Language Selection

English French German Italian Portuguese Spanish


DragonFlyBSD 6.0 Performance Is Looking Great - Initial Benchmarks

Filed under

I am currently testing DragonFlyBSD 6.0 on multiple systems and will in turn compare DragonFlyBSD 6.0 against the recent FreeBSD 13.0 (the recent FreeBSD 13.0 also brings its own performance improvements) and various Linux distributions. Upon early testing though of DragonFlyBSD 5.8.3 as the prior stable release against the new DragonFlyBSD 6.0, there is nice uplift in many benchmarks.

Today's tests are on an Intel Core i9 10980XE workstation and the uplift found from DragonFlyBSD 6.0 even with still using the same GCC 8.3 compiler release and HAMMER2 on both releases is looking quite good.

Read more

Graphics/Video: PipeWire, Intel, and NVIDIA

Filed under
  • Fedora Magazine: PipeWire: the new audio and video daemon in Fedora Linux 34

    Wim Taymans has a long track record in the Linux community. He was one of the two original developers of the GStreamer multimedia framework and he was the principal maintainer for most of the project’s initial existence. He joined Red Hat in 2013 and has helped maintain GStreamer and PulseAudio for Red Hat since. In 2015 he started working on PipeWire: a project that has come to full fruition in Fedora Workstation 34, where it handles both audio and video. In addition to that, it also merges the world of pro-audio with mainstream Linux. In this interview we will talk about where PipeWire came from, where it is at and where Wim sees it going from here.

  • Intel Posts Latest Linux Patches For Reporting Per-Client GPU/Media Engine Utilization

    For two years now Intel open-source engineers have floated patches for reporting per-client engine utilization for showing on an application level how much it's leveraging the Intel graphics render/3D, blitter, and video/multimedia engines. This can be used for some nifty system information reporting like a GPU top or other system monitoring functionality. The latest version of these patches were sent out this week.

    The benefit of these patches for Intel graphics hardware on Linux is being able to report on a per-process level how the Intel GPU is being utilized and by what software. This "per-client engine busyness" information is exposed to user-space via sysfs so any interested application can make use of the information.

  • NVIDIA released another small update to their Vulkan Beta Driver

    After releasing upgrading their stable drivers with version 460.80 following the release of the the RTX 3050 and RTX 3050 Ti for laptops - a new Vulkan Beta Driver is out now.

Graphics: AMDVLK, Radeon and ROCm

Filed under

  • AMDVLK 2021.Q2.2 Driver Re-Released - Phoronix

    Back in April we wrote about the AMDVLK 2021.Q2.2 Vulkan driver update for Radeon Linux systems while as some driver deja vu this driver version with the same changes have been re-released.

    As noted last month, with the AMDVLK 2021.Q2.2 driver release the headers have been re-based against Vulkan API 1.2.174 and there are two listed new features. AMDVLK 2021.Q2.2 adds support to dynamic enable of color writes and partial nested command buffer support in the GPU debug layer.

  • AMD Radeon Open Compute 4.2 Is Released

    The latest AMD ROCm compute stack has nothing new for Linux desktop users, and there is no mention of OpenCL in the release notes. It is still incapable of providing compute capabilities to desktop applications like Blender. Data center customers can enjoy new platform macros and several other improvements to the ROCm tools and libraries.

  • AMDVLK 2021.Q2.2 Driver Is Re-Compiled And Re-Released

    AMD has released new binary versions their AMDVLK 2021.Q2.2 driver that was originally released on April 28th. We have no idea what, if anything, is different in the new re-release, We can only speculate that the only change in the re-release is that the "new" version is compiled with an updated version of AMD's LLVM compiler fork.


    The release notes remain the same as they were when 2021.Q2.2 was first released on April 28th. The old release notes mention that the Vulkan apiVersion (from the Vulkan headers) was bumbed to 1.2.17, that color writes can be enabled dynamically and that there were three minor bug-fixes relating to DCC color compression, the AMD switchable graphics layer being ignored in some cases and out of memory errors if AMDVLK is installed on a machine with no AMD GPU.

