Language Selection

English French German Italian Portuguese Spanish

Intel graphics patch "wrecks" Gen7 iGPU Linux performance

Filed under
Graphics/Benchmarks
  • Intel graphics patch "wrecks" Gen7 iGPU Linux performance

    Earlier this week Intel released details about a vulnerability in its integrated graphics hardware. Its advisory ID was INTEL-SA-00314 and it talked about the CVE-2019-14615 vulnerability. Products from 3rd Gen Core up to 10th Gen are affected including the contemporaneous Xeon, Pentium, Celeron and Atom products. Intel was made aware of this vulnerability as far back as August so already has patches available and links to recommended new drivers for both Windows and Linux users (scroll down this page about half way).

    All so regular and nothing surprising so far… However, since the updated drivers have been released, Linux-centric tech site Phoronix has been busy checking and testing the new drivers (on Linux of course) to see if there are any performance penalties, or other aberrations, delivered with the vulnerability patches.

    Intel describes the CVE-2019-14615 vulnerability as follows: "Insufficient control flow in certain data structures for some Intel Processors with Intel Processor Graphics may allow an unauthenticated user to potentially enable information disclosure via local access." Please note the key phrase - local access - but Phoronix thinks that WebGL within web browsers is another possible attack vector.

    In its Linux testing, Phoronix was initially unperturbed by results on processors sportin

  • Intel's Mitigation For CVE-2019-14615 Graphics Vulnerability Obliterates Gen7 iGPU Performance

    Yesterday we noted that the Linux kernel picked up a patch mitigating an Intel Gen9 graphics vulnerability. It didn't sound too bad at first but then seeing Ivy Bridge Gen7 and Haswell Gen7.5 graphics are also affected raised eyebrows especially with that requiring a much larger mitigation. Now in testing the performance impact, the current mitigation patches completely wreck the performance of Ivybridge/Haswell graphics performance.

    The vulnerability being discussed and analyzed this week is CVE-2019-14615. This CVE still hasn't been made public over 24 hours later (though there are the Intel SA-00314 details for this disclosure), but from going through kernel patches and other resources, it certainly caught our interest right away and have been benchmarking it since yesterday evening. The CVE-2019-14615 vulnerability amounts to a new information disclosure issue due to insufficient control flow in certain data structures. Local access is required for exploiting this control flow issue in the hardware, but it's not yet known/published if say WebGL within web browsers could exploit this issue. This is a hardware issue with all operating systems being affected. Our testing today, of course, is under Linux.

Intel graphics patch "wrecks" Gen7 iGPU Linux performance

  • Intel graphics patch "wrecks" Gen7 iGPU Linux performance

    Earlier this week Intel released details about a vulnerability in its integrated graphics hardware. Its advisory ID was INTEL-SA-00314 and it talked about the CVE-2019-14615 vulnerability. Products from 3rd Gen Core up to 10th Gen are affected including the contemporaneous Xeon, Pentium, Celeron and Atom products. Intel was made aware of this vulnerability as far back as August so already has patches available and links to recommended new drivers for both Windows and Linux users (scroll down this page about half way).

    All so regular and nothing surprising so far… However, since the updated drivers have been released, Linux-centric tech site Phoronix has been busy checking and testing the new drivers (on Linux of course) to see if there are any performance penalties, or other aberrations, delivered with the vulnerability patches.

More Details On Intel's CVE-2019-14615 Graphics Vulnerability

  • More Details On Intel's CVE-2019-14615 Graphics Vulnerability, a.k.a. iGPU Leak

    As for CVE-2019-14615 the Intel graphics vulnerability disclosed this week affecting Gen7 through Gen9 graphics architectures, it's been dubbed "iGPU Leak" by the researchers involved. Thanks to the researcher who originally discovered this vulnerability having reached out to us, we now have some more information on this issue they describe as a "dangerous vulnerability."

    This is the vulnerability that initially piqued our interest over the big graphics performance hit to older Ivybridge/Haswell processors with integrated graphics where in the initial patches we've seen quite dramatic losses.. Fortunately though the current Gen9 graphics have a mitigation where we're seeing fortunately no change in performance. As relayed yesterday, however, they hope for no Gen7 graphics performance penalty in the final version of their mitigation.

Intel Gen7 Graphics Mitigation Will Try To Avoid Performance

More Benchmarks Of The Initial Performance Hit

  • More Benchmarks Of The Initial Performance Hit From CVE-2019-14615 On Intel Gen7 Graphics

    On Wednesday I shined the light on the initial performance hit from Intel's CVE-2019-14615 graphics vulnerability particularly striking their "Gen7" graphics hard. That initial testing was done with Core i7 hardware while here are results looking at the equally disturbing performance hits from Core i3 and i5 affected processors too.

    This article offers some benchmarks with Core i3/i5 results added in alongside the i7 CPUs previously tested with the Gen7 graphics found most commonly with Ivy Bridge and Haswell processors. Each distinct system was tested before/after from the CVE-2019-14615 posted on Wednesday.

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.

More in Tux Machines

today's howtos

Programming: Golang, Perl, Python and the GCC Story

  • 9 Reasons You Should Use Golang Language

    Golang is the open-source programming language developed by Google in the year 2007. Several programming languages are present in the market with advantages and disadvantages. We cannot predict which language is better, it would take months to discuss. However, the most sensible thing that helps choose a better language is the one that suits a specific purpose more reliably than the others. Thus, Golang development will be most suitable for those who are willing to combine simplicity, concurrency, and safety of the code. Different programming languages are less memory efficient and are unable to communicate with the hardware. Therefore, Golang is one of the most preferred languages for developers that help build software. It is also the open-source and procedural language that is advantageous to deploy simple, effective, and reliable software. Go language aids the environment to adopt different patterns that are similar to dynamic languages. Go language has several advantages that are responsible to quicken the development process. Moreover, Golang is the language that makes the process of software development easy and simple for programmers. These days, Golang is gaining popularity amongst the developers as it has a plethora of advantages than the other programming languages. So, the use of Golang has been adopted by mobile app development companies.

