【最新】cuDNN在CUDA11.7+Ubuntu20.04下的安装及卸载

已于 2022-11-03 10:29:54 修改
阅读量4.9k 收藏 38
点赞数 11
分类专栏： install 文章标签： linux ubuntu 深度学习
于 2022-10-24 13:38:34 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_54470372/article/details/127473509
版权

CUDA11.7已经安装好了，现在安装cuDNN

1、卸载

（1）查询

sudo dpkg -l | grep cudnn

$ sudo dpkg -l | grep cudnn
ii  cudnn-local-repo-ubuntu2004-8.6.0.163      1.0-1                               amd64        cudnn-local repository configuration files
ii  libcudnn8                                  8.6.0.163-1+cuda11.8                amd64        cuDNN runtime libraries
ii  libcudnn8-dev                              8.6.0.163-1+cuda11.8                amd64        cuDNN development libraries and headers
ii  libcudnn8-samples                          8.6.0.163-1+cuda11.8                amd64        cuDNN samples

（2）卸载

$ sudo dpkg -r libcudnn8-samples
(Reading database ... 227274 files and directories currently installed.)
Removing libcudnn8-samples (8.6.0.163-1+cuda11.8) ...
$ sudo dpkg -r libcudnn8-dev
(Reading database ... 227208 files and directories currently installed.)
Removing libcudnn8-dev (8.6.0.163-1+cuda11.8) ...
update-alternatives: removing manually selected alternative - switching libcudnn to auto mode
$ sudo dpkg -r libcudnn8
(Reading database ... 227175 files and directories currently installed.)
Removing libcudnn8 (8.6.0.163-1+cuda11.8) ...

注意cudnn-local-repo-ubuntu2004-8.6.0.163要用purge命令删除

否则会提示：ignoring request to remove cudnn-local-repo-ubuntu2004-8.6.0.163, only the config
 files of which are on the system; use --purge to remove them too

$ sudo apt-get purge cudnn-local-repo-ubuntu2004-8.6.0.163
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following packages will be REMOVED:
  cudnn-local-repo-ubuntu2004-8.6.0.163*
0 upgraded, 0 newly installed, 1 to remove and 0 not upgraded.
After this operation, 0 B of additional disk space will be used.
Do you want to continue? [Y/n] y
(Reading database ... 227143 files and directories currently installed.)
Purging configuration files for cudnn-local-repo-ubuntu2004-8.6.0.163 (1.0-1) ...

（3）再次查询，没有输出则卸载完成

接下来根据官方文档进行下载安装，选择2.3.2. Debian Local Installation

官方文档链接：Installation Guide :: NVIDIA Deep Learning cuDNN Documentation

2、下载

下载链接：https://developer.nvidia.com/rdp/cudnn-download

这里我选择的是Local Installer for Ubuntu20.04 x86_64 (Deb)

​​

下载后得到文件cudnn-local-repo-ubuntu2004-8.5.0.96_1.0-1_amd64.deb

3、安装

r****@r********:~/Downloads$ sudo dpkg -i cudnn-local-repo-ubuntu2004-8.5.0.96_1.0-1_amd64.deb
[sudo] password for r**: 
Selecting previously unselected package cudnn-local-repo-ubuntu2004-8.5.0.96.
(Reading database ... 191620 files and directories currently installed.)
Preparing to unpack cudnn-local-repo-ubuntu2004-8.5.0.96_1.0-1_amd64.deb ...
Unpacking cudnn-local-repo-ubuntu2004-8.5.0.96 (1.0-1) ...
Setting up cudnn-local-repo-ubuntu2004-8.5.0.96 (1.0-1) ...

The public CUDA GPG key does not appear to be installed.
To install the key, run this command:
sudo cp /var/cudnn-local-repo-ubuntu2004-8.5.0.96/cudnn-local-0579404E-keyring.gpg /usr/share/keyrings/

r****@r********:~/Downloads$ sudo cp /var/cudnn-local-repo-ubuntu2004-8.5.0.96/cudnn-local-0579404E-keyring.gpg /usr/share/keyrings/
r****@r********:~/Downloads$ sudo apt-get update
Get:1 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  InRelease [1,575 B]
Get:1 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  InRelease [1,575 B]
Get:2 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  Packages [945 B]                                    
Get:3 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB]                                                           
Hit:4 http://cn.archive.ubuntu.com/ubuntu focal InRelease                                    
Fetched 114 kB in 2s (52.7 kB/s)                                                             
Reading package lists... Done

r***@r******:~/Downloads$ sudo apt-get install libcudnn8=8.5.0.96-1+cuda11.7
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following NEW packages will be installed:
  libcudnn8
0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
Need to get 0 B/347 MB of archives.
After this operation, 892 MB of additional disk space will be used.
Get:1 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  libcudnn8 8.5.0.96-1+cuda11.7 [347 MB]
Selecting previously unselected package libcudnn8.
(Reading database ... 191636 files and directories currently installed.)
Preparing to unpack .../libcudnn8_8.5.0.96-1+cuda11.7_amd64.deb ...
Unpacking libcudnn8 (8.5.0.96-1+cuda11.7) ...
Setting up libcudnn8 (8.5.0.96-1+cuda11.7) ...

r***@r******:~/Downloads$ sudo apt-get install libcudnn8-dev=8.5.0.96-1+cuda11.7
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following NEW packages will be installed:
  libcudnn8-dev
0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
Need to get 0 B/356 MB of archives.
After this operation, 1,050 MB of additional disk space will be used.
Get:1 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  libcudnn8-dev 8.5.0.96-1+cuda11.7 [356 MB]
Selecting previously unselected package libcudnn8-dev.
(Reading database ... 191653 files and directories currently installed.)
Preparing to unpack .../libcudnn8-dev_8.5.0.96-1+cuda11.7_amd64.deb ...
Unpacking libcudnn8-dev (8.5.0.96-1+cuda11.7) ...
Setting up libcudnn8-dev (8.5.0.96-1+cuda11.7) ...
update-alternatives: using /usr/include/x86_64-linux-gnu/cudnn_v8.h to provide /usr/include/cudnn.h (libcudnn) in auto mode

r***@r******:~/Downloads$ sudo apt-get install libcudnn8-samples=8.5.0.96-1+cuda11.7
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following NEW packages will be installed:
  libcudnn8-samples
0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
Need to get 0 B/1,665 kB of archives.
After this operation, 2,169 kB of additional disk space will be used.
Get:1 file:/var/cudnn-local-repo-ubuntu2004-8.5.0.96  libcudnn8-samples 8.5.0.96-1+cuda11.7 [1,665 kB]
Selecting previously unselected package libcudnn8-samples.
(Reading database ... 191686 files and directories currently installed.)
Preparing to unpack .../libcudnn8-samples_8.5.0.96-1+cuda11.7_amd64.deb ...
Unpacking libcudnn8-samples (8.5.0.96-1+cuda11.7) ...
Setting up libcudnn8-samples (8.5.0.96-1+cuda11.7) ...

 运行：

cat /usr/include/x86_64-linux-gnu/cudnn_version_v8.h | grep CUDNN_MAJOR -A 2

$ cat /usr/include/x86_64-linux-gnu/cudnn_version_v8.h | grep CUDNN_MAJOR -A 2
#define CUDNN_MAJOR 8
#define CUDNN_MINOR 5
#define CUDNN_PATCHLEVEL 0
--
#define CUDNN_VERSION (CUDNN_MAJOR * 1000 + CUDNN_MINOR * 100 + CUDNN_PATCHLEVEL)

#endif /* CUDNN_VERSION_H */

 4、测试

r*****@r**********:~/Downloads$ sudo cp -r /usr/src/cudnn_samples_v8/ $HOME
r*****@r**********:~/Downloads$ cd  $HOME/cudnn_samples_v8/mnistCUDNN
r*****@r**********:~/cudnn_samples_v8/mnistCUDNN$ make clean
rm -rf *o
rm -rf mnistCUDNN

 执行make时报错

ra**@r*****:~/cudnn_samples_v8/mnistCUDNN$ make
CUDA_VERSION is 11070
Linking agains cublasLt = true
CUDA VERSION: 11070
TARGET ARCH: x86_64
HOST_ARCH: x86_64
TARGET OS: linux
SMS: 35 50 53 60 61 62 70 72 75 80 86 87
/bin/sh: 1: cannot create test.c: Permission denied
/bin/sh: 1: cannot create test.c: Permission denied
g++: error: test.c: No such file or directory
g++: warning: ‘-x c’ after last input file has no effect
g++: fatal error: no input files
compilation terminated.
>>> WARNING - FreeImage is not set up correctly. Please ensure FreeImage is set up correctly. <<<
[@] /usr/local/cuda/bin/nvcc -I/usr/local/cuda/include -I/usr/local/cuda/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
[@] g++ -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include -o fp16_emu.o -c fp16_emu.cpp
[@] g++ -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include -o mnistCUDNN.o -c mnistCUDNN.cpp
[@] /usr/local/cuda/bin/nvcc -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 mnistCUDNN fp16_dev.o fp16_emu.o mnistCUDNN.o -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib64 -lcublasLt -LFreeImage/lib/linux/x86_64 -LFreeImage/lib/linux -lcudart -lcublas -lcudnn -lfreeimage -lstdc++ -lm

（1）因为有warning：

WARNING - FreeImage is not set up correctly. Please ensure FreeImage is set up correctly.

所以先下载libfreeimage：sudo apt-get install libfreeimage3 libfreeimage-dev

$ sudo apt-get install libfreeimage3 libfreeimage-dev
Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following additional packages will be installed:
  libilmbase24 libjxr0 libopenexr24
The following NEW packages will be installed:
  libfreeimage-dev libfreeimage3 libilmbase24 libjxr0 libopenexr24
0 upgraded, 5 newly installed, 0 to remove and 0 not upgraded.
Need to get 1,113 kB of archives.
After this operation, 5,116 kB of additional disk space will be used.
Do you want to continue? [Y/n] y
Get:1 http://cn.archive.ubuntu.com/ubuntu focal/universe amd64 libilmbase24 amd64 2.3.0-6build1 [75.1 kB]
Get:2 http://security.ubuntu.com/ubuntu focal-security/universe amd64 libopenexr24 amd64 2.3.0-6ubuntu0.5 [592 kB]
Get:3 http://cn.archive.ubuntu.com/ubuntu focal/universe amd64 libjxr0 amd64 1.1-6build1 [158 kB]
Get:4 http://cn.archive.ubuntu.com/ubuntu focal/universe amd64 libfreeimage3 amd64 3.18.0+ds2-1ubuntu3 [269 kB]
Get:5 http://cn.archive.ubuntu.com/ubuntu focal/universe amd64 libfreeimage-dev amd64 3.18.0+ds2-1ubuntu3 [18.8 kB]
Fetched 1,113 kB in 3s (383 kB/s)                                              
Selecting previously unselected package libilmbase24:amd64.
(Reading database ... 191752 files and directories currently installed.)
Preparing to unpack .../libilmbase24_2.3.0-6build1_amd64.deb ...
Unpacking libilmbase24:amd64 (2.3.0-6build1) ...
Selecting previously unselected package libjxr0:amd64.
Preparing to unpack .../libjxr0_1.1-6build1_amd64.deb ...
Unpacking libjxr0:amd64 (1.1-6build1) ...
Selecting previously unselected package libopenexr24:amd64.
Preparing to unpack .../libopenexr24_2.3.0-6ubuntu0.5_amd64.deb ...
Unpacking libopenexr24:amd64 (2.3.0-6ubuntu0.5) ...
Selecting previously unselected package libfreeimage3:amd64.
Preparing to unpack .../libfreeimage3_3.18.0+ds2-1ubuntu3_amd64.deb ...
Unpacking libfreeimage3:amd64 (3.18.0+ds2-1ubuntu3) ...
Selecting previously unselected package libfreeimage-dev.
Preparing to unpack .../libfreeimage-dev_3.18.0+ds2-1ubuntu3_amd64.deb ...
Unpacking libfreeimage-dev (3.18.0+ds2-1ubuntu3) ...
Setting up libjxr0:amd64 (1.1-6build1) ...
Setting up libilmbase24:amd64 (2.3.0-6build1) ...
Setting up libopenexr24:amd64 (2.3.0-6ubuntu0.5) ...
Setting up libfreeimage3:amd64 (3.18.0+ds2-1ubuntu3) ...
Setting up libfreeimage-dev (3.18.0+ds2-1ubuntu3) ...
Processing triggers for libc-bin (2.31-0ubuntu9.9) ...

