Cool VL Viewer forum http://sldev.free.fr/forum/ |
|
Some AVX2 / SSE2 optimization for llface.cpp http://sldev.free.fr/forum/viewtopic.php?f=10&t=2086 |
Page 2 of 2 |
Author: | Henri Beauchamp [ 2020-11-01 23:53:22 ] |
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp |
EDIT: Found the bug in Kathrine's SSE2 code: a _mm_add_ps used for tvv instead of _mm_sub_ps... |
Author: | ZaneZimer [ 2020-11-02 00:27:27 ] | |||||||||
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp | |||||||||
|
Author: | Henri Beauchamp [ 2020-11-02 00:30:11 ] |
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp |
No need any more: found the bug (see my edit above). Thank you ! |
Author: | ZaneZimer [ 2020-11-02 00:31:47 ] | |||||||||
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp | |||||||||
|
Author: | Henri Beauchamp [ 2020-11-02 00:32:18 ] | ||
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp | ||
Fixed patch:
|
Author: | ZaneZimer [ 2020-11-02 00:33:41 ] | |||||||||
Post subject: | Re: Some AVX2 / SSE2 optimization for llface.cpp | |||||||||
*Edit: I have applied the new patch, built and can verify that corrects the texture orientation issue that I had. |
Page 2 of 2 | All times are UTC |
Powered by phpBB® Forum Software © phpBB Group https://www.phpbb.com/ |