Ubuntu
nvidia-graphics-drivers-450-server package

nvidia-graphics-drivers-450-server 450.80.02-0ubuntu0.18.04.3 source package in Ubuntu

Changelog

nvidia-graphics-drivers-450-server (450.80.02-0ubuntu0.18.04.3) bionic; urgency=medium

  * debian/templates/dkms_nvidia.conf.in:
    - Drop buildfix_kernel_5.8.patch
  * debian/templates/dkms_nvidia.conf.in,
    debian/templates/nvidia-dkms-flavour.install.in,
    debian/templates/nvidia-dkms-flavour.postinst.in,
    debian/templates/nvidia-dkms-flavour.prerm.in,
    debian/templates/nvidia-kernel-source-flavour.install.in:
    - Change DKMS directory and name adding "-srv". This should fix
      kernel builds now that the 450 and the 450-server drivers share
      the same version.

nvidia-graphics-drivers-450-server (450.80.02-0ubuntu0.18.04.2) bionic; urgency=medium

  * debian/templates/control.in:
    - Add missing comma in cuda provides (LP: #1897910).

nvidia-graphics-drivers-450-server (450.80.02-0ubuntu0.18.04.1) bionic; urgency=medium

  * New upstream release (LP: #1897910):
    - Improvements:
      o Added a new system-level interface using nvidia-capabilities
        via /dev for Multi-Instance GPU (MIG) on NVIDIA A100.
        For more information on these new device node capabilities,
        refer to the MIG user guide.
     o Added support for CUDA compatibility for CUDA 11.1, where CUDA
       11.1 applications will work on supported GPUs when used with
       drivers >= 450.80.00 on Linux. Refer to CUDA Compatibility for
       more information.
    - Fixed Issues:
      o Various security issues were addressed. For additional details
        on the med-high severity issues, review the NVIDIA Security
        Bulletin 5075.
      o Fixed an issue where, when NVLink training encounters a fatal
        error, link training is still considered successful resulting
        in broken nodes assigned to clients. An escape case in the
        NVLink link state reporting caused the driver to report the
        links as "Active" and functional even though the link had
        received a fatal error. This fatal error does not allow
        traffic to be sent over the link, and thus would cause P2P
        apps to fail. This is a reporting issue, but not a
        functionality issue. The lacking reporting case was
        addressed, so the failing link state is properly reported.
      o Fixed a software race condition that caused link training
        failure (CUDA_ERROR_LAUNCH_FAILED). A race condition within
        the driver polling code caused a false failure in some of
        the link training steps. This causes the driver to not
        continue link training even though training actually was
        successful up to that point. The fix corrects these
        sequences so that these false failures no longer happen.
  * debian/templates/control:
    - Provide cuda 11.0-1 and 11.0-1.

 -- Alberto Milone <email address hidden>  Fri, 02 Oct 2020 18:58:37 +0200

Upload details

Uploaded by:
Alberto Milone
Uploaded to:
Bionic
Original maintainer:
Ubuntu Developers
Architectures:
amd64 i386 all
Section:
libs
Urgency:
Medium Urgency

See full publishing history Publishing

Series Pocket Published Component Section

Builds

Bionic: [FULLYBUILT] amd64 [FULLYBUILT] i386

Downloads

File Size SHA-256 Checksum
nvidia-graphics-drivers-450-server_450.80.02.orig-amd64.tar.gz 134.5 MiB 535ba2728f9cb87c392a2963cc85f9d0e51c2dc58d29ce418c4cf1b62fd745d8
nvidia-graphics-drivers-450-server_450.80.02.orig.tar.gz 140 bytes d0356ec72027e126b393d587a2af1069d9d7edeae58669db509ba2239567f515
nvidia-graphics-drivers-450-server_450.80.02-0ubuntu0.18.04.3.debian.tar.xz 51.1 KiB 8973901809240ebeb97663a4dd9587bd436bc7eab4f3a0c4b40615c839e140a9
nvidia-graphics-drivers-450-server_450.80.02-0ubuntu0.18.04.3.dsc 4.4 KiB 26896ea47ad0d77ead3694ed5e157311763d0335925b8fa682aaba1bfe10925e

View changes file

Binary packages built by this source

libnvidia-cfg1-450-server: NVIDIA binary OpenGL/GLX configuration library

 The NVIDIA binary driver provides optimized hardware acceleration of
 OpenGL/GLX/EGL/GLES applications via a direct-rendering X Server
 for graphics cards using NVIDIA chip sets.
 .
 This package contains the libnvidia-cfg.so.1 runtime library.

libnvidia-common-450-server: Shared files used by the NVIDIA libraries

 This package provides a set of files that are required by the NVIDIA
 libraries.

libnvidia-compute-450-server: NVIDIA libcompute package

 This package provides a set of libraries which enable the NVIDIA Server Driver
 to use GPUs for parallel general purpose computation through CUDA and
 OpenCL.

