NTFSPLUS Now Supports $MFT File Extension, FITRIM, More Mount Options

The NTFSPLUS Linux kernel driver as a modern NTFS file-system driver implementation continues quickly taking shape as it aims to become the most performant and feature-rich NTFS read/write driver for Linux systems.

It was just one month ago that NTFSPLUS was announced by veteran Linux storage/file-system developer Namjae Jeon. Since then Namjae Jeon has been quickly working on addressing remaining gaps in NTFSPLUS compared to Paragon's NTFS3 driver and other NTFS driver alternatives.

Earlier this week I wrote about NTFSPLUS continuing to develop and
Continue reading...

HQspinlock Proposal For Linux Shows Very Nice Performance Benefits For Large Servers

A Huawei engineer has sent out patches proposing HQspinlock as a Hierarchical Queued NUMA-aware spinlock for the Linux kernel. HQspinlock aims to addresss inefficiencies within the Linux kernel's spinlock on modern NUMA-systems due to frequent and costly cross-NUMA cache-line transfers.

The HQspinlock is described in Thursday's patch proposal as:
"In a high contention case, existing Linux kernel spinlock implementations can become inefficient on modern NUMA-systems due to frequent and expensive cross-NUMA cache-line transfers.

This might happen
Continue reading...

Black Friday Reminder For Those Hating Ads But Loving Linux Hardware/Software

As the one and last friendly reminder, if you enjoy the daily and original content found on Phoronix.com but not liking ads and wanting to view multi-page articles on a single page, native dark mode, and more: the 2025 Black Friday / Cyber Week deal is ending Monday to help support the site while enjoying a discounted rate.

The 2025 Cyber Week deal is ongoing for those wishing to help support Phoronix.com during these difficult times for web publishers and also frustrating times

Vulkan 1.4.335 Released With The Very Notable VK_EXT_present_timing

Vulkan 1.4.335 released a few hours ago as the latest iteration of this high performance graphics and compute API. With being just a week since the prior update and given the US Thanksgiving week, it's on the lighter side in terms of issues addressed. There is one new extension though and it's a big one: VK_EXT_present_timing is finally merged.

As I wrote about back on Wednesday when it was first merged in Git, VK_EXT_present
Continue reading...

Intel

One Of Intel's Xe Open-Source Linux Graphics Driver Maintainers Is Departing

It's been two months since there were any notable Intel Linux engineering departures to note following various layoffs and voluntary departures this year that have unfortunately impacted their Linux/open-source talent. Sadly this US Thanksgiving is a new departure to note: one of Intel's maintainers for the Xe open-source Linux kernel graphics driver is leaving the company. This is for the modern Xe driver used by default since Lunar Lake and playing a pivotal role for Intel Linux graphics moving forward.

Lucas De Marchi sent in the
Continue reading...

GCC 16 Switches To Using C++20 Standard By Default

Following up on the discussion from earlier this month among GCC developers over switching to C++20 by default for the GCC compiler as the default C++ standard when not otherwise set, that change has indeed happened. Merged now is the change defaulting to C++20 (well, the GNU++20 dialect) rather than C++17/GNU++17 when not otherwise specified when compiling C++ code.

GCC developers had discovered that their own codebase wasn
Continue reading...

Intel Battlemage Graphics Enjoyed Nice GPU Compute Performance Gains In 2025

In addition to Intel Arrow Lake desktop performance evolving nicely on Linux over the course of 2025, the Intel Arc B-Series graphics that launched last December with the Arc B580 have evolved quite nicely too with their open-source driver stack. With it coming up on one year since the Arc B580 launch, here is a look at how the GPU compute performance has evolved since that point. Similar Intel Arc B580 Linux graphics comparisons are also coming up in a

Continue reading...

Zlib-ng 2.3.1 Released With More CPU Performance Optimizations

Zlib-ng 2.3.1 is out today as the first stable release in the v2.3 series for this Zlib replacement that carries a variety of performance optimizations for speedier compression/decompression.

Zlib-ng 2.3.1 brings yet more performance optimizations and one of the big drivers to this new release is the Corba CRC32 code:
"The biggest addition is the Chorba CRC32 code, this is a major improvement to crc32 calculation speed for pre-PCLMUL (or
Continue reading...

Valve-Backed Color Pipeline API For Linux Is Finally Ready For Upstream

For those Linux desktop users in the US needing another reason to be thankful this Thanksgiving, a huge and long-awaited accomplishment is ready for merging to the kernel: the Color Pipeline API that is important for HDR is ready for merging! As of last night the code is queued in DRM-Misc-Next for this years-in-the-making effort.

AMD, Igalia, Valve, and other stakeholders have long been working on the Color Pipeline API for advanced color management . Much of the focus has been
Continue reading...

GNU C Library Sees Up To 12.9x Improvement With New Generic FMA Implementation

Just a few days ago I wrote about the Glibc math code seeing a 4x improvement on AMD Zen by changing the used FMA implementation. Merged overnight was a new generic FMA implementation for the GNU C Library and now yielding up to a 12.9x throughput improvement on AMD Zen 3.

Adhemerval Zanella contributed this new generic FMA implementation to the GNU C Library. Zanella explained in the patch landing this new generic Fused Multiply Add (FMA) implementation:
"The current implementation relies on setting the rounding mode for
Continue reading...