phoronix 

feeds.twtxt.net

Linux Performance, Benchmarks & Open-Source News - Phoronix

Wine-Staging 11.1 Adds Patches For Enabling Recent Adobe Photoshop Versions On Linux
Following yesterday’s release of Wine 11.1 for kicking off the new post-11.0 development cycle, Wine-Staging 11.1 is now available for this experimental/testing version of Wine that present is around 254 patches over the upstream Wine state… ⌘ Read more

⤋ Read More

CachyOS Starts 2026 By Switching To Plasma Login Manager & Live ISO Using Wayland
The Arch Linux powered CachyOS distribution is out with its first new ISO release of 2026. This Linux distribution continues to be quite popular with Linux gamers, enthusiasts craving peak performance, and others for wanting to enjoy a polished Arch Linux desktop experience… ⌘ Read more

⤋ Read More

DXVK-NVAPI 0.9.1 Released With New Override & Improvements
DXVK-NVAPI 0.9.1 is out today as this NVIDIA NVAPI implementation that is used by Valve’s Steam Play (Proton) with DXVK and VKD3D-Proton. This is the important piece of the Steam Play puzzle to allow for NVIDIA DLSS, NVIDIA Reflex, PhysX, and other features for Windows games running on Linux… ⌘ Read more

⤋ Read More

A Decade In The Making, Time Slice Extension Could Be Merged For Linux 7.0
With the upcoming Linux 6.20~7.0 kernel cycle it looks like the time slice extension work could finally been merged, which has seen various attempts over the past decade. Time slice extension for the Linux kernel implemented using Restartable Sequences “RSEQ” allows user-space processes to request a temporary, opportunistic extension of their CPU time slice without being preempted… ⌘ Read more

⤋ Read More

AMD Releases MLIR-AIE 1.2 Compiler Toolchain For Targeting Ryzen AI NPUs
In addition to AMD releasing the Ryzen AI Software 1.7 release on Friday, they also published a new version of their MLIR-AIE compiler toolchain for targeting AMD Ryzen AI NPU devices with this LLVM-based MLIR-focused stack… ⌘ Read more

⤋ Read More

AMDGPU Driver Reverts Code For A Number Of Regressions On Linux 6.19
Merged on Friday as part of this week’s DRM kernel graphics driver fixes for the week is addressing a regression affecting many different users with the Linux 6.19 development kernel… ⌘ Read more

⤋ Read More

GNOME’s AI Assistant Newelle Adds Llama.cpp Support, Command Execution Tool
Newlle as a virtual AI assistant for the GNOME desktop with API integration for Google Gemini, OpenAI, Groq, and also local LLMs is out with a new release. Newelle has been steadily expanding its AI integration and capabilities and with the new Newelle 1.2 are yet more capabilities for those wanting AI on the GNOME desktop… ⌘ Read more

⤋ Read More

ASUS Armoury Driver For Linux 6.19 Picks Up Support For More ASUS Laptops
A new driver in the Linux 6.19 kernel is the ASUS Armoury driver for supporting additional functionality with the ROG Ally gaming handhelds and other ASUS ROG gaming hardware like their laptops. The ASUS Armoury driver builds off the existing ASUS WMI driver but provides some design improvements to make it better than handling it within the existing driver. There is support for adjusting the APU-allocated memory, Intel core count control … ⌘ Read more

⤋ Read More

KDE Plasma Saw At Least 9 Crash Fixes This Week
KDE Plasma 6.6 feature development work continues winding down while Plasma 6.7 has begun seeing more feature work. This week also saw at least nine different crash fixes affecting Plasma/KWin… ⌘ Read more

⤋ Read More

GNU C Library 2.43 Released With More C23 Features, mseal & openat2 Functions
Version 2.43 of the GNU C Library “glibc” was released on Friday evening as the newest half-year feature update. This is a very feature packaged update and even managed to be released ahead of the 1 February release plan… ⌘ Read more

⤋ Read More

Wine 11.1 Released In Kicking Off The New Development Cycle
Following the release of Wine 11.0 stable just under two weeks ago, Wine 11.1 is now available as the first of the bi-weekly development snapshots for Wine in leading toward the Wine 12.0 release next January… ⌘ Read more

⤋ Read More

Firmware Upstreamed For Audio Support With Upcoming Dell & Lenovo Panther Lake Laptops
Similar to the new Intel IPU 7.5 firmware upstreamed for Panther Lake this week, Cirrus has upstreamed their CS42L45 codec firmware for upcoming Dell and Lenovo laptops making use of this audio codec… ⌘ Read more