Intel Xeon Platinum 8380 Ice Lake Linux Performance vs. AMD EPYC Milan, Cascade Lake

Filed under

Last month Intel launched their 3rd Gen Xeon Scalable "Ice Lake" processors for these 10nm server processors and SKUs up to 40 cores while boasting around a 20% IPC improvement overall and big reported improvements for AI workloads and more. Recently we received an Intel Ice Lake reference server with the dual Xeon Platinum 8380 processors so we can carry out our own performance tests. In this initial article is our first look at the Xeon Platinum 8380 Linux support in general and a number of performance benchmarks.

The Intel 3rd Gen Xeon Scalable Ice Lake processors are a big improvement over 2nd Gen Cascade Lake processors with the transition to the 10nm Sunny Cove architecture and now offering processors up to 40 cores rather than topping out at 28 cores, but still lower than the likes of EPYC at 64 cores or Ampere Altra at even higher core counts. The new Xeon Scalable processors also now support eight channels of DDR4-3200, 64 lanes of PCI Express 4.0 per socket, and other improvements as outlined in the launch-day article.

Read more

Games and Graphics: Go Godot Jam, Drova - Forsaken Kin, and ROCm 4.2

Filed under
  • Godot Engine - Announcing Go Godot Jam

    Meet Adrian, a game developer from Stockholm, Sweden. He co-organises Go Godot Jam, a one-month long community festival with a game jam included. Adrian answered a few questions.


    Godot is a great game engine that unlocks possibilities for game developers. It is a free, open-source 2D and 3D engine that provides many features so that you can focus on your game.

    Yet most people start developing games with proprietary engines such as Unity or Unreal. They are solid engines with a proven track record and a vibrant ecosystem. One advantage having experience with more than one engine can enable people to create better games. In the end, it's up to each individual to pick the one that they’ll be most comfortable with to fulfil their creative vision.

    I know that Godot has a lot to offer to new developers, with a distinctive approach to game development which enables more people to express their creativity. It's open, focused on user-friendliness, easy to learn, yet feature-packed and a great fit for many types of games. As such, I want to increase awareness of the engine so that more users decide to try it out and add it to their toolset.

  • Try out the new teaser for Drova - Forsaken Kin, an upcoming 2D action RPG

    After already being available on, the free teaser for Drova - Forsaken Kin is now available on Steam and it's been upgraded for the new release.

    "Drova - Forsaken Kin is an Action Based RPG filled with handcrafted open world adventures inspired by the much renowned Gothic game series. A society has discovered the power of a dead empire: to capture the spirits that govern nature and rule over them instead. However, the anger of the remaining spirits divided them. Where will you stand?"

  • AMD Releases ROCm 4.2 Compute Stack

    Just over one month has passed since the release of Radeon ROCm 4.1 and it's now been succeeded by the ROCm 4.2 feature release.

    The Radeon Open eCosystem 4.2 release comes with changes such as:

    - HIP target platform macros were added for easily targeting HIP_PLATFORM_AMD / HIP_PLATFORM_NVIDIA code differences such as including different header files.

AMDGPU and AMD Source Code

Filed under

  • AMDGPU Appears Ready To Flip On ASPM For More GPUs To Help With Power Savings

    With Linux 5.13 AMD began enabling ASPM by default in the AMDGPU DRM driver for Navi 1x, Vega, and Polaris GPUs. Looking ahead to potentially 5.14, AMD appears to be ready to flip on this power-savings feature for the Radeon RX 6000 series (Navi 2x) along with older pre-Polaris GPUs too. 

    PCI Express Active State Power Management (ASPM) has been a tricky situation on Linux especially for years. Due to quirky motherboards as well as some problematic PCIe cards, this feature while part of the PCI Express standard hasn't often been used by default due to various problems that can come up with quirky hardware as well as the latency when returning from the ASPM state. When working nominally, ASPM is designed to provide active-state link power management to cut power to the PCIe link when otherwise idle and can often deliver measurable power savings for laptops and desktops. 

  • AMD Publishes Radeon Rays 4.1 As Open-Source

    Last year Radeon Rays 4.0 brought Vulkan support while dropping OpenCL and at the same time no longer being open-source... This GPU-accelerated ray intersection library used by the likes of Radeon ProRender is out today with version 4.1 and now it's back to being open-source. 

    Today with AMD's Radeon Rays 4.1 release they are celebrating that it's now "open source!" Though that's just for Radeon Rays 4 as mentioned with their prior release having gone closed-source compared to prior releases, but thankfully it's now returned to being open-source. 

NVIDIA 460.80 Linux Driver Released

Filed under
  • NVIDIA 460.80 Linux Driver Released With New Laptop GPU Support, Bug Fixes

    With today NVIDIA announcing the GeForce RTX 3050 and RTX 3050 Ti laptop GPUs, they have issued the 460.80 Linux driver as their newest long-lived driver release.

    The NVIDIA 460.80 Linux driver adds support for the GeForce RTX 3050 / RTX 3050 Ti laptop GPUs along with the laptop GPUs of the T600, T1200, RTX A2000, RTX A3000, RTX A4000, and RTX A5000 GPUs. These additional laptop GPUs were already supported by the latest NVIDIA 465 series Linux driver but have now been brought back to the long-term 460 series driver branch.

  • NVIDIA released the stable Linux 460.80 driver following their new GPU releases

    Following on from the news earlier that NVIDIA has released the RTX 3050 and RTX 3050 Ti for laptops, their new stable driver 460.80 is out for Linux.

    As always for NVIDIA, they push out a new driver right away to get Linux support for their GPUs hooked up day and date with the release.

Matthias Clasen: Adventures in graphics APIs

Filed under

Various people are working on porting desktop virtualization UIs to GTK4. This typically involves virgl, and the GTK3 solution was to use GtkGLArea.

With GTK4, rendering is happening in GL anyway, so it should be enough to just wrap your content in a GdkTexture and hand it to GTK, either by using it as a paintable with GtkPicture, or with a GskTextureNode in your own snapshot() implementation.

Read more

Also: NVIDIA Adding Experimental Vulkan Support For Executing CUDA Binaries - Phoronix

NVIDIA GeForce RTX 3090 - Windows vs. Linux GPU Compute Performance

Filed under

Following the recent RTX 30 series Linux gaming benchmarks and RTX 30 compute comparison, I was curious how the Linux performance for the flagship GeForce RTX 3090 graphics card compares to the Windows 10 performance in various GPU compute workloads. Well, here are those benchmarks for those wondering about Vulkan / OpenCL / CUDA / OptiX compute performance between Windows and Linux with the very latest NVIDIA drivers.

With the official NVIDIA Windows and Linux (and FreeBSD and Solari) drivers being comprised from largely the same sources, historically the performance has been close to the same across platforms when it comes to the binary driver speed. It mostly though comes down to a function of the application/game under test how well it is optimized for a given platform and if it's relying upon any emulation / additional abstraction layers primarily on Linux. For today's article is a fresh look at the Windows vs. Linux NVIDIA performance when focusing in on the GPU compute performance.

Read more

Windows 10 Build 21370 vs. Ubuntu 21.04 Linux On AMD Ryzen 5900X

Filed under

Last month when carrying out tests of Windows 10 vs. Linux on the Intel Core i9 11900K "Rocket Lake" processor we were very surprised to see Windows 10 frankly performing so well compared to Ubuntu and picking up more wins than usual. That unexpectedly strong showing for Windows 10 might be due to Intel's P-State behavior with Rocket Lake or other power management tuning or there the lack of on Linux at this time. But it led me to wondering if the latest Windows 10 updates spelled out anything different on the AMD Ryzen side... So here are some benchmarks of the latest Microsoft Windows 10 against Ubuntu 21.04 on the same AMD Ryzen 9 5900X system.

Microsoft Windows 10 Pro x64 Build 21370 was benchmarked as the very newest Windows Insider Preview build for getting the latest software support and also using the latest AMD drivers as of testing. On the Linux side was the recently released Ubuntu 21.04 with the Linux 5.11 kernel.

