赞
踩
官方文档地址:https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html
NVIDIA CUDA Toolkit 的发行说明可访问 https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html
Note: 发行说明已重组为两个主要部分:通用 CUDA 的发行说明和 CUDA libraries 的发行说明,包括 12.x 版本的历史信息。
从 CUDA 11 开始,Toolkit 中的各个组件的版本都是相互独立的。
下表列出了 CUDA 12.0 的对应版本:
组件名称 | 版本信息 | 支持的 Architectures | 支持的平台 |
---|---|---|---|
CUDA C++ 核心计算库:Thrust | 2.0.1 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA C++ 核心计算库:CUB | 2.0.1 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA C++ 核心计算库:libcu++ | 1.9.0 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA C++ 核心计算库:Cooperative Groups | 12.0.0 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA Compatibility | 12.0.31752801 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA Runtime (cudart) | 12.0.107 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
cuobjdump | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUPTI | 12.0.90 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuxxfilt (demangler) | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA Demo Suite | 12.0.76 | x86_64 | Linux, Windows |
CUDA GDB | 12.0.90 | x86_64, POWER, aarch64-jetson | Linux, WSL |
CUDA Nsight Eclipse Plugin | 12.0.78 | x86_64, POWER | Linux |
CUDA NVCC | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA nvdisasm | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows |
CUDA NVML Headers | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA nvprof | 12.0.90 | x86_64, POWER | Linux, Windows |
CUDA nvprune | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA NVRTC | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
NVTX | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA NVVP | 12.0.90 | x86_64, POWER | Linux, Windows |
CUDA OpenCL | 12.0.76 | x86_64 | Linux, Windows |
CUDA Profiler API | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA Compute Sanitizer API | 12.0.90 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuBLAS | 12.0.1.189 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuDLA | 12.0.76 | aarch64-jetson | Linux |
CUDA cuFFT | 11.0.0.21 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuFile | 1.5.0.59 | x86_64 | Linux |
CUDA cuRAND | 10.3.1.50 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuSOLVER | 11.4.2.57 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA cuSPARSE | 12.0.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA NPP | 12.0.0.30 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA nvJitLink | 12.0.76 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA nvJPEG | 12.0.0.28 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
CUDA NVVM Samples | 12.0.94 | x86_64, POWER, aarch64-jetson | Linux, Windows |
Nsight Compute | 2022.4.0.15 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL (Windows 11) |
Nsight Systems | 2022.4.2.18 | x86_64, POWER, aarch64-jetson | Linux, Windows, WSL |
Nsight Visual Studio Edition (VSE) | 2022.4.0.22322 | x86_64 (Windows) | Windows |
nvidia_fs | 2.14.12 | x86_64, aarch64-jetson | Linux |
Visual Studio Integration | 12.0.76 | x86_64 (Windows) | Windows |
NVIDIA Linux Driver(Linux 驱动程序) | 525.60.13 | x86_64, POWER, aarch64-jetson | Linux |
NVIDIA Windows Driver(Windows 驱动程序) | 527.41 | x86_64 (Windows) | Windows, WSL |
运行 CUDA 应用程序需要保证操作系统满足如下条件:
有关支持 CUDA 的各种 GPU 产品的更多信息,可访问 https://developer.nvidia.com/cuda-gpus。
CUDA Toolkit 的每个版本都需要 CUDA 驱动程序达到对应的最低版本。CUDA 驱动程序是向后兼容的,即使用 CUDA 的特定版本开发的应用程序将在后续(更高版本)的驱动程序中正常运行。
有关兼容性的更多信息,可访问 https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html#cuda-compatibility-and-upgrades。
Note: 从 CUDA 11.0 版本开始,Toolkit 组件单独进行版本空间,toolkit 的版本如下表(表 2)所示。
CUDA 各二级版本所需的 CUDA 驱动程序的最低版本如下表所示。CUDA 各二级版本的兼容性详见 https://docs.nvidia.com/deploy/cuda-compatibility/index.html。
CUDA Toolkit | Linux x86_64 Driver Version | Windows x86_64 Driver Version |
---|---|---|
CUDA 12.0.x | >=525.60.13 | >=527.41 |
CUDA 11.8.x | >=450.80.02 | >=452.39 |
CUDA 11.7.x | >=450.80.02 | >=452.39 |
CUDA 11.6.x | >=450.80.02 | >=452.39 |
CUDA 11.5.x | >=450.80.02 | >=452.39 |
CUDA 11.4.x | >=450.80.02 | >=452.39 |
CUDA 11.3.x | >=450.80.02 | >=452.39 |
CUDA 11.2.x | >=450.80.02 | >=452.39 |
CUDA 11.1 (11.1.0) | >=450.80.02 | >=452.39 |
CUDA 11.0 (11.0.3) | >=450.36.06** | >=451.22** |
在兼容模式下,可能允许使用与 Toolkit 驱动程序版本不同的最低要求版本 —— 详见 CUDA Compatibility Guide。
CUDA 11.0 与 早期的驱动程序版本一起发布,但通过升级到 Tesla Recommended Drivers 450.80.02(Linux)/452.39(Windows)可以适配 CUDA Toolkit 11.x 大版本的最低驱动程序版本要求。
The version of the development NVIDIA GPU Driver packaged in each CUDA Toolkit release is shown below.
