Language Selection

English French German Italian Portuguese Spanish


The xf86-video-ati X.Org Driver Receives Some EOY Updates Ported From AMDGPU

Filed under

If you are still running a pre-GCN AMD graphics card and unfortunately didn't find a new graphics card under any Christmas tree this year, AMD's Michel Dänzer does have a present for you with some improvements to the xf86-video-ati driver that continues serving as the common X.Org driver for pre-HD7000 series graphics cards.

A batch of 13 patches were posted a few days ago to this aging X.Org driver. These changes are back-porting relevant fixes/updates from the modern xf86-video-amdgpu driver back to xf86-video-ati for benefiting these dated Radeon GPUs... Assuming you are not running Wayland or otherwise using the generic xf86-video-modesetting DDX driver atop the Radeon DRM/KMS driver.

Read more

Intel Iris Gallium3D Driver Lands Support For Broadwell Graphics

Filed under

The in-development Iris Gallium3D driver that is being developed as Intel's next-gen, open-source OpenGL Linux graphics driver started out with supporting Skylake graphics and newer. But now with the latest Iris driver code, the hardware support has been extended to cover Broadwell graphics.

With Intel Broadwell graphics hardware not being radically different from Skylake, the latest Iris Gallium3D code has made the necessary changes to provide initial support for Broadwell. This is great news if you are still rocking an older Broadwell CPU, like the still very capable Core i7 5775C with its Iris Pro Graphics 6200 with eDRAM.

Read more

Also: Debootstrap 1.0.112 Released To Speed Up The Bootstrapping Of Debian

Accepted debootstrap 1.0.112 (source) into unstable

Windows Server 2019 vs. Linux vs. FreeBSD Performance On A 2P EPYC Server

Filed under

When Microsoft rolled out their Windows 10 October 2018 Update they also released Windows Server 2019. Now over the slower holiday period I am finally getting caught up in benchmarking Windows Server 2019. For this initial benchmark comparison is a look at the Microsoft Windows Server 2019 performance against a handful of Linux distributions as well as FreeBSD 12.0 for seeing how this latest Windows Server performance compares on a dual AMD EPYC 7601 server.

This initial benchmarking was done on the Dell PowerEdge R7425 server, which features two EPYC 7601 processors for a combined 64 cores / 128 threads while the server was equipped with 512GB DDR4-2666 memory and each OS was installed to the SSDSCKJB120G7R Intel M.2 SSD (the twenty Samsung 860 EVO SSDs weren't part of this round of OS benchmarking). For those interested in the Intel Core/Xeon performance with Windows Server 2019 against Linux, those results will be coming in the days ahead -- this level of testing is quite time consuming.

Read more

Samsung 860 QVO SSD Linux Benchmarks: 1TB SATA 3.0 SSD For $150 USD

Filed under

After being announced a few weeks back, the Samsung 860 QVO series is beginning to ship as a new, lower-cost SATA 3.0 SSD offering. The Samsung 860 QVO series offers four bit per cell flash memory to usher in a new era of lower-cost solid-state storage with the now-shipping 1TB model costing just $150 USD while the 2TB version coming soon at $300 USD and $600 USD for a 4TB edition.

This Samsung 64-layer 3D QLC NAND flash memory is paired with Samsung's proven MJX controller. Samsung rates the 860 QVO series for sequential reads of 550 MB/s and sequential writes of 520MB/s or lower when hitting the QLC memory rather than the cache.

Read more

Initial Linux Benchmarks Of The NVIDIA TITAN RTX Graphics Card For Compute & Gaming

Filed under

Yesterday I unexpectedly found my hands on a NVIDIA TITAN RTX graphics card as the company's newest Titan graphics card built upon the Turing architecture and is now available via retail channels at $2499 USD. Here is an initial look at the NVIDIA TITAN RTX performance under Ubuntu Linux with a variety of compute workloads (including TensorFlow) as well as for entertainment are some Vulkan gaming benchmarks.

Simply put, the TITAN RTX is a beast for GPU compute workloads. While costing $2500 USD, the TITAN RTX offers 4608 CUDA cores compared to 4352 on the RTX 2080 Ti and 576 tensor cores compared to 544 on the RTX 2080 Ti while keeping to the same 1350MHz base clock speed but offering a 1770MHz boost clock (the 2080 Ti carries a boost clock of 1545MHz or 1635MHz on the Founder's Edition GPU). Not only is the TU102 operating at its full potential with the TITAN RTX, but there is also 24GB of GDDR6 video memory -- more than twice that of the RTX 2080 Ti or three times that of the RTX 2070 and RTX 2080 series, making it much more capable for memory intensive computations on the GPU.

Read more

Mesa Picks Up Faster Support For S3TC Decoding Using LLVM

Filed under

In the event you need to deal with software S3TC decoding rather than on the GPU in cases of hardware limitations or running within a VM, Mesa this week picked up a faster implementation.