Read more

Syndicate content

More in Tux Machines

today's howtos

  • How To Install Flatpak on Ubuntu 20.04 LTS - idroot

    In this tutorial, we will show you how to install Flatpak on Ubuntu 20.04 LTS. For those of you who didn’t know, Flatpak is a package management and software deployment tool created to make the distribution of desktop applications on Linux easier. Flatpak is similar to Ubuntu’s Snapcraft. However, the snap technology is proprietary to Ubuntu. This is why many Linux distribution does not have support for a Snap but they have for Flatpak. This article assumes you have at least basic knowledge of Linux, know how to use the shell, and most importantly, you host your site on your own VPS. The installation is quite simple and assumes you are running in the root account, if not you may need to add ‘sudo‘ to the commands to get root privileges. I will show you through the step-by-step installation of Flatpak on an Ubuntu 20.04 (Focal Fossa) server. You can follow the same instructions for Ubuntu 18.04, 16.04, and any other Debian-based distribution like Linux Mint.

  • NO_ZERO_IN_DATE with MySQL 5.7

    I’m going through some old notes and found this little gem that really confused me last time I was migrating MySQL databases.

  • How to turn off login banner in Linux/Unix with .hushlogin - nixCraft

    Here is a quick tip that explains how to hide and turn off annoying banner in Linux or Unix by creating .hushlogin file.

  • curl -G vs curl -X GET

    You normally use curl without explicitly saying which request method to use. If you just pass in a HTTP URL like curl, curl will use GET. If you use -d or -F curl will use POST, -I will cause a HEAD and -T will make it a PUT. If for whatever reason you’re not happy with these default choices that curl does for you, you can override those request methods by specifying -X [WHATEVER]. This way you can for example send a DELETE by doing curl -X DELETE [URL]. It is thus pointless to do curl -X GET [URL] as GET would be used anyway. In the same vein it is pointless to do curl -X POST -d data [URL]... But you can make a fun and somewhat rare request that sends a request-body in a GET request with something like curl -X GET -d data [URL].

Ramblings about GNOME development

I still like the "C + GLib + GTK-Doc + Devhelp" combination for software development. But it's maybe because that's what I've practiced the most during the 2010's, and it's hard to change habits. What I don't really like, though, is creating lots of GObject subclasses, and writing GObject Introspection-friendly APIs (to take care of language bindings). It's a burden that GNOME library developers need to carry. I said in the previous section that I like a verbose syntax, but here when subclassing a GObject in C, it's a little too verbose (boilerplate code). It needs to be generated with a tool (here is the one that I wrote: gobject-boilerplate scripts). And it's not really malleable code. In the small glib-gtk-book that I wrote several years ago, I described in a chapter the "semi-OOP" C style used by GLib core (not GIO). So, having a kind of simple Object-Oriented style in C, without using GObject. It doesn't require a lot of code to write your own semi-OOP class in C. But then in later chapters I recommended to create GObject subclasses. Time to revisit my copy :-) ? [...] When we know well something, we also know well what are its benefits and drawbacks. We sometimes question ourself: is the grass greener elsewhere? It's nice to explore other worlds, see how things can be done differently. And then coming back to where we were, but with a changed look, new ideas, and, most importantly, a renewed motivation! Read more

Pinebook Pro

I recently bought a Pinebook Pro. This was mainly out of general interest, but also because I wanted to have a spare portable computer. When I was recently having some difficulty with my laptop not charging, I realised that I am dependent on having access to Emacs, notmuch.el and my usual git repositories in the way that most people are dependent on their smartphones – all the info I need to get things done is in there, and it’s very disabling not to have it. So, good to have a spare. I decided to get the machine running the hard way, and have been working to add a facility to install the device-specific bootloader to Consfigurator. It has been good to learn about how ARM machines boot. The only really hard part turned out to be coming up with the right abstractions within Consfigurator, thanks to the hard work of the Debian U-Boot maintainers. This left me with a chroot and a corresponding disk image, properly partitioned and with the bootloader installed. It was only then that the difficulties began: getting a kernel and initrd combination which can output to the Pinebook Pro’s screen and take input from its keyboard is not really straightforward yet, but that’s required for inputting disk encryption passwords, which are required on portable devices. I don’t have the right hardware to make a serial connection to the machine, so all this took a lot of trial and error. I’ve ended up using Manjaro’s patched upstream kernel build for now, because that compiles in the right drivers, and debugging an initrd without a serial connection is far too inefficient. Read more

Elive 3.8.20 beta released

The Elive Team is proud to announce the release of the beta version 3.8.20 Read more