AMD EPYC 7002 & Ryzen 3000 Series Dominated Linux Interest During August
AMD Zen 2 processors continue intriguing Linux/open-source fans, at least among our reader base. Linux fans appear to be loving the invigorated competition out of AMD in reshaping the CPU market for both desktops and servers. Also attracting a lot of interest in August was the in-development Linux 5.3 kernel, the new "SWAPGS" vulnerability, continued open-source graphics driver improvements, and other software milestones.
Of the 270 news articles on Phoronix last month, the most popular articles are listed below followed by the most popular hardware reviews/benchmarks for the month. If you enjoy the daily original open-source/Linux content on Phoronix, consider showing your support in September by at the very least not viewing this site with an ad-blocker otherwise joining Phoronix Premium for the site ad-free and multi-page articles on a single page. PayPal tips are also accepted. Looking ahead to September will be tests of more AMD processors, Linux 5.4 kernel development cycle kicking off, and plenty more benchmarks.
NVIDIA Starts Publishing GPU Hardware Documentation To Help Open-Source Drivers
Today is a wild one for open-source/Linux users. Let's begin with the unexpected news: NVIDIA is releasing more GPU hardware documentation at long last! Yes, freely-available hardware interface documentation to assist in the development of the open-source NVIDIA Linux driver (Nouveau).
Summing Up The AMD EPYC 7742 2P Performance In One Graphic
If you didn't have a chance since last night to check out our benchmarks of the AMD EPYC 7742 and EPYC 7502 Linux performance, I certainly encourage you to do so. Even if you aren't a server enthusiast, it's incredible to see the engineering achievement of AMD with Zen 2 and how the race is certainly back on in the CPU space. If you are short on time, here's the quick summary of our initial AMD EPYC 7002 benchmark results.
Yes, Linux Does Bad In Low RAM / Memory Pressure Situations On The Desktop
It's been a gripe for many running Linux on low RAM systems especially is that when the Linux desktop is under memory pressure the performance can be quite brutal with the system barely being responsive. The discussion over that behavior has been reignited this week.
CVE-2019-1125 "SWAPGS" Is The Newest Spectre Vulnerability
CVE-2019-1125 was made public today or also referred to as the "SWAPGS" vulnerability as a new variant of Spectre V1 affecting Windows and Linux with Intel (and according to mixed information, AMD - though the current Linux kernel patches at least seem to only apply to Intel) x86_64 processors.
Building The Default x86_64 Linux Kernel In Just 16 Seconds
It's now been one week since the launch of AMD's EPYC Rome processors with up to 64 cores / 128 threads per socket and better IPC uplift compared to their previous-generation parts. Rome has outperformed Intel Xeon Scalable CPUs in their class while offering better power efficiency and way better performance-per-dollar. One of my favorite metrics has been how quickly the new EPYC 7742 2P can build the Linux kernel.
Intel's Linux Graphics Driver Developers Discover 3~20% Boost For Current-Gen Hardware
Last week was the Intel Gallium driver one line patch to boost performance by 1%. Today's code churn within Mesa for Intel's open-source Linux graphics drivers were larger but also with a more profound performance impact with some workloads now being faster by around 20%. Making this more exciting is that today's round of driver optimizations apply to the very common and mature "Gen 9" graphics hardware.
Firefox 68 vs. Chrome 76 Linux Web Browser Performance Benchmarks
With this week's release of the Chrome 76 web browser, here are some fresh benchmarks of that latest Google web browser release compared to Firefox 68 on Ubuntu Linux.
Valve's Proton Offers Branch With VKD3D For Direct3D 12 Over Vulkan
While VKD3D continues to be under heavy development, Valve already appears pleased with it enough that it's now being built as part of their Wine-based Proton software for powering Steam Play on Linux.
How Can AMD EPYC "Rome" 7002 Series Be Even Better? Open-Source BIOS / Coreboot
By now you've likely seen the fantastic performance out of AMD's new "Rome" 7002 series processors. The performance is phenomenal and generally blowing well past Intel's Xeon Cascade Lake processors. So that's all good and it can get even better outside of performance: I asked AMD about the prospects of Coreboot / open-source BIOS support and got a surprising response.
Red Hat Joins The RISC-V Foundation
Red Hat has joined the RISC-V Foundation to help foster this open-source processor ISA.
And the most popular featured articles:
AMD EPYC 7502 + EPYC 7742 Linux Performance Benchmarks
Now that you have read our AMD EPYC "Rome" 7002 series overview, here is a look at the initial performance benchmarks from our testing over the past few weeks. This testing focused on the new AMD EPYC 7502 and EPYC 7742 processors in both single (1P) and dual (2P) socket configurations using AMD's Daytona server reference platform. Tests were done on Ubuntu Linux and compared to previous AMD EPYC processors as well as Intel Xeon Scalable.
