- Overview
The NVIDIA CUDA Deep Neural Network library (cuDNN) is a GPU-accelerated library
of primitives for deep neural networks.
cuDNN provides highly tuned implementations for standard routines such as forward
and backward convolution, pooling, normalization, and activation layers.
cuDNN is part of the NVIDIA Deep Learning SDK.
Deep learning researchers and framework developers worldwide rely on cuDNN for
high-performance GPU acceleration.
It allows them to focus on training neural networks and developing software
applications rather than spending time on low-level GPU performance tuning.
cuDNN accelerates widely used deep learning frameworks, including Caffe, Caffe2,
TensorFlow, Theano, Torch, PyTorch, MXNet, and Microsoft Cognitive Toolkit.
cuDNN is freely available to members of the NVIDIA Developer Program.
- install
2.1 Prerequisites
Ensure you meet the following requirements before you install cuDNN.
A GPU of compute capability 3.0 or higher. To understand the compute capability of the GPU on your system, see: CUDA GPUs.
If you are using cuDNN with a Volta GPU, version 7 or later is required.
One of the following supported platforms:
Ubuntu 14.04
Ubuntu 16.04
POWER8
One of the following supported CUDA versions and NVIDIA graphics driver:
NVIDIA graphics driver 375.88 or newer for CUDA 8
NVIDIA graphics driver 384.81 or newer for CUDA 9
For more information, see
Installing NVIDIA Graphics Drivers
Installing CUDA
2.2 Downloading cuDNN
Go to: NVIDIA cuDNN home page. (https://developer.nvidia.com/cudnn\)
Click Download.
Login Site.
Accept the Terms and Conditions. A list of available download versions of cuDNN displays.
Select the cuDNN version you want to install. A list of available resources displays.
2.3 installing cuDNN
Navigate to your <cudnnpath> directory containing cuDNN Debian file.
Install the runtime library, for example:
sudo dpkg -i libcudnn7_7.0.5.15-1+cuda9.1_amd64.deb
Install the developer library, for example:
sudo dpkg -i libcudnn7-dev_7.0.5.15-1+cuda9.1_amd64.deb
Install the code samples and the cuDNN Library User Guide, for example:
sudo dpkg -i libcudnn7-doc_7.0.5.15-1+cuda9.1_amd64.deb
2.4 Verify
2.4.1 Copy the cuDNN sample to a writable path.
$cp -r /usr/src/cudnn\_samples\_v7/ $HOME
2.4.2 Go to the writable path.
$ cd $HOME/cudnn\_samples\_v7/mnistCUDNN
2.4.3 Compile the mnistCUDNN sample.
$make clean && make
2.4.4 Run the mnistCUDNN sample.
$ ./mnistCUDNN
If cuDNN is properly installed and running on your Linux system, you will see a message similar to the following:
Test passed!