Merged today to the GNU Compiler Collection Git code is the new -m128bit-atomic option for next year's GCC 17 feature release.

Manjaro 26.1 Bian-May is now available as the newest feature release to this desktop Linux distribution built atop an Arch Linux base.

One of the most compelling features for Intel Xeon 6 Granite Rapids alongside MRDIMMs is Advanced Matrix Extensions (AMX) for helping accelerate AI workloads and more. AMX is also found with the new Granite Rapids WS processors and in currently having my hands on an Intel Xeon 678X in the HP Z4 G6i workstation, I ran some benchmarks looking at the AMX performance and power impact for this high-end workstation.

Patches posted today to the Linux kernel mailing list provide support for Apple GMUX hybrid graphics support on 2018~2019 Apple MacBook Pros. This allows for better power savings on these nearly decade old MacBook Pro laptops by allowing the discrete GPU to power down and be properly restored as needed.

Hyunjun Ko of Igalia continues working on Vulkan Video support for Intel graphics hardware on Linux with the ANV driver. Merged now for Mesa 26.3-devel is enabling AV1 video encoding via Vulkan Video on DG2/Alchemist hardware.

One of the Direct Rendering Manager changes made for Linux 7.2 was switching to "fair" as the DRM scheduler default in place of the existing FIFO policy. The intent was on making the DRM scheduler policy more fair with this being used by AMDGPU and various other DRM kernel graphics drivers. But due to a last minute regression report, the fair policy is being reverted for Linux 7.2.

It's been quiet since the Mold 2.41 release back in April while today it's now been succeeded by Mold 2.42 for deliver even greater performance out of this high speed linker.

Intel's LLM-Scaler project that was born out of their Project Battlematrix initiative aims to make it easier to run generative AI on Arc (Pro) B-Series graphics cards with the likes of vLLM, ComfyUI, SGLang, and other popular AI software in this Docker-based pre-configured AI stack. This week new LLM-Scaler releases brought same-day support for new models and other enhancements.

LACT is one of the popular third-party Linux GPU configuration and monitoring utilities that works across NVIDIA, AMD, and Intel graphics. This GUI provides GPU overclocking controls plus a wealth of information reporting, which is especially great considering the lack of any official GUI control panel for AMD Radeon and Intel Arc graphics on Linux. With today's LACT 0.10 release, there are yet more features in tow.

For those using QEMU as part of the open-source virtualization stack, QEMU 11.1 is now available with a number of new feature enhancements and fixes.

A new blog post out today from the Redox OS crew highlights all of the interesting improvements made to this Rust-based, open-source operating system over the course of July.

Intel today published their 20260811 CPU microcode updates to fix a variety of issues for existing processors, including shipping the first new microcode images for Bartlett Lake and Wildcat Lake. The new microcode updates stretch back to Intel Core Gen10 processors.

OpenAI announced today they have brought their ChatGPT Desktop application to Linux and is currently in preview form.

As part of my recent Linux testing of the Framework Laptop 13 Pro I had recently benchmarked six Linux distributions on the Framework Laptop 13 Pro. CachyOS was the fastest to not much surprise but arguably the most surprising aspect was finding Fedora Workstation 44 typically running slower than the five other modern Linux distributions benchmarked. Here's a follow-up to that with more Fedora Linux benchmarks and the cause/workaround for Fedora's slower performance on the Intel Panther Lake laptop.

Flatpak 1.19 was released today as a new development release along with the Flatpak 1.18.1 stable point release. Both of these releases ship a number of newly-discovered security issues with this app sandboxing and distribution tech.

GNOME interaction designer Tobias Bernard has shared some of the plans and ideas for long-term GNOME Shell improvements they have been eyeing for future GNOME releases.

Linux developer Rik van Riel has pulled off some nice Linux kernel optimizations over the years and the Meta engineer has been working on another one around batching of look-ups with Linux's follow_page_mask() that is used for translating virtual addresses to the corresponding struct page.

One of the Raspberry Pi device drivers that has remained elusive from the mainline Linux kernel has been for the performance monitoring unit (PMU) for the Broadcom AXI on all Raspberry Pi 1 through Raspberry Pi 5 models. Thanks to the work of a Google engineer, there is a new effort working to get a mainline Linux driver for the Raspberry Pi AXI PMU.

FastFlowLM is the open-source software for getting vision, audio, embedding, and MoE large language models up and running on AMD Ryzen AI NPUs. FastFlowLM 1.0 released today and is also now part of the AMD ROCm software umbrella.

With the recent release of Mesa 26.2 the Rusticl OpenCL driver now supports OpenCL 3.1 on RadeonSI, LLVMpipe, Zink, Intel Iris, and Apple Asahi. But the work is not over and more improvements to this Rust-based, modern OpenCL driver continue to land.