Unsupported gpu architecture 'compute_110'

[mahmoodn]

Hi,
When I want to build the matrixMul sample, I see this error:

[ 33%] Building CUDA object CMakeFiles/matrixMul.dir/matrixMul.cu.o
nvcc fatal   : Unsupported gpu architecture 'compute_110'

The device and driver versions are shown below:

$ nvidia-smi
Mon Dec 15 04:26:04 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.90.07              Driver Version: 550.90.07      CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA A100-SXM4-80GB          Off |   00000000:CA:00.0 Off |                    0 |
| N/A   24C    P0             59W /  225W |       1MiB /  81920MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Wed_Jan_15_19:20:09_PST_2025
Cuda compilation tools, release 12.8, V12.8.61
Build cuda_12.8.r12.8/compiler.35404655_0

It should be fine because the list of architectures is set(CMAKE_CUDA_ARCHITECTURES 75 80 86 87 89 90 100 110 120), but I don't know why that error is shown. Any idea about that?

[HHHskkk]

checkout to v12.8 branch and test again, your nvidia-smi output show cuda max version is 12.4, but nvcc version is 12.8