-
-
Save zed/910aa19c6bc70874f974 to your computer and use it in GitHub Desktop.
cython vs. numpy performance
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#cython: boundscheck=False, wraparound=False | |
import numpy as np | |
cimport numpy as np | |
def rotT(np.ndarray[np.float64_t, ndim=4] T, | |
np.ndarray[np.float64_t, ndim=2] g): | |
cdef np.ndarray[np.float64_t, ndim=4] Tprime | |
cdef Py_ssize_t i, j, k, l, ii, jj, kk, ll | |
cdef np.float64_t gg | |
Tprime = np.zeros((3,3,3,3), dtype=T.dtype) | |
for i in range(3): | |
for j in range(3): | |
for k in range(3): | |
for l in range(3): | |
for ii in range(3): | |
for jj in range(3): | |
for kk in range(3): | |
for ll in range(3): | |
gg = g[ii,i]*g[jj,j]*g[kk,k]*g[ll,l] | |
Tprime[i,j,k,l] = Tprime[i,j,k,l] + \ | |
gg*T[ii,jj,kk,ll] | |
return Tprime |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# http://stackoverflow.com/questions/4962606/fast-tensor-rotation-with-numpy | |
import pyximport; pyximport.install() # pip install cython | |
from rotT_cython import rotT | |
import numpy as np | |
T = np.array([[[[ 4.66533067e+01, 5.84985000e-02, -5.37671310e-01], | |
[ 5.84985000e-02, 1.56722231e+01, 2.32831900e-02], | |
[ -5.37671310e-01, 2.32831900e-02, 1.33399259e+01]], | |
[[ 4.60051700e-02, 1.54658176e+01, 2.19568200e-02], | |
[ 1.54658176e+01, -5.18223500e-02, -1.52814920e-01], | |
[ 2.19568200e-02, -1.52814920e-01, -2.43874100e-02]], | |
[[ -5.35577630e-01, 1.95558600e-02, 1.31108757e+01], | |
[ 1.95558600e-02, -1.51342210e-01, -6.67615000e-03], | |
[ 1.31108757e+01, -6.67615000e-03, 6.90486240e-01]]], | |
[[[ 4.60051700e-02, 1.54658176e+01, 2.19568200e-02], | |
[ 1.54658176e+01, -5.18223500e-02, -1.52814920e-01], | |
[ 2.19568200e-02, -1.52814920e-01, -2.43874100e-02]], | |
[[ 1.57414726e+01, -3.86167500e-02, -1.55971950e-01], | |
[ -3.86167500e-02, 4.65601977e+01, -3.57741000e-02], | |
[ -1.55971950e-01, -3.57741000e-02, 1.34215636e+01]], | |
[[ 2.58256300e-02, -1.49072770e-01, -7.38843000e-03], | |
[ -1.49072770e-01, -3.63410500e-02, 1.32039847e+01], | |
[ -7.38843000e-03, 1.32039847e+01, 1.38172700e-02]]], | |
[[[ -5.35577630e-01, 1.95558600e-02, 1.31108757e+01], | |
[ 1.95558600e-02, -1.51342210e-01, -6.67615000e-03], | |
[ 1.31108757e+01, -6.67615000e-03, 6.90486240e-01]], | |
[[ 2.58256300e-02, -1.49072770e-01, -7.38843000e-03], | |
[ -1.49072770e-01, -3.63410500e-02, 1.32039847e+01], | |
[ -7.38843000e-03, 1.32039847e+01, 1.38172700e-02]], | |
[[ 1.33639532e+01, -1.26331100e-02, 6.84650400e-01], | |
[ -1.26331100e-02, 1.34222177e+01, 1.67851800e-02], | |
[ 6.84650400e-01, 1.67851800e-02, 4.89151396e+01]]]]) | |
g = np.array([[ 0.79389393, 0.54184237, 0.27593346], | |
[-0.59925749, 0.62028664, 0.50609776], | |
[ 0.10306737, -0.56714313, 0.8171449 ]]) | |
def rotT_philipp(T, g): | |
gg = np.outer(g, g) | |
gggg = np.outer(gg, gg).reshape(4 * g.shape) | |
axes = ((0, 2, 4, 6), (0, 1, 2, 3)) | |
return np.tensordot(gggg, T, axes) | |
if __name__ == '__main__': | |
assert np.allclose(rotT_philipp(T, g), rotT(T, g)) | |
# | rotT | 10000 loops, best of 3: 28 usec per loop | | |
# | rotT_philipp | 10000 loops, best of 3: 113 usec per loop | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment