Ubuntu服务器上的NVIDA CUDA
2017年11月3日
在上一篇有关在Ubuntu上进行以太坊挖矿的文章中,我最后指出要获得NVIDIA的CUDA驱动程序需要花费什么。在某些应用程序中使用CUDA驱动程序可以进一步释放我的NVIDIA GTX 1070显卡的性能,特别是在进行以太坊挖矿时可以证明其改进。
这篇文章将演示CUDA驱动程序的两种安装方法:
- Ubuntu软件包存档
- NVIDIA套件档案
Ubuntu软件包存档
从存档安装非常简单快捷。所需要做的就是安装nvidia-cuda-toolkit软件包,它还将获取所有必需的CUDA库和工具:
sudo apt update
sudo apt install nvidia-cuda-toolkit
sudo shutdown -r now
重新启动后,要验证是否已安装CUDA驱动程序,可以通过以下三种方法来检查一切是否正常运行:
- 检查/ dev中是否存在nvidia *设备文件
- 使用nvcc命令显示已安装的驱动程序版本
- 运行nvidia-smi以获取有关设备的详细版本,例如电源和风扇信息,使用GPU的进程以及驱动程序版本。
这三个示例的输出如下:
$ ls /dev/nvidia*
/dev/nvidia0 /dev/nvidiactl /dev/nvidia-uvm
$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2015 NVIDIA Corporation
Built on Tue_Aug_11_14:27:32_CDT_2015
Cuda compilation tools, release 7.5, V7.5.17
$ nvidia-smi
Sat Oct 28 14:17:15 2017
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.90 Driver Version: 384.90 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 1070 Off | 00000000:01:00.0 On | N/A |
| 0% 49C P8 11W / 185W | 99MiB / 8110MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1170 G /usr/lib/xorg/Xorg 97MiB |
+-----------------------------------------------------------------------------+
NVIDIA封装档案
本节将寻求直接从NVIDIA本身下载库,以获取软件包的最新版本。NVIDIA repo还包含各种元数据包,使最终用户可以将安装限制为所需的库,运行时或工具包,而不是安装所有内容。
NVIDIA运行一个存储库,可以将其添加到apt,然后直接从中安装。使用此存储库意味着安装将保持最新。我将使用CUDA元软件包,该软件包将安装所有CUDA工具包和驱动程序软件包,并在发布新版本时进行升级:
echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/ /" | sudo tee /etc/apt/sources.list.d/cuda.list
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub
sudo apt update
sudo apt install cuda
sudo shutdown -r now
最后一步是需要修改路径以指向二进制文件:
export PATH=/usr/local/cuda-9.0/bin${PATH:+:${PATH}}
测试CUDA
/ dev,nvcc和nvidia-smi的输出类似于下面的存档中的安装:
$ ls /dev/nvidia*
/dev/nvidia0 /dev/nvidiactl /dev/nvidia-modeset /dev/nvidia-uvm /dev/nvidia-uvm-tools
$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2017 NVIDIA Corporation
Built on Fri_Sep__1_21:08:03_CDT_2017
Cuda compilation tools, release 9.0, V9.0.176
$ nvidia-smi
Sat Oct 28 15:57:59 2017
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.90 Driver Version: 384.90 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 1070 Off | 00000000:01:00.0 On | N/A |
| 0% 41C P8 10W / 185W | 121MiB / 8110MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1181 G /usr/lib/xorg/Xorg 119MiB |
+-----------------------------------------------------------------------------+
此外,该软件包还附带了一些有趣的脚本,可在参考资料中找到/usr/local/cuda/extras/demo_suite
。
设备查询
$ /usr/local/cuda/extras/demo_suite/deviceQuery
./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "GeForce GTX 1070"
CUDA Driver Version / Runtime Version 9.0 / 9.0
CUDA Capability Major/Minor version number: 6.1
Total amount of global memory: 8111 MBytes (8504868864 bytes)
(15) Multiprocessors, (128) CUDA Cores/MP: 1920 CUDA Cores
GPU Max Clock rate: 1797 MHz (1.80 GHz)
Memory Clock rate: 4004 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 2097152 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.0, CUDA Runtime Version = 9.0, NumDevs = 1
Result = PASS
带宽测试
$ /usr/local/cuda/extras/demo_suite/bandwidthTest
[CUDA Bandwidth Test] - Starting...
Running on...
Device 0: GeForce GTX 1070
Quick Mode
Host to Device Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 12665.1
Device to Host Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 12916.1
Device to Device Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 190526.5
Result = PASS
NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.