（2）error

/bin/sh: 1: cannot create test.c: Permission denied
/bin/sh: 1: cannot create test.c: Permission denied
g++: error: test.c: No such file or directory
g++: warning: ‘-x c’ after last input file has no effect
g++: fatal error: no input files

Permission denied，命令前添加sudo，即sudo make，成功

$ sudo make
CUDA_VERSION is 11070
Linking agains cublasLt = true
CUDA VERSION: 11070
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/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 warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
g++ -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include   -o fp16_emu.o -c fp16_emu.cpp
g++ -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include   -o mnistCUDNN.o -c mnistCUDNN.cpp
/usr/local/cuda/bin/nvcc   -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 mnistCUDNN fp16_dev.o fp16_emu.o mnistCUDNN.o -I/usr/local/cuda/include -I/usr/local/cuda/include -IFreeImage/include -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib64 -L/usr/local/cuda/lib64 -lcublasLt -LFreeImage/lib/linux/x86_64 -LFreeImage/lib/linux -lcudart -lcublas -lcudnn -lfreeimage -lstdc++ -lm
nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).

（3）虽然有warning

nvcc warning : The 'compute_35', 'compute_37', 'sm_35', and 'sm_37' architectures are deprecated, and may be removed in a future release

参考：opencv编译时警告vncc warning: The ‘compute_35’, ‘compute_37’, ‘compute_50’, ‘sm_35’, ‘sm_37’ and ‘sm_50’_古典部程序员的博客-CSDN博客_sm_35

Makefile中采用了CUDA中的compute capability 3.5、3.7和5.0这几种计算能力，而这几种计算能力CUDA11.7中可能已经弃用了。参考中作者利用的是CUDA_ARCH_BIN这个选项，而输出的建议是使用Wno-deprecated-gpu-targets这个选项（Use -Wno-deprecated-gpu-targets to suppress warning），我选择不管（手动狗头），反正最后成功输出了test passed

$ ./mnistCUDNN
Executing: mnistCUDNN
cudnnGetVersion() : 8500 , CUDNN_VERSION from cudnn.h : 8500 (8.5.0)
Host compiler version : GCC 9.4.0

There are 1 CUDA capable devices on your machine :
device 0 : sms 34  Capabilities 7.5, SmClock 1650.0 Mhz, MemSize (Mb) 12007, MemClock 7001.0 Mhz, Ecc=0, boardGroupID=0
Using device 0

