dtype: NotImplementedError: float16

Hello, I am trying to reduce the memory footprint of the matrices containing small integers, and want to set the dtype to np.int8 or np.float16.

import sparse
import numpy as np
x=sparse.COO(np.random.rand(5*10**2, 5*10**2)).astype(np.float16)
y = sparse.dot(x,x)
z = sparse.dot(y,y)

This is the error I get:

myenvpath/lib/python3.6/site-packages/sparse/coo/common.py in _dot_coo_coo_type(dt1, dt2)
   1208 
   1209     @numba.jit(nopython=True, nogil=True,
-> 1210                locals={'data_curr': numba.numpy_support.from_dtype(dtr)})
   1211     def _dot_coo_coo(coords1, data1, coords2, data2):  # pragma: no cover
   1212         """

myenvpath/lib/python3.6/site-packages/numba/numpy_support.py in from_dtype(dtype)
    106             return types.NestedArray(subtype, dtype.shape)
    107 
--> 108     raise NotImplementedError(dtype)
    109 
    110 

NotImplementedError: float16

Start with sparse/coo/common.py at _dot_coo_coo_type and reproduce the reported sparse.COO and sparse.dot sequence using np.float16 or np.int8. Check how the dtype reaches the Numba helper; done means the reported dot operations no longer raise NotImplementedError for the requested dtype.