Over the past number of weeks the Dell Pro Max with GB10 has been undergoing a lot of testing at Phoronix. This NVIDIA GB10 powered mini PC with its 20 Arm cores (10 x Cortex-X925, 10 x Cortex-A725) and Blackwell GPU offers a lot of combined compute potential for AI and other workloads. In this article is a look at how the Dell Pro Max with GB10 competes with AMD's Ryzen AI Max+ 395 "Strix Halo" within the Framework Desktop SFF PC.

Next-generation AMD server SoCs -- presumably the AMD EPYC "Venice" on Zen 6 -- is poised to introduce a firmware-agnostic platform configuration platform configuration change method/format. This is This aims to improve server platform interoperability and eliminate redundant configuration efforts for different firmware solutions...

Natalie Vock as one of the open-source developers on Valve's Linux graphics team has been spearheading another big ray-tracing performance improvement for the AMD Radeon Vulkan driver. RADV ray-tracing performance improved a lot in 2025 but it's looking like 2026 could be even more exciting...

A new feature in the queue for likely introduction with the next version of the Linux kernel (Linux 6.20~7.0) is compiler-based context and locking analysis. This kernel code depends on the yet-to-be-released LLVM Clang 22 compiler but can provide some powerful insights to kernel developers...

For those with Acer laptops running Linux on GitHub there has been an out-of-tree driver providing an experimental "acer-wmi-battery" kernel module to allow controlling battery-related features. Now a cleaned-up version of that driver is working on getting into the mainline Linux kernel...

Back in October was an initial proposal for a DRM splash screen client for the Linux kernel that would be primarily useful for embedded systems for rendering a simple "splash screen" when updating the system firmware/software, early display activation at boot, during system recovery, or similar processes. Sent out today was a second revision to the DRM splash screen code...

The Linux kernel's "new mount API" that has been in the kernel since 2019 and recently made rounds for taking 6+ years to land the man page documentation on it will soon be the the only mount API internally within the kernel. Removing the "old" Linux kernel mount API internals is a candidate for the upcoming Linux 7.0 kernel cycle...

The Gentoo Linux project published their 2025 retrospective this week with their many accomplishments, including the recruitment of four more developers and now being up to 31,663 ebuilds and a total of 89GB worth of x86_64 binary packages on mirrors...

The Fedora Engineering and Steering Committee (FESCo) has approved a Fedora 44 change for switching all KDE variants away from using the SDDM display manager to instead use the newer Plasma Login Manager...

The Rust-written Redox OS operating system had an exciting end to the year as it began developing its own native Intel graphics driver...

With some Linux distributions like Fedora Workstation and Ubuntu defaulting to "madvise" Transparent Hugepages (THP) while others like CachyOS and openSUSE defaulting to "always", you may be curious about the madvise vs. always THP difference in modern Linux environments. If so this round of benchmarking is for you in looking at the performance impact of madvise vs. always THP.

LLVM developers and other stakeholders have begun debating the use of pre-compiled headers "PCH" as a means of speeding up the compiulation of the LLVM compiler infrastructure by 1.5x to 2x than with non-PCH builds...

Back on the 1st Valve published the Steam Survey results for December 2025 and they put the Linux gaming marketshare at 3.19%, a 0.01% dip from November. But now the December results have been revised with a nice bump to the Linux marketshare...

Open-source developer Sebastian Wick has written a blog post outlining work to improve the graphics driver situation for Flatpaks. Particularly around situations like the NVIDIA driver stack that may depend upon a specific kernel version or where a Flatpak runtime may be end-of-life, dealing with GPU drivers in Flatpaks can be a burden. A solution being explored is GPU virtualization to deal with those GPU driver handling challenges while still providing robust and secure GPU access...

Last year AMD announced GAIA as short for "Generative AI Is Awesome". It started off as a Windows-only AI demo but over time added Linux support along with introducing different AI agents. For going along with AMD's AI announcements at CES 2026, AMD released GAIA 0.15 where they are now positioning this software as a framework/SDK for building AI PC agents...

Yesterday when Intel formally introduced Panther Lake as the Core Ultra Series 3 with pre-orders set to begin today and available globally later this month, one of the key questions remaining was around pricing... I've been scouting various Internet retailers today and so far have found a Ultra X7 358H model with the 12 Xe cores for the Xe3 integrated graphics to be priced around $1299 USD with 32GB of RAM...

On Monday the first release candidate of the GStreamer 1.28 multimedia framework was released. As is a recurring focus in recent releases, more GStreamer code is written in Rust for memory safety especially around decoding content...

Lisa Su's keynote just wrapped up at CES 2026 and in turn the embargo regarding AMD's first consumer product announcements for 2026. The AMD Ryzen AI 400 series and new Ryzen 7 9850X3D 3D V-Cache processors are what's in focus for CES this year.

Intel just hosted their CES keynote where they formally launched Panther Lake as the Core Ultra Series 3 SoCs...

Back in November AMD began posting open-source Linux graphics driver patches for some next-gen graphics IP. Those IP block patches were for MMHUB, PSP, and other blocks making up modern AMD GPUs. The GFXHUB patch pointed it to being part of the GFX12 / RDNA4 family. Out today are new patches for enabling the SMU15 IP and an interesting takeaway there is some apparent NPU integration for future Radeon graphics...