Numba

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Numba
Original author(s)Continuum Analytics
Developer(s)Community project
Initial release15 August 2012; 6 years ago (2012-08-15)
Stable release
0.39.0 / 6 July 2018; 4 months ago (2018-07-06)
Preview release
0.40.0dev0 / 10 July 2018; 4 months ago (2018-07-10)
Repository Edit this at Wikidata
Written inPython, C
Operating systemCross-platform
TypeTechnical computing
Websitenumba.pydata.org

Numba is an open-source NumPy-aware optimizing compiler for Python sponsored by Anaconda, Inc and a grant from the Gordon and Betty Moore Foundation. It uses the LLVM compiler infrastructure to compile Python to CPU and GPU machine code.[1]

Traits[edit]

Numba compiles Python code with LLVM to code which can be natively executed by the CPU or GPU at runtime. This happens by decorating Python functions, which allows users to create native functions for different input types, or to create them on the fly:

@jit('f8(f8[:])')
def sum1d(my_double_array):
    total = 0.0
    for i in range(my_double_array.shape[0]):
        total += my_double_array[i]
    return total

This optimized function runs 200 times faster than the interpreted original function on a long NumPy array; and it is 30% faster than NumPy's builtin sum()function (version 0.27.0).[2][3]

To make the above example work for any compatible input types automatically, we can create a function that specializes automatically:

@jit
def sum1d(my_array):
    ...

GPU Support[edit]

Numba can compile Python functions to GPU code. There are two approaches available currently:

NVIDIA CUDA[edit]

@cuda.jit
def increment_a_2D_array(an_array):
    x, y = cuda.grid(2)
    if x < an_array.shape[0] and y < an_array.shape[1]:
       an_array[x, y] += 1

numba.pydata.org/numba-doc/dev/cuda/overview.html

AMD HSA[edit]

Simply use the annotation '@hsa.jit':

@hsa.jit(device=True)
def a_device_function(a, b):
    return a + b

numba.pydata.org/numba-doc/dev/hsa/overview.html

Alternative approaches[edit]

The following projects are alternative approaches to accelerating Python:

References[edit]

  1. ^ "numba/numba: NumPy aware dynamic Python compiler using LLVM". GitHub.
  2. ^ "A Speed Comparison Of C, Julia, Python, Numba, and Cython on LU Factorization".
  3. ^ "Numba vs. Cython: Take 2".