Language Selection

English French German Italian Portuguese Spanish

Graphics/Benchmarks

Benchmarks and Phoronix Test Suite

Filed under
Graphics/Benchmarks

Graphics: NVIDIA, AMD/Vega and Mesa

Filed under
Graphics/Benchmarks
  • NVIDIA 390.59 Linux Driver Brings New GPU Support, X.Org Server 1.20 Compatibility

    For those using the long-lived NVIDIA 390 driver series rather than the latest NVIDIA 396 short-lived series (or happen to be stuck on 390 like for Fermi GPU support), the NVIDIA 390.59 Linux driver was released minutes ago.

    Most notable for existing NVIDIA 390 driver series is there is now xorg-server 1.20 compatibility. There is X.Org Server 1.20 support on the NVIDIA 396 series already, but for those using this long-lived driver branch, there is back-ported 1.20 server compatibility.

  • AMDGPU Feature Updates Submitted For Linux 4.18, Bringing Vega M & More

    Alex Deucher of AMD today submitted the initial batch of Radeon/AMDGPU DRM driver feature updates to DRM-Next that in turn are slated to land in the Linux 4.18 merge window in June. There's a fair amount of notable feature work this round for Radeon Linux users.

  • AMD Publishes Open-Source Driver Support For Vega 20

    AMD today published their big set of patches bringing open-source Linux kernel support for the "Vega 20" graphics processor.

    Vega 20 is the rumored 7nm AMD graphics processor that is said to be up to 70% faster than the current leading RX Vega 64 graphics card, according to some reported leaks. Vega 20 is expected to offer up to 32GB of HBM2 memory and be announced this calendar year, but there is some belief that it might just be a deep learning accelerator and not focused as a gaming graphics card or at least not initially.

  • Gallium3D's HUD Gets A Frametime Graph Capability

    In addition to being able to plot the frames per second, CPU usage, and many other possible sensor outputs, the Gallium3D Heads-Up Display (HUD) is now capable of showing the frametime while gaming.

  • Mesa 18.0.4 Coming This Week With More Fixes

    While Mesa 18.1 is expected for release this week, those riding the Mesa 18.0 stable series will also have an 18.0.4 point release coming in the next few days.

    Mesa 18.0.4 is expected for release this Thursday or Friday as the newest point release for this Q1'2018 Mesa series. Mesa 18.0.4 release candidate 1 was issued today with just over two dozen fixes.

  • Mesa 18.0.4 Linux Graphics Stack to Squash Rendering Bugs in Trine & The Witcher

    The Mesa graphics stack for Linux-based operating systems will soon receive a new maintenance update that addresses a few important bugs in some games and improves various of the included open-source graphics drivers.

    Mesa 18.0.4 is expected to arrive this week as the fourth maintenance update to the Mesa 18 series, bringing improvements to the r600 graphics driver for ATI/Radeon GPUs that fix some rendering bugs in the Trine and The Witcher video games, as well as several bug fixes for the Radeon RADV Vulkan driver.

    The Intel ANV Vulkan and Intel i965 OpenGL graphics drivers have been improved as well in this Mesa 18.0.4, which patches a leak in Intel's BLORP code for 4th Generation and 5th Generation Intel Core processors, and adds a few fixes to code emission around 16-bit integers and Image Signal Processor (ISP).

Linux Graphics: AMDVLK and GEM

Filed under
Graphics/Benchmarks
  • AMDVLK Driver Adds VK_KHR_display Support

    The AMD developers working on their official Vulkan driver code updated the public source trees yesterday for XGL and PAL that form the AMDVLK open-source Linux driver.

  • GEM Improvements & Better Intel Icelake Support Coming To Linux 4.18

    Building off their first batch of DRM updates for Linux 4.18, the Intel open-source crew has submitted a second batch of new feature material to DRM-Next that in turn will land with this next kernel cycle.

    Changes with this pull request include NV12 pixel format support finally being firmed up, a number of Intel Icelake improvements, GVT virtualization updates, Panel Self Refresh (PSR) updates, execlist fixes and updates, "tons" of GEM memory management improvements, and a variety of other fixes and code improvements.

The Performance Of Clear Linux With GCC 8

Filed under
Graphics/Benchmarks

Intel's Clear Linux operating system has been among the first notable Linux distributions upgrading to the recently-released GCC 8.1 as the default system compiler and then proceeding to rebuild its packages against this annual update to the GNU Compiler Collection. Here are some before/after benchmarks of their GCC 8 deployment for those interested.

GCC 8 offers many compiler improvements from tentative C17 and C++20/C++2A support to newer CPU support and performance optimizations. In fact, our tests have found for some significant compiler boosts on Intel Skylake hardware but there are also benefits for AMD Ryzen and other CPU microarchitectures.

Read more

GPU/Graphics: OpenCL, AMD, X.Org

Filed under
Graphics/Benchmarks
  • OpenCL 2.2 Sees A Maintenance Update With Document Clarifications, Bug Fixes

    While OpenCL 2.2 support by the major hardware vendors' drivers are sadly languishing, a new maintenance release of this year-old OpenCL standard was issued today to provide various bug fixes as well as documentation clarifications to the specification. Additionally, there is also an update to the OpenCL SPIR-V specification.

  • AMD's Compressonator 3.0 Brings Better Texture Compression

    AMD's GPUOpen team has released Compressonator 3.0, the latest major update to this tools collection for dealing with texture and 3D model compression and optimizations for Linux, macOS, and Windows.

    The Compressonator 3.0 release brings improved texture compression, mesh optimizations, mesh compression support, and other enhancements.

  • AMDKFD In Linux 4.18 Bringing Vega GPU Support

    The AMDKFD kernel driver in the upcoming Linux 4.17 has the long-awaited discrete Radeon GPU support working so it can be used with the ROCm/OpenCL compute user-space, but Vega GPU support wasn't ready for this release. Fortunately, it's ready for Linux 4.18.

  • Four Years After Launch, AMD Kaveri Sees Huge Performance Boost On Linux

    For those making use of AMD Kaveri APUs, the latest Linux graphics stack improvements will now yield much better performance -- up to twice as fast in some instances! Here are some benchmarks with Ubuntu 18.04 on the AMD A10-7870K.

  • X.Org Server 1.21 Opens For Development

    Following the long drawn out and feature-packed X.Org Server 1.20 cycle, the 1.21 window officially opened up today.

    Adam Jackson of Red Hat who continues serving as the X.Org Server release manager today did the post-1.20 version bump to begin allowing new feature material to land for this next cycle.

    For the time being xserver Git is living as version 1.20.99.1 and Adam's latest codename is "Carrot and Ginger Soup."

    No release plans have been posted yet, so it remains to be seen if 1.21 will aim to get back on a six-month release cadence like X.Org had been getting good at delivering on. Or if it will be like 1.20 where it was one and a half years in the making.

Graphics Leftovers

Filed under
Graphics/Benchmarks
  • RADV Lands VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT

    The RADV Vulkan driver within Mesa has landed its VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT support so applications/games can opt to disable optimizations when compiling a Vulkan pipeline. This is notably what was just covered the other day for helping to reduce stuttering with DXVK.

  • DXVK 0.51 Brings Fixes & Asynchronous Pipeline Compilation Support

    DXVK 0.51 is now available as the latest version of this library for running Direct3D 11 games under Wine via the Vulkan graphics API.

    The DXVK 0.51 release most notable adds asynchronous pipeline compilation support for Vulkan drivers making use of VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT. This is the feature for reducing stuttering for games on DXVK and as of this morning is now supported by the RADV driver. We'll see how long it will take until the NVIDIA Vulkan driver and others support this feature. For now though DXVK ships with this support disabled and requires using the DXVK_USE_PIPECOMPILER=1 environment variable as this feature can cause hangs for Prey and potentially other titles.

