This week's Vulkan 1.2.158 spec release brought the fragment shading rate extension to control the rate at which fragments are shaded on a per-draw, per-primitive, or per-region basis. This can be useful similar to OpenGL and Direct3D support for helping to allow different, less important areas of the screen be shaded less than areas requiring greater detail/focus.

While NVIDIA is usually quite timely in supporting new versions of the Linux kernel and aim to have out a driver by the end of the release candidates for new series, in the case of the recently minted Linux 5.9 kernel it's taking a lot longer.

Last month marked the release of the 455.23.04 beta driver for NVIDIA Linux users in providing support for the GeForce RTX 3080 and 3090 graphics cards. The NVIDIA 455.28 Linux driver is out today as their first official 455 series release and also stable RTX 3080/3090 Ampere support.

NVIDIA's online GTC 2020 event kicks off today with a ton of announcements coming across the wire but not one many Linux users have been clamoring to hear more about.

NVIDIA's Linux Vulkan beta driver build has moved from the 450 series that it's been on for a while to the current 455 branch.

NVIDIA has released version 11.1 of their CUDA toolkit that now supports the GeForce RTX 30 "Ampere" series graphics cards.

Introduced last year as part of CUDA 10.2 was libcu++ as the CUDA C++ standard library, which works with not only NVIDIA CUDA enabled configurations but also CPUs. The libcu++ sources are now available via GitHub.

NVIDIA has once again managed to provide launch-day Linux driver support for their next-generation graphics processors. Today the NVIDIA 455.23.04 beta driver is shipping for Linux support with the GeForce RTX 3080 and RTX 3090 "Ampere" graphics cards.

We still don't have our hands on the GeForce RTX 3080 yet and remains to be seen when we will get our hands on RTX 30 series hardware for Linux testing, but at least there's a pretty good rhythm for how the NVIDIA Linux support will play out.

The recent rumors panned out and NVIDIA just announced they have reached a definitive deal with SoftBank to acquire Arm.

A few days ago I published a deep dive into the CPU and GPU performance with Blender 2.90 as a major update to this open-source 3D modeling software. Following that I kept on testing more and older NVIDIA GPUs with the CUDA and OptiX back-end targets to now have an 18-way comparison from Maxwell to Turing with the new Blender 2.90.

Longtime NVIDIA engineer Thierry Reding who has been involved with the open-source Nouveau driver efforts largely from an embedded/mobile Tegra angle last week sent out the newest patch series.

Earlier this summer building off the latest Windows Subsystem for Linux 2 advancements by Microsoft, NVIDIA released early support for CUDA / GPU compute on WSL2. This week NVIDIA offered up a new version of their CUDA WSL support.

NVIDIA software engineer Zi Yan who specializes in the Linux kernel memory management subsystem today sent out a set of patches proposing the addition of 1GB THP support for the Linux kernel.

One important bit not covered in today's GeForce RTX 3070/3080/3090 announcement but now detailed via the NVIDIA website is confirmation that the RTX 30 "Ampere" GPUs do in fact have dedicated AV1 hardware decode capabilities.

As widely expected amid a constant flow of rumors and leaks in recent weeks, NVIDIA just revealed their GeForce RTX 3000 "Ampere" series.

DALI is the project at NVIDIA focused on GPU-accelerated data augmentation and image loading along with other tasks while being optimized for deep learning workflows. DALI 0.25 was released on Friday as the latest step forward for this open-source NVIDIA project.

While NVIDIA's desktop graphics drivers may not be open-source, there are other open-source projects maintained by NVIDIA that we have covered over the years particularly in the high performance computing and visual design space, among other interesting bits. Dirk Van Gelder who is NVIDIA's Direct of Software Development gave a talk this week about some of the open-source efforts engaged in by the company.

Red Hat's Adam Jackson has been working on "GLX Delay" as a means of offering accelerated GLX with OpenGL for XWayland when using the NVIDIA proprietary driver. The proposed code is going through Mesa even though it's for the proprietary NVIDIA driver benefit and also requires a change to the OpenGL Vendor Neutral Dispatch Library (libglvnd).

NVIDIA is preparing to remove support for multi-GPU modes of AA (anti-aliasing), AFR (alternate frame rendering), and SFR (split frame rendering) from the Linux driver in the near future.

NVIDIA today released 450.66 as their latest stable Linux graphics driver update.

Earlier this year at GTC Digital was the announcement of the NVIDIA High Performance Computing Software Development Kit while this week they have finally released this HPC SDK for developers at large.

Following a NVIDIA 450 Linux beta with the CUDA 11.0-rc in early June and the more formal NVIDIA 450.51 Linux beta later in June, NVIDIA has now promoted the 450 Linux driver series to stable with today's release of the 450.57 driver build.

NVIDIA appears to have quietly promoted CUDA 11.0 to its stable channel.

NVIDIA has quietly released Video Codec SDK 10 as the newest version of their proprietary video encode/decode implementation designed for their GPUs.

Our recent benchmarks have shown WSL/WSL2 performance on the latest Windows 10 builds to generally be quite good compared to running bare metal Linux. But past the May 2020 Update and on the latest Insider Preview builds is the initial support for GPU acceleration in conjunction with updated Windows graphics drivers. The initial emphasis is on GPU compute with DirectML and for NVIDIA hardware CUDA support as well. Here are a couple CUDA benchmarks that ran gracefully under WSL2 albeit the performance leaves a lot to be desired.

Earlier this month a NVIDIA 450 Linux beta driver popped out as part of the CUDA 11.0 release candidate. Today though is the first public and generally available NVIDIA 450 series Linux driver beta for all users.

NVIDIA today released a new Vulkan beta driver for Linux systems at version 440.66.17.

After announcing the NVIDIA Ampere architecture at last month's virtual keynote, beginning today the NVIDIA A100 PCI Express accelerator is now shipping in GPU compute servers.

NVIDIA has yet to formally announce the 450 Linux driver series in beta or stable form, but the first pre-release builds in the 450 branch did manage to creep out this past week alongside the CUDA 11.0 release candidate.