search

IntelLabs / numba

NumPy aware dynamic Python compiler using LLVM
http://numba.pydata.org/
BSD 2-Clause "Simplified" License
12 stars 2 forks source link

Cartesian map operator #32

Open ehsantn opened 7 years ago

ehsantn commented 7 years ago

We need a more general form of prange that provides a parallel iterator in multiple dimensions. Currently, parallel functions like min/max have to linearize the array using ravel first.

ninegua commented 6 years ago

There is a ndindex function in numpy that iterates over indices, which is actually very close to our loopnest. So maybe some like a pndindex?

DrTodd13 commented 6 years ago

Good idea.

ehsantn commented 6 years ago

Yes, this looks great for our purpose.