支持CUDA 5的GPU上不受支持的GPU架构compute_30 [英] Unsupported gpu architecture compute_30 on a CUDA 5 capable gpu

问题描述

我目前正在尝试在最新的CUDA工具包(版本11.1)上编译darknet.我有一个能够运行CUDA版本5(即GeForce 940M)的GPU.但是，在使用最新的cuda工具包重建Darknet时，它表示

I'm currently trying to compile darknet on the latest CUDA toolkit which is version 11.1. I have a GPU capable of running CUDA version 5 which is a GeForce 940M. However, while rebuilding darknet using the latest cuda toolkit, it said

nvcc致命:不支持的GPU架构'compute_30'

nvcc fatal : Unsupported gpu architecture 'compute_30'

compute_30适用于版本3，当我的gpu可以运行版本5时它怎么会失败我的代码是否有可能检测到了我的英特尔图形卡，而不是我的nvidia gpu?如果是这样，是否可以更改其检测?

compute_30 is for version 3, how can it fail while my gpu can run version 5 Is it possible that my code detected my intel graphics card instead of my nvidia gpu? if that's the case, is it possible to change its detection?

推荐答案

Support for compute_30 has been removed for versions after CUDA 10.2. So if you are using nvcc make sure to use this flag to target the correct architecture in the build system for darknet

-gencode=arch=compute_50,code=sm_50

您可能还需要使用此代码，以避免警告不推荐使用的体系结构.

You may also need to use this one to avoid a warning of architectures are deprecated.

-Wno-deprecated-gpu-targets 

这篇关于支持CUDA 5的GPU上不受支持的GPU架构compute_30的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！