Roland Scheidegger of VMware landed a patch into Mesa 19.0 that makes use of the LLVM JIT code for decoding S3TC.

Read more

RadeonSI Gallium3D Made Some More OpenGL Performance Gains This Year

Filed under

From carrying out various benchmarks, the OpenGL performance of RadeonSI across the Mesa 18.x releases ranged from performing the same to in cases like Deus Ex: Mankind Divided being around 10% faster than just over one year ago. Not bad at all when considering most of the work on getting RadeonSI up to parity with their proprietary driver and the NVIDIA competition happened during 2016~2017 when it entered a really polished state.

The only main downside this year with the RadeonSI driver is that there is still no OpenGL 4.6 support due to the SPIR-V ingestion support not yet being complete... The proprietary AMD OpenGL driver meanwhile does support OpenGL 4.6 but for most Linux games runs slower than RadeonSI. Overall it was quite an exciting year for open-source Radeon graphics with these RadeonSI performance improvements, significant RADV Vulkan performance/feature work, ironing out various open-source driver issues, and now as we prepare for 2019 there is the long-awaited FreeSync/Adaptive-Sync support set to be merged with the upcoming Linux 4.21. Now we just need to cross our fingers that next year's Radeon Navi support will be in good open-source standing at launch.

Read more

Sounds, Graphics and Compute Servers on Linux

Filed under
  • Sound Updates Slated For Linux 4.21 Have AMD ACP3 Support, Other New Hardware Support

    In preparing for the Linux 4.21 merge window that is expected to open up over the holidays, the sound subsystem updates have already been submitted. There isn't much in the way of core infrastructure work this cycle, but a lot of sound driver activity.

  • AMD Working On Making It Easier To Build & Install Radeon Open Compute (ROCm)

    Now that Radeon Open Compute 2.0 is shipping with OpenCL 2.0 support and many other improvements around Radeon GPU computing, a new focus by the developers working on ROCm is to make it easier to build and install on more Linux distributions.

    AMD/GPUOpen provides ROCm repositories for RHEL/CentOS 7 and Ubuntu LTS users in order to have easy access to release binaries for this Linux GPU computing stack. But those wanting to build from source on your own or utilizing a different Linux distribution, currently its quite a chore building ROCm. There are more than a dozen different code repositories for building the complete ROCm stack from the kernel module to various user-space libraries and different components. It's not a straight-forward process and the documentation has been a bit lacking.

  • Linux Getting Driver Work To Support Tesla V100 NVLink GPUs On High-End POWER9 Servers

    IBM is working on the necessary upstream Linux kernel work for supporting the NVIDIA Tesla V100 GPUs on the POWER9 servers like what comprises the Sierra and Summit supercomputers.

    The V100 Volta GPUs on these POWER9 servers aren't just conventional PCIe cards plugged in but connected via NVLink and allow for coherent memory and NPU/ATS support on the POWER9 CPU. IBM has been leading the Linux kernel work to allow for the unmodified NVIDIA POWER driver to work on this hardware.

The Performance Of Five Linux Distributions From Early 2016 To The End Of 2018

Filed under

With the end of another year upon us, there has been the start of many year-end benchmark comparisons looking at how various aspects of Linux performance has evolved over 2018. In this comparison though is going back further than that and seeing how five Linux distributions have experienced performance changes over the past nearly three years -- using the CentOS, Clear Linux, Fedora, and openSUSE Linux distribution releases from early 2016 to their latest releases as of right now with their stable updates.

Read more

Free Software in Graphics: NVIDIA/PhysX, Radeon, and Nouveau

Filed under
  • The Open-Source NVIDIA PhysX 4.0 Code Is Now Available

    Earlier this month NVIDIA announced their latest plans for an open-source PhysX and at the time put out the PhysX 3.4 SDK under a three-clause BSD license. Now the PhysX 4.0 release is available.

    When making the open-source PhysX announcement at the beginning of the month they also implied the upcoming 4.0 release would see its code dropped too. With PhysX 4.0 availability today, NVIDIA has uploaded the sources under the same BSD license.

  • Radeon Linux Driver Picks Up Support For Another Vega M GPU

    It looks like Intel might soon be launching a new CPU with the onboard Radeon "Vega M" graphics as another PCI ID was just added to the open-source Linux graphics driver.

    Since early this year the AMDGPU Linux driver has supported Vega M - the Radeon graphics found within Intel's Kabylake-G processors and branded as the Vega M GL and Vega M GH parts.

  • Linux Not Booting To A Desktop? Try Disabling The Nouveau Driver

    To be clear up front, this is exclusive to NVIDIA users, as Nouveau is the open-source driver for GeForce and Quadro. For some reason, current Linux installers seem to hate Nouveau on our X399-based PCs. Yes, that’s plural: both the MEG CREATION and Aorus’ X399 Gaming 7 deliver the exact same issue. In talking to others, I can’t find anyone else dealing with this, so I can’t really blame the platform as a whole, but it’s the only one giving me hassle right now.

