diff options
| author | Stan Seibert <stan@mtrr.org> | 2012-01-30 16:59:45 -0500 |
|---|---|---|
| committer | tlatorre <tlatorre@uchicago.edu> | 2021-05-09 08:42:38 -0700 |
| commit | f6fa4739cc476b21b755522e252ebfbb81c6fd13 (patch) | |
| tree | 38103c04c5b7a9dc90620c619e44f9633569a6c5 /test/test_cache.py | |
| parent | 6a5a1bafd0a24ca1b91a972c2f8042d61eaeea7a (diff) | |
| download | chroma-f6fa4739cc476b21b755522e252ebfbb81c6fd13.tar.gz chroma-f6fa4739cc476b21b755522e252ebfbb81c6fd13.tar.bz2 chroma-f6fa4739cc476b21b755522e252ebfbb81c6fd13.zip | |
Speed up node intersection by 2.5x using tips from "Optimizing ray
tracing for CUDA" by Hannu Saransaari.
The intersect_box() function has been rewritten to be much shorter and
use the min() and max() functions, which map directly to hardware
instructions. Additionally, the calculations inside intersect_box()
have been reorganized to allow the compiler to use the combined
multiply-add instruction, instead of doing a subtraction followed by a
division (which is way slower).
Diffstat (limited to 'test/test_cache.py')
0 files changed, 0 insertions, 0 deletions