libnvidia-decode-450-server: NVIDIA Video Decoding runtime libraries

 This package includes the NVIDIA CUDA Video Decoder (NVCUVID) library which
 provides an interface to hardware video decoding capabilities on NVIDIA GPUs with CUDA.
 .
 The package also provides a VDPAU (Video Decode and Presentation API for Unix-like
 systems) library for the NVIDIA vendor implementation.

libnvidia-encode-450-server: NVENC Video Encoding runtime library

 The NVENC Video Encoding library provides an interface to video encoder
 hardware on supported NVIDIA GPUs.
 .
 This package contains the nvidia-encode runtime library.

libnvidia-extra-450-server: Extra libraries for the NVIDIA Server Driver

 This package provides an additional set of libraries to be used with
 the NVIDIA Server Driver.

libnvidia-fbc1-450-server: NVIDIA OpenGL-based Framebuffer Capture runtime library

 The NVIDIA OpenGL-based Framebuffer Capture (NvFBCOpenGL) library provides
 a high performance, low latency interface to capture and optionally encode an
 OpenGL framebuffer. NvFBCOpenGL is a private API that is only available to
 approved partners for use in remote graphics scenarios.
 .
 This package contains the NvFBCOpenGL runtime library.

libnvidia-gl-450-server: NVIDIA OpenGL/GLX/EGL/GLES GLVND libraries and Vulkan ICD

 This package provides the NVIDIA OpenGL/GLX/EGL/GLES libraries and the
 Vulkan ICD.

libnvidia-ifr1-450-server: NVIDIA OpenGL-based Inband Frame Readback runtime library

 The NVIDIA OpenGL-based Inband Frame Readback (NvIFROpenGL) library provides
 a high performance, low latency interface to capture and optionally encode an
 OpenGL framebuffer. NvIFROpenGL is a private API that is only available to
 approved partners for use in remote graphics scenarios.
 .
 This package contains the NvIFROpenGL runtime library.

nvidia-compute-utils-450-server: NVIDIA compute utilities

 This package provides utility binaries for paraller general purpose
 computing use cases with the NVIDIA Server Driver.
 .
 CUDA MPS is a feature that allows multiple CUDA processes to share a single
 GPU context. CUDA MPS should be transparent to CUDA programs.
 .
 CUDA MPS requires a device that supports Unified Virtual Address (UVA) and
 has compute capability SM 3.5 or higher.
 Pre-CUDA 4.0 APIs are not supported under CUDA MPS.

nvidia-dkms-450-server: NVIDIA DKMS package

 This package builds the NVIDIA kernel module needed by the userspace
 driver, using DKMS.
 Provided that you have the kernel header packages installed, the kernel
 module will be built for your running kernel, and automatically rebuilt for
 any new kernel headers that are installed.

nvidia-driver-450-server: NVIDIA Server Driver metapackage

 This metapackage depends on the NVIDIA binary driver and on all of its libraries,
 to provide hardware acceleration for OpenGL/GLX/EGL/GLES/Vulkan
 applications on either X11 or on Wayland.
 .
 See /usr/share/doc/nvidia-driver-450-server/README.txt.gz
 for a complete list of supported GPUs and PCI IDs.

nvidia-headless-450-server: NVIDIA headless metapackage

 This metapackage installs the NVIDIA Server Driver and the libraries that enable
 parallel general purpose computation through CUDA and
 OpenCL.
 .
 Install this package if you do not need X11 or Wayland support, which is
 provided by the nvidia-driver-450-server metapackage.

nvidia-headless-no-dkms-450-server: NVIDIA headless metapackage - no DKMS

 This metapackage installs the NVIDIA Server Driver and the libraries that enable
 parallel general purpose computation through CUDA and
 OpenCL. DKMS will not be installed, and, therefore, the kernel module
 will not be built.
 .
 Install this package if you do not need X11 or Wayland support, which is
 provided by the nvidia-driver-450-server metapackage.

nvidia-kernel-common-450-server: Shared files used with the kernel module

 This package installs all the optional accessory files for the NVIDIA
 kernel module.
 .
 Install this package if you want to blacklist any conflicting kernel
 modules, and if you want udev to load the the NVIDIA kernel modules,
 and to create the uvm devices automatically.

nvidia-kernel-source-450-server: NVIDIA kernel source package

 This package provides the NVIDIA kernel source needed by the userspace
 driver.

nvidia-utils-450-server: NVIDIA Server Driver support binaries

 This package contains supporting binaries for the NVIDIA Server Driver.

xserver-xorg-video-nvidia-450-server: NVIDIA binary Xorg driver

 The NVIDIA binary driver provides optimized hardware acceleration of
 OpenGL/GLX/EGL/GLES applications via a direct-rendering X Server
 for graphics cards using NVIDIA chip sets.
 .
 See /usr/share/doc/nvidia-driver-450-server/README.txt.gz
 for a complete list of supported GPUs and PCI IDs.