ashwin / gDel3D

gDel3D is the fastest 3D Delaunay triangulation algorithm. It uses the GPU for massive parallelism.

Home Page:https://github.com/ashwin/gDel3D

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

CUDA error 8

BEBULAE opened this issue · comments

Hello! When running this program, I came across two problems which say " CUDA error 8 [c:\program files\nvidia gpu computing toolkit\cuda\v10.0\include\thrust\system\cuda\detail\cub\iterator../util_device.cuh, 151]: invalid device function " and " CUDA error 48 [C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\include\thrust/system/cuda/detail/parallel_for.h, 143]: no kernel image is available for execution on the device "
I don't know why.
I use Microsoft Visual Studio 2017 and CUDA 10.0 with RTX 2060.
The problem occurs when I run demo.cpp, in line 85 " triangulator.compute( pointVec, &output ); " . Then I click on this function and jump to " GpuDelaunay.cu " . Then I find that the program stopped in line 89 " initForFlip ( pointVec ) ". I click on this and jump to line 611. It seems there is a problem in " RealPtr coords( ( RealType* ) toKernelPtr( _pointVec ) ); ".
By the way, In " GPUDecl.h " line 309, the " assign ( ) " function doesn't work either.
I'm in urgent need of help.
Thank you !