[Numpy-discussion] Speedup by avoiding memory alloc twice in scalar array
arinkverma at gmail.com
Tue Jul 16 06:34:47 EDT 2013
I am working on performance parity between numpy scalar/small array and
python array as GSOC mentored By Charles.
Currently I am looking at PyArray_Return, which allocate separate memory
just for scalar return. Unlike python which allocate memory once for
returning result of scalar operations; numpy calls malloc twice once for
the array object itself, and a second time for the array data.
These memory allocations are happening in PyArray_NewFromDescr and
PyArray_Scalar. Stashing both within a single allocation would be more
In, PyArray_Scalar, new struct (PyLongScalarObject) need allocation in case
of scalar arrays. Instead, can we just some how convert/cast PyArrayObject
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the NumPy-Discussion