Testing single precision
Loading binary file data/conv1.bin
Loading binary file data/conv1.bias.bin
Loading binary file data/conv2.bin
Loading binary file data/conv2.bias.bin
Loading binary file data/ip1.bin
Loading binary file data/ip1.bias.bin
Loading binary file data/ip2.bin
Loading binary file data/ip2.bias.bin
Loading image data/one_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 57600 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 184784 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.014976 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.016064 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.025440 time requiring 57600 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.037280 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.235328 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 1.416096 time requiring 184784 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 128000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 4656640 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.034656 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.034848 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.059392 time requiring 128000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.072960 time requiring 4656640 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.198272 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.714656 time requiring 2450080 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Resulting weights from Softmax:
0.0000000 0.9999399 0.0000000 0.0000000 0.0000561 0.0000000 0.0000012 0.0000017 0.0000010 0.0000000 
Loading image data/three_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 57600 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 184784 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.010688 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.011232 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.017952 time requiring 57600 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.034848 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.036608 time requiring 184784 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.040576 time requiring 2057744 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 128000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 4656640 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.032160 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.033760 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.035264 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.056064 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.059520 time requiring 128000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.073248 time requiring 4656640 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Resulting weights from Softmax:
0.0000000 0.0000000 0.0000000 0.9999288 0.0000000 0.0000711 0.0000000 0.0000000 0.0000000 0.0000000 
Loading image data/five_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000008 0.0000000 0.0000002 0.0000000 0.9999820 0.0000154 0.0000000 0.0000012 0.0000006 

Result of classification: 1 3 5

Test passed!

Testing half precision (math in single precision)
Loading binary file data/conv1.bin
Loading binary file data/conv1.bias.bin
Loading binary file data/conv2.bin
Loading binary file data/conv2.bias.bin
Loading binary file data/ip1.bin
Loading binary file data/ip1.bias.bin
Loading binary file data/ip2.bin
Loading binary file data/ip2.bias.bin
Loading image data/one_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 184784 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.010912 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.011424 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.014688 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.034112 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.039360 time requiring 184784 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.041280 time requiring 2057744 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 51584 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 64000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 4656640 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 1433120 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.045632 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.047008 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.059616 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.073056 time requiring 4656640 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.081472 time requiring 51584 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.115200 time requiring 64000 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Resulting weights from Softmax:
0.0000001 1.0000000 0.0000001 0.0000000 0.0000563 0.0000001 0.0000012 0.0000017 0.0000010 0.0000001 
Loading image data/three_28x28.pgm
Performing forward propagation ...
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 2057744 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 184784 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.012288 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.013504 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.014016 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.033408 time requiring 178432 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.036928 time requiring 184784 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.040928 time requiring 2057744 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnGetConvolutionForwardAlgorithm_v7 ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: -1.000000 time requiring 51584 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: -1.000000 time requiring 64000 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: -1.000000 time requiring 4656640 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: -1.000000 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: -1.000000 time requiring 1433120 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Testing cudnnFindConvolutionForwardAlgorithm ...
^^^^ CUDNN_STATUS_SUCCESS for Algo 4: 0.034784 time requiring 2450080 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 0: 0.045024 time requiring 0 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 7: 0.059648 time requiring 1433120 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 5: 0.070400 time requiring 4656640 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 1: 0.077696 time requiring 51584 memory
^^^^ CUDNN_STATUS_SUCCESS for Algo 2: 0.114624 time requiring 64000 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 6: -1.000000 time requiring 0 memory
^^^^ CUDNN_STATUS_NOT_SUPPORTED for Algo 3: -1.000000 time requiring 0 memory
Resulting weights from Softmax:
0.0000000 0.0000000 0.0000000 1.0000000 0.0000000 0.0000714 0.0000000 0.0000000 0.0000000 0.0000000 
Loading image data/five_28x28.pgm
Performing forward propagation ...
Resulting weights from Softmax:
0.0000000 0.0000008 0.0000000 0.0000002 0.0000000 1.0000000 0.0000154 0.0000000 0.0000012 0.0000006 

Result of classification: 1 3 5

Test passed!