各 CUDA Toolkit 版本中封装的 development NVIDIA GPU Driver 版本如下表所示。
CUDA Toolkit | Linux x86_64 Driver Version | Windows x86_64 Driver Version |
---|---|---|
CUDA 12.0 GA | >=525.60.13 | >=527.41 |
CUDA 11.8 GA | >=520.61.05 | >=520.06 |
CUDA 11.7 Update 1 | >=515.48.07 | >=516.31 |
CUDA 11.7 GA | >=515.43.04 | >=516.01 |
CUDA 11.6 Update 2 | >=510.47.03 | >=511.65 |
CUDA 11.6 Update 1 | >=510.47.03 | >=511.65 |
CUDA 11.6 GA | >=510.39.01 | >=511.23 |
CUDA 11.5 Update 2 | >=495.29.05 | >=496.13 |
CUDA 11.5 Update 1 | >=495.29.05 | >=496.13 |
CUDA 11.5 GA | >=495.29.05 | >=496.04 |
CUDA 11.4 Update 4 | >=470.82.01 | >=472.50 |
CUDA 11.4 Update 3 | >=470.82.01 | >=472.50 |
CUDA 11.4 Update 2 | >=470.57.02 | >=471.41 |
CUDA 11.4 Update 1 | >=470.57.02 | >=471.41 |
CUDA 11.4.0 GA | >=470.42.01 | >=471.11 |
CUDA 11.3.1 Update 1 | >=465.19.01 | >=465.89 |
CUDA 11.3.0 GA | >=465.19.01 | >=465.89 |
CUDA 11.2.2 Update 2 | >=460.32.03 | >=461.33 |
CUDA 11.2.1 Update 1 | >=460.32.03 | >=461.09 |
CUDA 11.2.0 GA | >=460.27.03 | >=460.82 |
CUDA 11.1.1 Update 1 | >=455.32 | >=456.81 |
CUDA 11.1 GA | >=455.23 | >=456.38 |
CUDA 11.0.3 Update 1 | >= 450.51.06 | >= 451.82 |
CUDA 11.0.2 GA | >= 450.51.05 | >= 451.48 |
CUDA 11.0.1 RC | >= 450.36.06 | >= 451.22 |
CUDA 10.2.89 | >= 440.33 | >= 441.22 |
CUDA 10.1 (10.1.105 general release, and updates) | >= 418.39 | >= 418.96 |
CUDA 10.0.130 | >= 410.48 | >= 411.31 |
CUDA 9.2 (9.2.148 Update 1) | >= 396.37 | >= 398.26 |
CUDA 9.2 (9.2.88) | >= 396.26 | >= 397.44 |
CUDA 9.1 (9.1.85) | >= 390.46 | >= 391.29 |
CUDA 9.0 (9.0.76) | >= 384.81 | >= 385.54 |
CUDA 8.0 (8.0.61 GA2) | >= 375.26 | >= 376.51 |
CUDA 8.0 (8.0.44) | >= 367.48 | >= 369.30 |
CUDA 7.5 (7.5.16) | >= 352.31 | >= 353.66 |
CUDA 7.0 (7.0.28) | >= 346.46 | >= 347.62 |
为方便起见,NVIDIA 驱动程序是作为 CUDA Toolkit 安装的一部分安装的。请注意,此驱动程序用于开发模式,不建议用于 Tesla GPU 的生产模式。
如需在生产模式中使用 Tesla GPU 的 CUDA 应用程序,建议从 NVIDIA 驱动程序下载网站下载 Tesla GPU 的最新驱动程序,网址为 https://www.nvidia.com/drivers。
在安装 Cuda Toolkit 的过程中,如下情况可能会导致跳过 NVIDA 驱动程序的安装:
有关在 Windows 系统自定义安装过程的详细信息,请参阅 https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html#install-cuda-software。
有关在 Linux 系统自定义安装过程的详细信息,请参阅 https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#package-manager-metas。
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。