    Despite using the exact same hardware as months ago, Ubuntu (and others) today require me to boot up with a special flag to disable the Nouveau driver. Fixing this particular issue is as simple as editing a line at the GRUB boot screen, adding nouveau.modeset=0 to the end of the blurb that starts with “linux” (as seen below). If you boot up and see only a purple screen without text, hit Esc as soon as you see it to reveal it.

Syndicate content

More in Tux Machines

Android Leftovers

Programming: Flask, Agile, Rust and Python

  • How to build an API for a machine learning model in 5 minutes using Flask
    As a data scientist consultant, I want to make impact with my machine learning models. However, this is easier said than done. When starting a new project, it starts with playing around with the data in a Jupyter notebook. Once you’ve got a full understanding of what data you’re dealing with and have aligned with the client on what steps to take, one of the outcomes can be to create a predictive model. You get excited and go back to your notebook to make the best model possible. The model and the results are presented and everyone is happy. The client wants to run the model in their infrastructure to test if they can really create the expected impact. Also, when people can use the model, you get the input necessary to improve it step by step. But how can we quickly do this, given that the client has some complicated infrastructure that you might not be familiar with?
  • What is Small Scale Scrum?
    Agile is fast becoming a mainstream way industries act, behave, and work as they look to improve efficiency, minimize costs, and empower staff. Most software developers naturally think, act, and work this way, and alignment towards agile software methodologies has gathered pace in recent years. VersionOne’s 2018 State of Agile report shows that scrum and its variants remain the most popular implementation of agile. This is in part due to changes made to the Scrum Guide’s wording in recent years that make it more amenable to non-software industries.
  • This Week in Rust 269
  • Async IO in Python: A Complete Walkthrough
    Async IO is a concurrent programming design that has received dedicated support in Python, evolving rapidly from Python 3.4 through 3.7, and probably beyond. You may be thinking with dread, “Concurrency, parallelism, threading, multiprocessing. That’s a lot to grasp already. Where does async IO fit in?” This tutorial is built to help you answer that question, giving you a firmer grasp of Python’s approach to async IO.

Security: Updates, Reproducible Builds and More

  • Security updates for Wednesday
  • Reproducible Builds: Weekly report #194
    Here’s what happened in the Reproducible Builds effort between Sunday January 6 and Saturday January 12 2019...
  • ES File Explorer Has A Hidden Web Server; Data Of 500 Million Users At Risk
  • The Evil-Twin Framework: A tool for testing WiFi security
    The increasing number of devices that connect over-the-air to the internet over-the-air and the wide availability of WiFi access points provide many opportunities for attackers to exploit users. By tricking users to connect to rogue access points, hackers gain full control over the users' network connection, which allows them to sniff and alter traffic, redirect users to malicious sites, and launch other attacks over the network.. To protect users and teach them to avoid risky online behaviors, security auditors and researchers must evaluate users' security practices and understand the reasons they connect to WiFi access points without being confident they are safe. There are a significant number of tools that can conduct WiFi audits, but no single tool can test the many different attack scenarios and none of the tools integrate well with one another. The Evil-Twin Framework (ETF) aims to fix these problems in the WiFi auditing process by enabling auditors to examine multiple scenarios and integrate multiple tools. This article describes the framework and its functionalities, then provides some examples to show how it can be used.
  • KDE Plasma5 – Jan ’19 release for Slackware
    Here is your monthly refresh for the best Desktop Environment you will find for Linux. I just uploaded “KDE-5_19.01” to the ‘ktown‘ repository. As always, these packages are meant to be installed on a Slackware-current which has had its KDE4 removed first. These packages will not work on Slackware 14.2. It looks like Slackware is not going to be blessed with Plasma5 any time soon, so I will no longer put an artificial limitation on the dependencies I think are required for a solid Plasma5 desktop experience. If Pat ever decides that Plasma5 has a place in the Slackware distro, he will have to make a judgement call on what KDE functionality can stay and what needs to go.

MongoDB "open-source" Server Side Public License rejected

MongoDB is open-source document NoSQL database with a problem. While very popular, cloud companies, such as Amazon Web Services (AWS), IBM Cloud, Scalegrid, and ObjectRocket has profited from it by offering it as a service while MongoDB Inc. hasn't been able to monetize it to the same degree. MongoDB's answer? Relicense the program under its new Server Side Public License (SSPL). Open-source powerhouse Red Hat's reaction? Drop MongoDB from Red Hat Enterprise Linux (RHEL) 8. Red Hat's Technical and Community Outreach Program Manager Tom Callaway explained, in a note stating MongoDB is being removed from Fedora Linux, that "It is the belief of Fedora that the SSPL is intentionally crafted to be aggressively discriminatory towards a specific class of users." Debian Linux had already dropped MongoDB from its distribution. Read more