weixin_54470372
关注
  • 11
    点赞
  • 踩
  • 38
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
专栏目录
ubuntu20.04显卡驱动,CUDA 安装和卸载,cudnn安装.pdf
07-06
ubuntu20.04显卡驱动安装,CUDA 安装和卸载,cudnn安装教程
Ubuntu 20.04 CUDA&cuDNN安装方法(图文教程)
09-14
在Ubuntu 20.04操作系统中安装CUDA和cuDNN是进行深度学习和高性能计算的重要步骤。CUDA是NVIDIA公司提供的一个并行计算平台，它允许开发者利用GPU的计算能力来加速应用程序。cuDNN（CUDA Deep Neural Network）则是...
Ubuntu22.04 下安装驱动、CUDA、cudnn以及TensorRT
lilin020401的专栏
08-22 8578
Ubuntu22.04 下安装 Anaconda3 + python3.10 + cuda11.7 + cudnn8.4.1.5+ opencv4.5.3
ubuntu纯净卸载CUDA+cudnn【全网最全】
最新发布
Supremelv的博客
04-27 723
使用ubuntu自带的卸载工具卸载。
基于RTX3090的Ubuntu22.04安装cuda11.7和cudnn8.6
weixin_49777848的博客
07-12 3205
本实验基于Linux的Ubuntu系统在搭载RTX3090的显卡后，完成驱动安装后继续安装cuda11.7和cudnn8.6，目的是为了运行CVPR文章Omnipose模型进行COCO数据集训练，下载的软件包包含python3.8、torch2.0.1、torchaudio2.0.2、torchision0.15.2等等。本实验于2023年7月12日实验成功。
win下pytorch安装—cuda11.7 + cudnn8.4 + pytorch1.13安装
qq_37346140的博客
03-22 3643
这里选择默认目录即可，是个安装过程的临时目录，结束后此文件夹会被自动删除。需要注意的是这里并非指定安装目录，若需要指定安装目录，此处需与指定安装目录不同。即可查看显卡适配的cuda版本,要
ubuntu 命令行卸载并清理软件
禄丰的博客
09-26 464
1、删除软件 方法一、如果你知道要删除软件的具体名称，可以使用 sudo apt-get remove --purge 软件名称 sudo apt-get autoremove --purge 软件名称 方法二、如果不知道要删除软件的具体名称，可以使用 dpkg --get-selections | grep ‘软件相关名称’ sudo apt-get purge 一个带cor...
NVIDIA drivers 460+CUDA11.7.0+CUDNN+​Anaconda+Pytorch​
weixin_49035017的博客
09-14 879
NVIDIA drivers 460+CUDA11.7.0+CUDNN+​Anaconda+Pytorch​
在ubuntu下安装cuda+cudnn+anaconda3+pytorch+pycharm流程
04-03
在双系统ubuntu20.04下安装cuda+cudnn+anaconda3+pytorch+pycharm的详细流程，包括安装时各个环节应注意的事项。
在Ubuntu20.04中安装ROS Noetic的方法
09-14
在Ubuntu 20.04中安装ROS Noetic，你需要遵循一系列步骤，确保系统的兼容性和稳定性。 首先，为了能够从ROS的官方仓库下载软件包，你需要更新你的`sources.list`文件。在终端中输入以下命令： ```bash sudo sh -c ...
QT6.0+ubuntu20.04
04-06
ubuntu 20.04 安装QT
cudnn-11.4-windows-x64-v8.2.4.15.zip
09-03
cudnn-11.4-windows-x64-v8.2.4.15.zip
Ubuntu20.04+GTX1060+显卡驱动+CUDA11.8+cuDNN8.5.0
weixin_43229238的博客
11-06 3322
UBUNTU 安装 CUDA toolkit. cudnn
linux 安装 CUDNN
my__blog的博客
07-12 1万+
linux 安装 CUDNN
Ubuntu 20.04 安装NVIDIA显卡驱动+cuda 11.7+cudnn 8.4
耶律大石的博客
12-03 5349
