def parallelsort(real[:] a):
    """
    In-place parallel sort for numpy types
    """
    sort(&a[0], &a[a.shape[0]])