  • Demonstrating PERL with Tic-Tac-Toe, Part 1

    PERL is a procedural programming language. A program written in PERL consists of a series of commands that are executed sequentially. With few exceptions, most commands alter the state of the computer’s memory in some way. Line 00 in the Tic-Tac-Toe program isn’t technically part of the PERL program and it can be omitted. It is called a shebang (the letter e is pronounced soft as it is in the word shell). The purpose of the shebang line is to tell the operating system what interpreter the remaining text should be processed with if one isn’t specified on the command line. Line 02 isn’t strictly necessary for this program either. It makes available an advanced command named state. The state command creates a variable that can retain its value after it has gone out of scope. I’m using it here as a way to avoid declaring a global variable. It is considered good practice in computer programming to avoid using global variables where possible because they allow for action at a distance. If you didn’t follow all of that, don’t worry about it. It’s not important at this point.

  • Perl Weekly Challenge 048: Survivor and Palindrome Dates

    I tried two different approaches to the problem. The first one uses an array of living people and a variable $sword that stores the index of the person holding the sword. In each iteration of the loop, the next person is removed from the array, and the sword is passed to the next person. The “next person” has a special cyclic meaning: at the end of the array, the sword must return to the beginning. This is achieved by using the modulo operator %. Note that we use it twice, once to find the person to kill, and once to find the person to pass the sword to—and each case uses a different array size in the modulo operation, as killing a person changes the size of the array.

  • My Unexpected Dive into Open-Source Python

    I'm very happy to announce that I have joined Quansight as a front-end developer and designer! It was a happy coincidence how I joined- the intersection of my skills and the open source community's expanded vision. I met Ralf Gommers, the director of Quansight Labs, at the PyData Conference in New York City last year after giving a Lightning Talk. However, as cool and confident as this may sound, I sure didn't start off that way. At that point, it's been a few months since I graduated from a coding bootcamp. I was feeling down in the job-search funk. I hadn't even done much in Python, since my focus was in Javascript.

  • Reposurgeon defeats all monsters!

    On January 12th 2020, reposurgeon performed a successful conversion of its biggest repository ever – the entire history of the GNU Compiler Collection, 280K commits with a history stretching back through 1987. Not only were some parts CVS, the earliest portions predated CVS and had been stored in RCS. I waited this long to talk about it to give the dust time to settle on the conversion. But it’s been 5 weeks now and I’ve heard nary a peep from the GCC developers about any problems, so I think we can score this as reposurgeon’s biggest victory yet. The Go port really proved itself. Those 280K commits can be handled on the 128GB Great Beast with a load time of about two hours. I have to tell the Go garbage collector to be really aggressive – set GOGC=30 – but that’s exactly what GOGC is for.

Kdenlive: From Beginner to Advanced Video Editing

This is a different kind of video because it has a bit of Time Travel in it. In June 2019, I presented a talk at the SouthEast LinuxFest entitled “Kdenlive: From Beginner to Advanced Video Editing”. This was an interesting experience and the editing process took an excessive amount of time which I suppose is fitting for a video about video editing. In this video, you will learn some tips and tricks that I use for working in Kdenlive as well as some cool transitions like Matte Transitions. There was also a very useful Questions & Answers section at the end of the talk. I actually learned some more things during the process of editing this video so there is always plenty to learn about this kind of software. If you would like more Kdenlive videos from me then please leave a comment below. I would be happy to make some specific tutorial videos, this is more of an overview and I think there’s plenty to show in tutorial form. Read more

Videos/Audiocasts/Shows: GNU/Linux and Python, Fresh Look at LMDE 4 Beta

  • Hopeful for HAMR | TechSNAP 423

    We explore the potential of heat-assisted magnetic recording and get excited about a possibly persistent L2ARC. Plus Jim's journeys with Clear Linux, and why Ubuntu 18.04.4 is a maintenance release worth talking about.

  • 2020-02-21 | Linux Headlines

    Red Hat OpenStack Platform reaches version 16, Google announces the mentors for this year’s Summer of Code, DigitalOcean secures new funding, the Raspberry Pi 4’s USB-C power problems get a fix, and the GTK Project unveils its new website.

  • Talk Python to Me: #252 What scientific computing can learn from CS

    Did you come into Python from a computational science side of things? Were you just looking for something better than Excel or Matlab and got pulled in by all the Python has to offer?  That's great! But following that path often means some of the more formal practices from software development weren't part of the journey.  On this episode, you'll meet Martin Héroux, who does data science in the context of academic research. He's here to share his best practices and lessons for data scientists of all sorts.

  • Matt Layman: Templates and Logic - Building SaaS #45

    In this episode, we added content to a template and talked about the N+1 query bug. I also worked tricky logic involving date handling. The first change was to update a course page to include a new icon for any course task that should be graded. After adding this, we hit an N+1 query bug, which is a performance bug that happens when code queries a database in a loop. We talked about why this happens and how to fix it. After finishing that issue, we switched gears and worked on a tricky logic bug. I need a daily view to fetch data and factor in the relative time shift between the selected day and today. We wrote an involved test to simulate the right conditions and then fixed the code to handle the date shift properly.

  • LMDE 4 Beta Debbie Run Through

    In this video, we are looking at LMDE (Linux Mint Debian Edition) 4 Debbie.