  • VK9 Gets Better Support For Shaders, 64-bit Fixes

    While the rapidly maturing DXVK library has been capturing much of the limelight when it comes to piping Direct3D over Vulkan, the VK9 project targeting Direct3D 9 on top of Vulkan continues making progress.

  • Intel's Mesa Driver Prepares To Kill Off The Blitter

    Jason Ekstrand has spent some time away from the Intel ANV Vulkan driver to kill the hardware blitter usage within the i965 Mesa OpenGL driver.

    With a set of patches posted on Friday, the Intel Mesa driver eliminates its hardware blitter usage for Intel Sandy Bridge hardware and newer. Ekstrand explained that the graphics hardware blitter has been degraded on recent generations of Intel graphics, "On Sandy Bridge, the blitter was moved to another ring and so using it incurs noticable synchronization overhead and, at the same time, that synchronization is an endless source of GPU hangs on SNB. Some time around the Ivy Bridge time frame, we suspect that the blitter ended up with somewhat slower paths to memory than the 3D engine so it's slower in general. To make matters worse, the blitter does not understand any sort of compression at all and so using it frequently means having to do some sort of resolve operation."

  • Latest Intel ARB_gl_spirv Patches Published By Igalia

    It's almost one year since the release of OpenGL 4.6 and while there is support outside of the Mesa tree, mainline Mesa still doesn't support this latest OpenGL revision due to the holdups around SPIR-V ingestion support.

    Intel's i965 and AMD's RadeonSI drivers would have supported OpenGL 4.6 with mainline Mesa months ago, but they've been held up on the ARB_gl_spirv extension and the related ARB_spirv_extensions support. This work allows for SPIR-V modules to be used by OpenGL complementary to GLSL and allows for GLSL to also to be used as a source language for creating SPIR-V modules for OpenGL consumption. This is basically all about better interoperability between OpenGL and Vulkan -- not an easy task to implement.

  • RADV Adding New Bit To Help Avoid Stuttering With DXVK

    The RADV Vulkan driver will soon have VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT to help avoid stuttering with DXVK for running Direct3D 11 games on Wine over Vulkan.

    While DXVK performance is already quite compelling and handling a surprising number of D3D11 games rendered via Vulkan considering how young this project is, DXVK and potentially the other Vulkan Linux drivers may soon see less stuttering.

  • Vulkan layer for Direct3D 11 & Wine 'DXVK' updated with fixes for Dark Souls 3, Overwatch & more

    DXVK [GitHub] is such an incredible project to bring Direct3D 11 support to Wine using Vulkan and another exciting release is now out.

KDE vs. GNOME, X.Org vs. Wayland Radeon Linux Gaming Performance With Ubuntu 18.04 LTS

Filed under
Graphics/Benchmarks

For those wondering how the Radeon Linux gaming performance is changed between desktop environments when testing Ubuntu 18.04 LTS out-of-the-box, here are some benchmarks. Not only is it looking at the performance between GNOME Shell 3.28.1 and KDE Plasma 5.12.4, but it's also comparing each desktop environment with its X.Org and Wayland session support. Additionally, these tests were done with both AMD Radeon Polaris and Vega graphics cards.

Read more

Graphics: X.Org Server 1.20, NVIDIA 396.18.11, Mesa 18.1

Filed under
Graphics/Benchmarks
  • Several DDX Drivers Aren't Yet Ready For X.Org Server 1.20

    If you were hoping to build the newly-released X.Org Server 1.20 on your system(s) this weekend, be forewarned that a number of the DDX drivers haven't yet been updated for supporting the API/ABI changes of this big server update.

    A number of the smaller, obscure drivers like Tseng, SiS, R128, and March64 haven't yet been updated for xorg-server 1.20 support but also the more prominent xf86-video-ati and xf86-video-amdgpu DDX drivers have not yet seen new releases with xorg-server 1.20 support.

  • NVIDIA 396.18.11 Linux Vulkan Driver Released With Fixes

    The NVIDIA 396.18.11 Vulkan beta driver for Linux was released on Friday as pulling in the latest upstream fixes to the Vulkan beta driver branch for Windows and Linux.

