nvcc fatal : Unsupported gpu architecture 'compute_20' WHILE BUILDING

[yyxr75]

Dear everyone, I'm in trouble when building this demo as the title shows. Error message goes like below:

CMake Error at kfusion_generated_imgproc.cu.o.cmake:207 (message): Error generating /home/yang/Desktop/KinFu-Demo/kinfu-remake/build/kfusion/CMakeFiles/kfusion.dir/src/cuda/./kfusion_generated_imgproc.cu.o

It is like I could not build out the output file "kfusion_generated_imgproc.cu.o " because of the nvcc fatal problem.

I've consulted the solution from the Internet which says I should modify my Makefile.config. But I have so many files containing these messages which makes me so confusing to do with them. I wonder whether you have a solution about this. Thank you all.

Here is my email address： [email protected]

I am doing the Kinect fusion on Intel-realsense-D400x.

This is my error message below:

[ 7%] Building NVCC (Device) object kfusion/CMakeFiles/kfusion.dir/src/cuda/kfusion_generated_imgproc.cu.o nvcc fatal : Unsupported gpu architecture 'compute_20' CMake Error at kfusion_generated_imgproc.cu.o.cmake:207 (message): Error generating /home/yang/Desktop/KinFu-Demo/kinfu-remake/build/kfusion/CMakeFiles/kfusion.dir/src/cuda/./kfusion_generated_imgproc.cu.o

kfusion/CMakeFiles/kfusion.dir/build.make:77: recipe for target 'kfusion/CMakeFiles/kfusion.dir/src/cuda/kfusion_generated_imgproc.cu.o' failed make[2]: *** [kfusion/CMakeFiles/kfusion.dir/src/cuda/kfusion_generated_imgproc.cu.o] Error 1 CMakeFiles/Makefile2:85: recipe for target 'kfusion/CMakeFiles/kfusion.dir/all' failed make[1]: *** [kfusion/CMakeFiles/kfusion.dir/all] Error 2 Makefile:127: recipe for target 'all' failed make: *** [all] Error 2

And my cuda version:

Detected 1 CUDA Capable device(s)

Device 0: "GeForce 710M" CUDA Driver Version / Runtime Version 9.1 / 9.0 CUDA Capability Major/Minor version number: 2.1 Total amount of global memory: 1985 MBytes (2081816576 bytes) MapSMtoCores for SM 2.1 is undefined. Default to use 64 Cores/SM MapSMtoCores for SM 2.1 is undefined. Default to use 64 Cores/SM ( 2) Multiprocessors, ( 64) CUDA Cores/MP: 128 CUDA Cores GPU Max Clock rate: 1550 MHz (1.55 GHz) Memory Clock rate: 900 Mhz Memory Bus Width: 64-bit L2 Cache Size: 131072 bytes Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65535), 3D=(2048, 2048, 2048) Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers Total amount of constant memory: 65536 bytes Total amount of shared memory per block: 49152 bytes Total number of registers available per block: 32768 Warp size: 32 Maximum number of threads per multiprocessor: 1536 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (65535, 65535, 65535) Maximum memory pitch: 2147483647 bytes Texture alignment: 512 bytes Concurrent copy and kernel execution: Yes with 1 copy engine(s) Run time limit on kernels: No Integrated GPU sharing Host Memory: No Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Disabled Device supports Unified Addressing (UVA): Yes Supports Cooperative Kernel Launch: No Supports MultiDevice Co-op Kernel Launch: No Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0 Compute Mode: < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.1, CUDA Runtime Version = 9.0, >NumDevs = 1 Result = PASS

[yyxr75]

NICE, I have done it with the help of

Fixed kinfu_remake to run in CUDA_ARCH >= 500 and CUDA_VERSION >= 9 #33

THANKS A LOT