参考： https://zhuanlan.zhihu.com/p/59618999 https://blog.csdn.net/linhai1028/article/details/79445722/ Windows+Ubuntu从双系统安装到CUDA cuDNN docker 配置K21https://blog.csdn.net/qq_45831128/article/details/1270604751）Ubuntu下查看Nvidia显卡的详细信息： 2）查看cuda 版本： 3）查看cudnn版本：
自动执行bash被拒绝 提示/bin/sh: /test.sh: Permission denied
caihuashen的专栏
01-04 7292
弄了个bash后台执行，结果第二天来看log里就一句话： /bin/sh: /data/chs/match.sh: Permission denied 奇了怪了。加了nohup 就可以执行，nohup就是放入后台执行。（我尼玛我以为我一直加了bash -x呢） 原语句：57 13 * * * /data/cdm/match.sh &> /data/cdm/m.log 修改后：22 16
Linux 操作**.sh文件时 Permission denied 解决
u014520797的专栏
05-20 2万+
1、Linux 操作**.sh文件时 Permission denied表示对该文件的权限不够。2、比如说，在部署tars服务时，需要用到create_tars_server.sh，但是出现了-bash: /usr/local/tars/cpp/script/create_tars_server.sh: Permission denied3、那么就需要chmod u+x /usr/local/ta...
Linux中mkdir：cannot create directory问题解决
热门推荐
u013273161的博客
10-12 12万+
1.想使用mkdir命令创建一个目录结果提示 linux-77@ubuntu:~$ mkdir 123 mkdir: cannot create directory ‘123’: No space left on device 2.查询资料是因为$代表普通用户模式，权限不够， 可以进入root帐号在建立文件夹 进入root帐号 ，打 su －（su - 切换到root用户，并转到root用...
如何在ubuntu 2210中安装NVIDIA 515显卡驱动、CUDA 11.7和cuDNN 8.4（2204同样方法）
qq_43226466的博客
07-26 5152
截止到2022年07月26日，本文章的驱动全部为最新。本文讲解如何在最新版的ubuntu2210中安装最新的NVIDIA515显卡驱动、CUDA11.7和cuDNN8.4的系列教程。
ubuntu20.04 cuda 11.7 cudnn8.9
10-02
为了在Ubuntu 20.04上安装CUDA 11.7和cuDNN 8.9，您可以按照以下步骤进行操作： 1. 首先，确保您的系统已经安装了正确的NVIDIA驱动程序，以支持CUDA 11.7。您可以使用以下命令检查您当前的驱动程序版本： ``` nvidia-smi ``` 2. 安装CUDA 11.7。您可以使用以下命令下载CUDA 11.7的安装程序： ``` wget https://developer.download.nvidia.com/compute/cuda/11.7.0/local_installers/cuda_11.7.0_515.43.04_linux.run ``` 3. 授予安装程序执行权限： ``` chmod +x cuda_11.7.0_515.43.04_linux.run ``` 4. 运行安装程序以安装CUDA 11.7： ``` sudo ./cuda_11.7.0_515.43.04_linux.run ``` 5. 安装完成后，您需要配置环境变量。打开您的`.bashrc`文件： ``` nano ~/.bashrc ``` 6. 在文件末尾添加以下行，并保存文件： ``` export PATH=/usr/local/cuda-11.7/bin${PATH:+:${PATH}} export LD_LIBRARY_PATH=/usr/local/cuda-11.7/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}} ``` 7. 更新环境变量： ``` source ~/.bashrc ``` 8. 下载并安装cuDNN 8.9。您可以从NVIDIA官方网站上下载cuDNN 8.9的安装文件，并按照其提供的说明进行安装。 现在，您的Ubuntu 20.04系统上应该已经成功安装了CUDA 11.7和cuDNN 8.9。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值