⤋ Read More

Linux 6.19 Scheduler Feature Being Disabled Due To Performance Regressions
Queued into tip/tip.git’s “sched/urgent” Git branch today is a patch to disable the kernel scheduler’s NEXT_BUDDY functionality that was re-implemented back during the Linux 6.19 merge window. It turns out to cause some performance regressions that have yet to be otherwise addressed… ⌘ Read more

⤋ Read More

Linux 6.19 Scheduler Feature Being Disabled Due To Performance Regressions
Queued into tip/tip.git’s “sched/urgent” Git branch today is a patch to disable the kernel scheduler’s NEXT_BUDDY functionality that was re-implemented back during the Linux 6.19 merge window. It turns out to cause some performance regressions that have yet to be otherwise addressed… ⌘ Read more

⤋ Read More

VVenC H.266 Encoder Rolls Out More ARM Optimizations For Nice Performance Gains
Fraunhofer HHI this week released a new version of VVenC, their open-source H.266 video encoder. Among the changes this release are more performance optimizations for ARM and I have run some comparison benchmarks using a NVIDIA GB10 SoC with the Dell Pro Max GB10… ⌘ Read more

⤋ Read More

Vulkan Roadmap 2026 Milestone: Variable Rate Shading, Host Image Copies & More
In addition to the release today of Vulkan 1.4.340 with the new descriptor heap “VK_EXT_descriptor_heap” extension and three other new extensions, The Khronos Group’s Vulkan Working Group has also published the Vulkan Roadmap 2026 Milestone… ⌘ Read more

⤋ Read More

AMD Ryzen AI Software 1.7 Released For Improved Performance On NPUs, New Model Support
AMD today released a new version of Ryzen AI Software, the user-space packages for Microsoft Windows and Linux for making use of the Ryzen AI NPUs for various AI software tasks like Stable Diffusion, ONNX, and more… ⌘ Read more

⤋ Read More

GNU Guix 1.5 Released With RISC-V Support, Experimental x86_64 GNU Hurd Kernel
GNU Guix 1.5 is out today as the latest major release for this platform built around its functional package manager. This is a big upgrade with it having been three years since the GNU Guix 1.4 release… ⌘ Read more

⤋ Read More

Linux Lands Fix For Its “Subtly Wrong” Page Fault Handling Code For The Past 5 Years
Merged today for the Linux 6.19 Git kernel and then in turn for back-porting to prior Linux kernel series is making the x86 page fault handling code disable interrupts properly. Since 2020 it turns out the handling was subtly wrong but now corrected by Intel… ⌘ Read more

⤋ Read More

Zlib-rs 0.6 Released With Improved AVX-512 Support
Zlib-rs is the effort out of the Trifecta Tech Foundation to provide a Zlib compression implementation written in the Rust programming language that can serve as a C dynamic library and Rust crate. The intent here being that zlib-rs is potentially safer than the classic C-based implementation of Zlib… ⌘ Read more

⤋ Read More

Vulkan 1.4.340 Released With Descriptor Heap & Other New Extensions
Vulkan 1.4.340 is out today as the first significant new Vulkan API update following the end of year holidays. With Vulkan 1.4.340 comes four new extensions worth talking about… ⌘ Read more

⤋ Read More

Servo 0.0.4 Browser Engine Released & Finally Supporting Multiple Windows
Servo 0.0.4 is out today as the newest monthly update to this open-source, Rust-based web browser engine. Building off recent Servo embedding API additions, Servo 0.0.4 introduces support for multiple browser windows… ⌘ Read more

⤋ Read More

AMD Lands Fresh Performance Improvements For RDNA4 In RadeonSI Driver
While slightly too late for making it into the Mesa 26.0 release that branched yesterday, merged now to Mesa Git for Q2’s Mesa 26.1 release are some new RadeonSI Gallium3D (OpenGL) driver optimizations for the latest AMD Radeon RDNA4 graphics cards… ⌘ Read more

⤋ Read More

Linux GPU Driver Loophole Being Fixed For Unprivileged Users Being Able To Tap Unbounded Kernel Memory
An oversight in the Linux kernel’s Direct Rendering Manager (DRM) graphics driver common code could allow unprivileged users to trigger unbounded kernel memory consumption for a potential system-wide out-of-memory “OOM” situation… ⌘ Read more

⤋ Read More

Intel Xeon 67980E “Sierra Forest” Linux Performance ~14% Faster Since Launch
As part of my end-of-year 2025 benchmarking I looked at how the Intel Xeon 6980P Granite Rapids performance evolved in the year since launch and seeing some nice open-source/Linux optimizations during that time. On the other side of the table were also benchmarks of how AMD EPYC 8004 Sienna evolved in its two years, the AMD EPYC Milan-X in its four years since launch, and also a look at the performance evolution lower down the st … ⌘ Read more