POWER9 & ARM Performance Against Intel Xeon Cascadelake + AMD EPYC Rome
For those wondering how ARM and IBM POWER hardware stack up against AMD's new EPYC "Rome" processors and that of Intel's existing Xeon "Cascade Lake" processors, here is a round of tests from the POWER9 Talos II, Ampere eMAG, and Cavium ThunderX in looking at the cross-architecture Linux CPU performance currently in the server space.
AMD Zen 2 Performance Looking Even Better With GCC 10
While this year's GCC 9 compiler release brought initial support for AMD Zen 2 processors with the Znver2 target, the support was sadly incomplete. While the GCC 9 support added some of the new instructions, it wasn't complete (such as RDPRU support remains missing) and the cost tables and scheduler model were not updated from Znver1 to account for the microarchitectural changes. Thankfully, SUSE's compiler experts recently fixed up this support for the GCC 10 compiler and more recently were able to get it back-ported for the upcoming GCC 9.2 for the Linux distributions that will upgrade to that point release. Here are some benchmarks looking at the performance impact of that updated AMD Zen 2 compiler code.
Intel Core i9 9900K vs. AMD Ryzen 9 3900X Linux Gaming Performance
Here is our most extensive look yet at the AMD Ryzen 9 3900X Linux gaming performance up against the Intel Core i9 9900K while testing the latest Linux drivers with the Radeon RX 5700 XT as well as the NVIDIA GeForce RTX 2070 and RTX 2080 graphics cards. Beyond testing all the benchmark-friendly Linux-native and Steam Play OpenGL/Vulkan games, the performance-per-Watt and performance-per-dollar of the tested systems are also being covered.
AMD Ryzen 5 3600X Linux Performance
Now that the new AMD Ryzen 3000 series are running great with the latest Linux distributions following prominent motherboard vendors issuing BIOS updates that correct the "RdRand" issue, we're moving on with looking at the performance of the rest of the Ryzen 3000 series line-up while having freshly re-tested the processors under Ubuntu 19.04. Up for exploration today is the AMD Ryzen 5 3600X, the six-core / 12-thread processor retailing for about $250 USD.
Cooling The Raspberry Pi 4 With The Fan SHIM & FLIRC For Better Performance
With the Raspberry Pi 4, a passive heatsink is an absolute minimum for running this new ARM SBC unless you want to deal with potentially drastic performance limitations based upon your operating conditions. However, if you will be enduring the Raspberry Pi 4 with significant load for any measurable length of time, an active cooler is almost warranted or otherwise a very capable passive cooler. In this article we're looking at the Raspberry Pi 4 performance with a Fan SHIM as an active fan designed for running on the Raspberry Pi off the GPIO pins as well as the FLIRC as a metal case that passively cools the device.
GCC vs. LLVM Clang vs. AOCC Compiler Benchmarks On The AMD EPYC 7742
While AMD's hardware folks were launching the EPYC 7002 series, their software crew was pushing out the AMD Optimizing C/C++ Compiler 2.0 with support/optimizations for the Zen 2 micro-architecture. Using the top-end AMD EPYC 7742 in a 2P Linux server configuration, here are C/C++ compiler benchmarks looking at the performance when built by the GNU Compiler Collection (GCC), LLVM Clang, and AOCC 2.0.
Initial Benchmarks Of The Spectre "SWAPGS" Mitigation Performance Impact
Yesterday the SWAPGS vulnerability was made public as a new variant of Spectre V1 that affects all operating systems and is believed to affect only Intel CPUs. The SWAPGS discovery by Bitdefender was quietly mitigated by Microsoft for Windows 10 last month while yesterday the patches were posted for the mainline Linux kernel as the Grand Schemozzle. As soon as learning of this SWAPGS vulnerability and seeing the kernel code, I began running some preliminary performance tests to look at the impact of this latest CPU mitigation.
AMD Ryzen 5 3400G Is Working Well On Linux
AMD Raven Ridge APUs were a rough launch particularly on Linux where even with the latest motherboard BIOS updates and Linux kernel I am still hitting occasional stability issues, so when the opportunity arose recently to try out the Ryzen 5 3400G as the successor in the Picasso family, I was interested. Fortunately, AMD Picasso APUs have proven to be in better shape on Linux so here is the initial round of performance tests for those interested in the AMD Linux performance on Ubuntu.
Blender 2.80 Performance With Intel Xeon Platinum 8280 vs. AMD EPYC 7742
The Blender 2.80 release arrived at the end of July that unfortunately was too late for using that big new release in our launch-day testing of AMD's EPYC 7002 "Rome" processors but as a follow-up here are AMD EPYC 7742 performance benchmarks up against the Intel Xeon Platinum 8280 Cascade Lake as well as the AMD EPYC 7601 2P. Blender 2.80 performance is the focus of this article along with some other renderer benchmarks.