Search found 209 matches

by acasta69
Thu May 21, 2020 5:15 pm
Forum: Development
Topic: Unified executable (for CPU-only, OpenCL and CUDA)
Replies: 62
Views: 8652

Re: Unified executable (for CPU-only, OpenCL and CUDA)

- you can compile the LuxCore sources without having to use OpenCL or CUDA SDK; Do you mean this should work even if compiled with OpenCL "disabled"? There is a problem, though: https://dev.azure.com/LuxCoreRender/LuxCoreRender/_build/results?buildId=2196&view=results These errors happen with no-oc...
by acasta69
Thu May 21, 2020 1:58 pm
Forum: Development
Topic: LuxCore API and Unicode UTF-8 support
Replies: 4
Views: 951

Re: LuxCore API and Unicode UTF-8 support

At the moment, I have done some test only on Linux and it seems to works fine with not-latin languages. I assume MacOS will work too. We need to check Windows. I tried some very simple test on Windows using a filename with non-latin characters: LuxCoreUI opens and renders correctly a file called 'ש...
by acasta69
Sat May 16, 2020 9:02 am
Forum: Development
Topic: What is differance?
Replies: 5
Views: 865

Re: What is differance?

The difference is that with the first two builds you can choose GPU-based render engines (e.g. PathOCL), having much better performance in many cases. The first build has Cuda enabled: you can use it if you have a suitable Nvidia GPU. Many users reported better performance using the Cuda build with ...
by acasta69
Wed May 13, 2020 9:03 pm
Forum: User Support
Topic: GPU rendering slower than CPU rendering
Replies: 18
Views: 2324

Re: v2.3 Vs v2.4 performance

I find the same very strange behaviour with TAO's scene, i.e. GPU is very slow, with LuxCoreUI 2.2 (but 2.4 is ok).
This line in the config file seems to be the source of the problem, at least on my laptop:

Code: Select all

opencl.gpu.workgroup.size = "0"
If I comment it, then GPU speed is again very high.
by acasta69
Sat May 02, 2020 8:59 am
Forum: Development
Topic: v2.3 Vs v2.4 performance
Replies: 39
Views: 5532

Re: v2.3 Vs v2.4 performance

Repeated tests without PhotonGI and denoiser, same versions as my previous posts, + latest version (with Cache Friendly Samplers): LuxCore2.3 OpenCL: 7906 rays/sec LuxCore2.4alpha0 OpenCL, build 20200430.12: 5325 rays/sec LuxCore2.4alpha0 CUDA, build 20200430.12: 5079 rays/sec LuxCore2.4alpha0 OpenC...
by acasta69
Fri May 01, 2020 1:17 pm
Forum: Development
Topic: v2.3 Vs v2.4 performance
Replies: 39
Views: 5532

Re: v2.3 Vs v2.4 performance

Dade wrote:
Fri May 01, 2020 1:12 pm
A 970 GTX can not be 7 times slower than a 2070 RTX :!:
Indeed! I dont' understand if it can be something broken on my system or not...
I tested both with Azure-built and self-built binaries, results are the same.
by acasta69
Fri May 01, 2020 1:06 pm
Forum: Development
Topic: v2.3 Vs v2.4 performance
Replies: 39
Views: 5532

Re: v2.3 Vs v2.4 performance

Here are results with GTX970 (2.3 vs. 2.4 build 20200430.12): LuxCore2.3.jpg LuxCore2.4alpha0_OpenCL.jpg LuxCore2.4alpha0_CUDA.jpg On this card CUDA underperforms OpenCL quite a bit... :? Anyone else with this or similar GPU series can confirm? P.S. With the very latest build, LuxCoreUI exits withou...
by acasta69
Wed Apr 29, 2020 10:06 am
Forum: Development
Topic: PATHGPU with OpenCL and CUDA support
Replies: 78
Views: 10042

Re: PATHGPU with OpenCL and CUDA support

Version 418 seems compatible with 10.1 toolkit, see here:
https://docs.nvidia.com/cuda/cuda-toolk ... index.html
Versions are not shown for MacOS, but I guess major number cannot differ too much.

If you build with toolkit 10.2, you are probably going to need an updated driver.
by acasta69
Wed Apr 29, 2020 6:51 am
Forum: Development
Topic: Windows Build FAILED
Replies: 107
Views: 14580

Re: Windows Build FAILED

Hi, I test only small scenes but does anybody have the same performance boost like me? It is about 1.8 times faster than OCL on my stone age GTX 760. I have a similar boost result on my old (gtx960 4gb) I get errors with latest build and OpenCL and the food demo scene, too, e.g. PATHOCL:clFinish(CL...
by acasta69
Mon Apr 27, 2020 7:44 pm
Forum: Development
Topic: Windows Build FAILED
Replies: 107
Views: 14580

Re: Windows Build FAILED

This is probably because we are the one to load the main nvrtc64_101_0.dll while it is the nvrtc64_101_0.dll to load nvrtc-builtins64_101.dll. Different settings may apply to the two different DLL loads. The first load probably uses the Python settings while the second may only use the System one :...