⤋ Read More

AMD Announces Ryzen 7 9850X3D Pricing Of $499 USD
Back at CES AMD announced the Ryen 7 9850X3D as a faster sibling to the Ryzen 7 9800X3D. Today they have announced the suggested price for this 3D V-Cache desktop processor and confirmation of its availability starting on 29 January… ⌘ Read more

⤋ Read More

Updated Intel Panther Lake IPU Firmware Published With New Features & Bug Fixes
Ahead of the first Intel Core Ultra Series 3 Panther Lake laptops expected to hit retail channels next week, Intel has published updated IPU7 (IPU 7.5) firmware for the image processing unit used by the web cameras on the higher-end Panther Lake laptops… ⌘ Read more

⤋ Read More

AMD AOMP 22.0-2 Released With Flang Fortran Improvements
Yesterday along with releasing ROCm 7.2 there was also the release of AOMP 22.0-2 as the newest version of their open-source downstream of LLVM/Clang/Flang that is focused on offering the best OpenMP/OpenACC offloading support to Instinct/Radeon hardware… ⌘ Read more

⤋ Read More

Prominent Intel Compiler Engineer Heads Off To AMD
James Brodman worked for the last 15 years at Intel on their ISPC SIMD compiler and then in more recent years on the Intel DPC++ compiler and SYCL support as part of Intel’s oneAPI initiative. Rather interestingly, this compiler expert has now joined AMD… ⌘ Read more

⤋ Read More

ReactOS Celebrates 30 Years In Striving To Be An Open-Source Windows Implementation
The ReactOS project is celebrating today that it marks 30 years since their first code commit in the ReactOS source tree. During the past 30 years now the project has seen more than 88k commits from more than 300 developers as it seeks to be a robust open-source Windows implementation. In their 30 year birthday blog post they also provide a look ahead at what they’re working on… ⌘ Read more

⤋ Read More

Linux Finally Retiring HIPPI: The First Near-Gigabit Standard For Networking Supercomputers
While the Linux kernel has been seeing preparations from NVIDIA for 1.6 Tb/s networking in preparing for next-generation super-computing, the kernel has still retained support to now for the High Performance Parallel Interface. HIPPI was the standard for connecting supercomputers in the late 1980s and a portion of the 1990s with being the first networking standard for near-Gigabit connectivity at 800 Mb/s over distances up to … ⌘ Read more

⤋ Read More

AMD Sends Out Linux Patches For Next-Gen EPYC Features: GLBE, GLSBE & PLZA
Sent out to the Linux kernel mailing list this afternoon were a set of 19 patches in preparing for some new CPU features presumably to be found with AMD’s next-generation EPYC “Venice” processors… ⌘ Read more

⤋ Read More

AMD ROCm 7.2 Now Released With More Radeon Graphics Cards Supported, ROCm Optiq Introduced
Back at CES earlier this month AMD talked up features of the ROCm 7.2 release. ROCm 7.2 though wasn’t actually released then, at least not for Linux. That ROCm 7.2.0 release though was pushed out today as the latest improvement to this open-source AMD GPU compute stack and officially extending the support to more Radeon graphics cards… ⌘ Read more

⤋ Read More

Mesa 26.0-rc1 Released With RADV Improvements Leading The Way Along With Intel & NVK
Eric Engestrom just released Mesa 26.0-rc1 with the code for this quarter’s Mesa feature release now branched and under a feature freeze leading up to the stable release in February… ⌘ Read more

⤋ Read More

PyTorch 2.10 Released With More Improvements For AMD ROCm & Intel GPUs
PyTorch 2.10 is out today as the latest feature update to this widely-used deep learning library. The new PyTorch release continues improving support for Intel GPUs as well as for the AMD ROCm compute stack along with still driving more enhancements for NVIDIA CUDA… ⌘ Read more

⤋ Read More

The CPU Performance Of The NVIDIA GB10 With The Dell Pro Max vs. AMD Ryzen AI Max+ “Strix Halo”
With the Dell Pro Max GB10 testing at Phoronix we have been focused on the AI performance with its Blackwell GPU as the GB10 superchip was designed for meeting the needs of AI. Many Phoronix readers have also been curious about the GB10’s CPU performance in more traditional Linux workloads. So for those curious about the GB10 CPU performance, here are some Linux benchmarks focused today on the CPU performance and going up aga … ⌘ Read more

⤋ Read More

XDG-Desktop-Portal 1.21 Released With Reduced Motion Setting, Support For Linyaps Apps
XDG-Desktop-Portal 1.21 is now available for testing with the latest features for this portal frontend service to Flatpak… ⌘ Read more

