Nvcc fatal : Unsupported gpu architecture 'compute_35', cdnn installation problem

AI & Data Science Deep Learning (Training & Inference) cuDNN
1

Hello there,

Im trying to install Cudnn on my laptop with the following specs:

Model: MSI GS43VR 7RE
OS: Ubuntu 22.04 LTS
GPU: GTX1060M
NVDA Driver: nvidia-driver-525
CUDA: 12.0

However, when Im trying to compile the mnistCUDNN sample, the following error message shows:

CUDA_VERSION is 12000
Linking agains cublasLt = true
CUDA VERSION: 12000
TARGET ARCH: x86_64
HOST_ARCH: x86_64
TARGET OS: linux
SMS: 35 50 53 60 61 62 70 72 75 80 86 87
/usr/local/cuda/bin/nvcc -I/usr/local/cuda/include -I/usr/local/cuda/targets/x86_64-linux/include -IFreeImage/include -ccbin g++ -m64 -gencode arch=compute_35,code=sm_35 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_53,code=sm_53 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_62,code=sm_62 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_72,code=sm_72 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_87,code=sm_87 -gencode arch=compute_87,code=compute_87 -o fp16_dev.o -c fp16_dev.cu
nvcc fatal : Unsupported gpu architecture ‘compute_35’
make: *** [Makefile:241: fp16_dev.o] Error 1

Does anyone know how to solve this issue? I spent days looking for solution but couldn’t find one… >_<|||

Thanks in advance!

Sincerely,
Tse Lin

2

Hi @mr.lintse ,
Can you pls confirm if you are using the compatible versions from here.
Thanks!

3

Dear Sir,

I have solved the problem! It was due to mismatch between CUDA and CUDNN versions. I downgraded CUDA to 11.8, and then everything worked out fine!

Anyway, thank you for the reply!

Sincerely,
Tse Lin

1 Like