from IPython.parallel import Client, require, interactive

rc = Client()
dv = rc.direct_view()
lv = rc.load_balanced_view()

with dv.sync_imports():
    import numpy

mat = numpy.random.random_sample((800, 800))
mat = numpy.asfortranarray(mat)

def simple_inner(i):
    column = mat[:, i]
    # have to use a list comprehension to prevent closure
    return sum([numpy.inner(column, mat[:, j]) for j in xrange(i + 1, mat.shape[1])])

%timeit sum(simple_inner(i) for i in xrange(mat.shape[1] - 1))

dv.push(dict(mat=mat), block=True);

%timeit sum(dv.map(simple_inner, range(mat.shape[1] - 1), block=False))

%timeit sum(lv.map(simple_inner, range(mat.shape[1] - 1), ordered=False, chunksize=(mat.shape[1] - 1) // len(lv), block=False))

%px mat = numpy.asfortranarray(mat)

%timeit sum(dv.map(simple_inner, range(mat.shape[1] - 1), block=False))

%timeit sum(lv.map(simple_inner, range(mat.shape[1] - 1), ordered=False, chunksize=(mat.shape[1] - 1) // len(lv), block=False))

def inner(i, j):
    return numpy.inner(mat[:, i], mat[:, j])

first = [i for i in xrange(mat.shape[1] - 1) for j in xrange(i + 1, mat.shape[1])]

second = [j for i in xrange(mat.shape[1] - 1) for j in xrange(i + 1, mat.shape[1])]

%timeit sum(dv.map(inner, first, second, block=False))

%timeit sum(lv.map(inner, first, second, unordered=True, chunksize=len(first) // len(lv), block=False))

%timeit sum(map(inner, first, second))