Question

我试图在Windows上使用gtx 1080来利用cuda，我从nvidia网站上安装了cuda toolkit 10，并使用以下教程在介质上设置环境变量：tutorial 但是，当我在anaconda提示符上运行numba -s命令时，收到以下消息：

Finding cublas
    ERROR: can't locate lib
Finding cusparse
    ERROR: can't locate lib
Finding cufft
    ERROR: can't locate lib
Finding curand
    ERROR: can't locate lib
Finding nvvm
    located at C:\Users\Nimrod Naim\Anaconda3\DLLs\nvvm64_32_0.dll
    finding libdevice for compute_20... ERROR: can't open libdevice for compute_20
    finding libdevice for compute_30... ERROR: can't open libdevice for compute_30
    finding libdevice for compute_35... ERROR: can't open libdevice for compute_35
    finding libdevice for compute_50... ERROR: can't open libdevice for compute_50
Found 1 CUDA devices
id 0     b'GeForce GTX 1080'                              [SUPPORTED]
                      compute capability: 6.1
                           pci device id: 0
                              pci bus id: 7
Summary:
    1/1 devices are supported

因此无法使用numba启用cuda。

您能帮我解决这个问题吗？

谢谢！

Answer 1

对于cublas：sudo apt-get install cuda-cublas-[version]

nvidia-smi给出cuda版本。

默认情况下安装了其他库（对我来说是10-2）。否则，软件包的名称将像cuda-cusparse- [使用补全查看可用版本，取一个好的版本：例如：sudo apt-get install cuda-cusparse-10-2]

现在有同样的问题，解决方法：将这些行放在〜/ .profil中：

export NUMBAPRO_CUDALIB=/usr/local/cuda/lib64
export NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice
export NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so

（请注意，此处的cuda的路径为/ usr / local / cuda /，如果需要，请更正）

Numba：找不到CUDA库

1 个答案: