For highest performance, HALCON provides an efficient automatic acceleration by optimal usage of the additional computing power of GPUs based on the OpenCL standard. Thereby, more than 50 HALCON operators can be accelerated considerably.

Processing time on GPU

Binomial filter (3x3)	0.18 ms
Image subtraction	0.12 ms
Affine transformation (bilinear)	0.15 ms
Polar transformation	0.24 ms
Color space conversion (hsi)	0.36 ms
These runtime examples were measured using images of size 1280 x 960 on a NVIDIA Tesla C2050 GPU.