    The 396.18.11 Linux driver and 397.76 Windows driver pull in the latest fixes from their general release driver. For the Linux release, it comes just three days after another small beta update (396.18.08) that was released to fix Alt-Tab freezing with the DXVK Direct3D11-over-Vulkan implementation.

  • Mesa 18.1 Expected To Officially Debut Next Week

    While Mesa 18.0 debuted just about one and a half months ago, the fourth and final release candidate of Mesa 18.1 is now available for testing as the next quarterly feature installment to these primarily OpenGL/Vulkan open-source drivers.

    First time Mesa release manager Dylan Baker issued Mesa 18.1.0-RC4 this Friday evening with 25 queued patches. The affected work ranges from core Mesa fixes to Gallium3D, R600, RADV, RadeonSI, i965, and ANV fixes... Pretty much fixes across the board at least as far as the major drivers are concerned sans Nouveau.

AMD Graphics and Linux

Filed under
Graphics/Benchmarks
Linux
  • Radeon EQAA Anti-Aliasing Support Merged To Mesa 18.2

    In addition to the potentially performance-doubling AMD Kaveri fix landing yesterday in Mesa 18.2 Git, also hitting this next version of Mesa is Enhanced Quality Anti-Aliasing (EQAA) support for Radeon GCN graphics processors.

    RadeonSI Gallium3D has wired up its Enhanced Quality Anti-Aliasing support. EQAA aims to deliver better quality over multi-sample anti-aliasing (MSAA) by providing more coverage samples per pixel. EQAA should have only slightly higher performance requirements than MSAA but with significant visual quality benefits.

  • AMD Kaveri Gets A Big Performance Boost With Mesa 18.2 & AMDGPU DRM

    When using the latest Git/development code of Mesa 18.2 on Kaveri APUs you may find up to a 2x increase in performance if you are using the AMDGPU DRM driver rather than the default Radeon DRM driver.

    It turns out the number of render back-ends reported by the kernel driver was wrong for Kaveri: there's two, not one. Both render back-ends for Kaveri should now be enabled when using Mesa 18.2 Git since yesterday, but you need to be using the AMDGPU kernel driver as otherwise with the Radeon DRM kernel driver one of the back-ends will still be disabled.

  • Radeon ROCm 1.8 Compute Stack Released

    Following the slew of recent AMD/Radeon Linux driver updates, the ROCm 1.8.0 release was issued today for the Radeon Open Compute stack.

    ROCm 1.8 can be obtained via the GitHub instructions. Binary packages are provided for Ubuntu 16.04 and CentOS/RHEL 7.4.

Graphics: AMD, X.Org Server 1.20, GPU Virtualization

Filed under
Graphics/Benchmarks
  • AMDVLK Vulkan Driver Sees A Big Update, Prepping For VK_EXT_descriptor_indexing

    The code to the AMDVLK official open-source Radeon Vulkan driver for Linux has received a big code update, syncing up the public tree from their internal development trees with about two weeks worth of changes.

  • Radeon Pro Software 18.Q2 Released For Linux

    AMD has carried out their quarterly Radeon Pro Software driver update designated for their Radeon Pro professional/workstation graphics drivers with these updates having received additional QA for certified workloads. The Radeon Pro Software 18.Q2 Linux driver made it out alongside their Windows update.

  • AMD TrueAudio Next 1.2 Released, But Still No Linux Support

    The latest feature update is now available to AMD's TrueAudio Next solution for delivering advanced audio effects using OpenCL kernels without relying upon any dedicated DSP hardware.

    TrueAudio Next 1.2 improvements to its audio convolution algorithm, many optimizations to its Graphics Audio Acceleration Library, support for AMD Resource Reservation, and a number of new samples were added.

  • xorg-server 1.20.0

    Lots of Present, DRI3 modifier, and buildsystem fixes. Thanks to everyone who contributed to this release!