⤋ Read More

The CPU Performance Of The NVIDIA GB10 With The Dell Pro Max vs. AMD Ryzen AI Max+ “Strix Halo”
With the Dell Pro Max GB10 testing at Phoronix we have been focused on the AI performance with its Blackwell GPU as the GB10 superchip was designed for meeting the needs of AI. Many Phoronix readers have also been curious about the GB10’s CPU performance in more traditional Linux workloads. So for those curious about the GB10 CPU performance, here are some Linux benchmarks focused today on the CPU performance and going up aga … ⌘ Read more

⤋ Read More

Linux 7.0 Apple Silicon Device Tree Updates Have All The Bits For USB Type-C Ports
Ahead of the Linux 6.20~7.0 cycle kicking off next month, the Apple Silicon Device Tree updates have been sent out for queuing ahead of that next merge window. Notable this round are the Device Tree additions for rounding out the USB 2.0/3.x support with the USB-C ports… ⌘ Read more

⤋ Read More

Adjusting One Line Of Linux Code Yields 5x Wakeup Latency Reduction For Modern Xeon CPUs
A new patch posted to the Linux kernel mailing list aims to address the high wake-up latency experienced on modern Intel Xeon server platforms. With Sapphire Rapids and newer, “excessive” wakeup latencies with the Linux menu governor and NOHZ_FULL configuration can negatively impair Xeon CPUs for latency-sensitive workloads but a 16 line patch aims to better improve the situation. That is, changing one line of actual co … ⌘ Read more

⤋ Read More

New Patches Aim To Make x86 Linux EFI Stub & Relocatable Kernel Support Unconditional
Prominent Intel Linux engineer H. Peter Anvin has posted a new patch series working to clean-up the Linux x86/x86_64 kernel boot code. Besides cleaning up the code, the kernel configuration would drop options around EFI stub mode and relocatable kernels in making those features now always enabled… ⌘ Read more

⤋ Read More

PHPStan Now 25~40% Faster For Static Analysis
For those using the powerful PHPStan tool for static analysis on PHP code, this week’s PHPStan 2.1.34 is promoting optimized performance with projects seeing around 25% to 40% faster analysis times… ⌘ Read more

⤋ Read More

An Exciting Day With More Performance Optimizations Merged For RADV In Mesa 26.0
Mesa 26.0 was due to be branched last week and in turn start its feature freeze but ended up being pushed back to tomorrow (21 January) to allow some lingering features to land. It’s been beneficial for the Radeon Vulkan driver “RADV” with several interesting merge requests having landed in time for Mesa 26.0… ⌘ Read more

⤋ Read More

New Linux Patch Improved NVMe Performance +15% With CPU Cluster-Aware Handling
Intel Linux engineers have been working on enhancing the NVMe storage performance with today’s high core count processors. Due to situations where multiple CPUs could end up sharing the same NVMe IRQ(s), performance penalties can arise if the IRQ affinity and the CPU’s cluster do not align. There is a pending patch to address this situation. A 15% performance improvement was reported with the pending patch… ⌘ Read more

⤋ Read More

Linux 6.19 ATA Fixes Address Power Management Regression For The Past Year
It’s typically rare these days for the ATA subsystem updates in the Linux kernel to contain anything really noteworthy. But today some important fixes were merged for the ATA code to deal with a reported power management regression affecting the past number of Linux kernel releases over the last year. ATAPI devices with dummy ports weren’t hitting their low-power state and in turn preventing the CPU from reaching low-power C-states … ⌘ Read more

⤋ Read More

System76 Continues Driving More Improvements Into The COSMIC Desktop
Following the December launch of Pop!_OS 24.04 LTS and the first major COSMIC desktop release, System76 software engineers have continued making improvements to their Rust-based desktop environment… ⌘ Read more

⤋ Read More

AMD Making It Easier To Install vLLM For ROCm
Deploying vLLM for LLM inference and serving on NVIDIA hardware can be as easy as pip3 install vllm. Beautifully simple just as many of the AI/LLM Python libraries can deploy straight-away and typically “just work” on NVIDIA. Running vLLM atop AMD Radeon/Instinct hardware though has traditionally meant either compiling vLLM from source yourself or AMD’s recommended approach of using Docker containers that contain pre-built versions of vLLM. Finally there is now a blessed P … ⌘ Read more

⤋ Read More

LLVM Adopts “Human In The Loop” Policy For AI/Tool-Assisted Contributions
Following recent discussions over AI contributions to the LLVM open-source compiler project, they have come to an agreement on allowing AI/tool-assisted contributions but that there must be a human involved that is first looking over the code before opening any pull request and similar. Strictly AI-driven contributions without any human vetting will not be permitted… ⌘ Read more

⤋ Read More