  • X.Org Server 1.20 "Avocado Toast" Released With DRI3 v1.2, VR Improvements

    After more than one and a half years in development that is well off their past six-month release cadence, the long-awaited X.Org Server 1.20 has finally been released as this stable X11 implementation for Linux desktop systems not yet prepared to migrate to Wayland.

  • GPU virtualization update

    A few months ago, Robert Foss wrote a blog post about virtualizing GPU Access. In his post, Robert explained the architecture of the GPU virtualization stack and, how to build and run a VM with hardware acceleration.

    If you are interested by the GPU virtualization topic, I suggest you read Robert’s post.

    Today, I will discuss the major improvements which landed upstream during these pasts 3 months.

Syndicate content

More in Tux Machines

15 books for kids who (you want to) love Linux and open source

In my job I've heard professionals in tech, from C-level executives to everyone in between, say they want their own kids to learn more about Linux and open source. Some of them seem to have an easy time with their kids following closely in their footsteps. And some have a tough time getting their kids to see what makes Linux and open source so cool. Maybe their time will come, maybe it won't. There's a lot of interesting, valuable stuff out there in this big world. Read more

Security: VPNFilter, Encryption in GNU/Linux, Intel CPU Bug Affecting rr Watchpoints

  • [Crackers] infect 500,000 consumer routers all over the world with malware

    VPNFilter—as the modular, multi-stage malware has been dubbed—works on consumer-grade routers made by Linksys, MikroTik, Netgear, TP-Link, and on network-attached storage devices from QNAP, Cisco researchers said in an advisory. It’s one of the few pieces of Internet-of-things malware that can survive a reboot. Infections in at least 54 countries have been slowly building since at least 2016, and Cisco researchers have been monitoring them for several months. The attacks drastically ramped up during the past three weeks, including two major assaults on devices located in Ukraine. The spike, combined with the advanced capabilities of the malware, prompted Cisco to release Wednesday’s report before the research is completed.

  • Do Not Use sha256crypt / sha512crypt - They're Dangerous

    I'd like to demonstrate why I think using sha256crypt or sha512crypt on current GNU/Linux operating systems is dangerous, and why I think the developers of GLIBC should move to scrypt or Argon2, or at least bcrypt or PBKDF2.

  • Intel CPU Bug Affecting rr Watchpoints
    I investigated an rr bug report and discovered an annoying Intel CPU bug that affects rr replay using data watchpoints. It doesn't seem to be hit very often in practice, which is good because I don't know any way to work around it. It turns out that the bug is probably covered by an existing Intel erratum for Skylake and Kaby Lake (and probably later generations, but I'm not sure), which I even blogged about previously! However, the erratum does not mention watchpoints and the bug I've found definitely depends on data watchpoints being set. I was able to write a stand-alone testcase to characterize the bug. The issue seems to be that if a rep stos (and probably rep movs) instruction writes between 1 and 64 bytes (inclusive), and you have a read or write watchpoint in the range [64, 128) bytes from the start of the writes (i.e., not triggered by the instruction), then one spurious retired conditional branch is (usually) counted. The alignment of the writes does not matter, and it's not related to speculative execution.

In Memoriam: Robin "Roblimo" Miller, a Videographer and Free Software Champion

Videographer Robin Roblimo Miller

Robin "Roblimo" Miller was a clever, friendly, and very amicable individual who everyone I know has plenty of positive things to say about. I had the pleasure of speaking to him for several hours about anything from personal life and professional views. Miller was a very knowledgeable person whose trade as a journalist and video producer I often envied. I have seen him facing his critics in his capacity as a journalist over a decade ago when he arranged a debate about OOXML (on live radio). Miller, to me, will always be remembered as a strong-minded and investigative journalist who "did the right thing" as the cliché goes, irrespective of financial gain -- something which can sometimes be detrimental to one's longterm health. Miller sacrificed many of his later years to a cause worth fighting for. This is what we ought to remember him for. Miller was - and always will be - a FOSS hero.

May everything you fought for be fulfilled, Mr. Miller. I already miss you.

Today in Techrights