It was back in May that the surprising event happened of AMD posting HDMI 2.1 FRL patches for their open-source AMDGPU Linux driver as part of their broader HDMI 2.1 bring-up. For years the open-source HDMI 2.1 support in AMDGPU was blocked by the HDMI Forum but whether it was due to Valve or some other event, the code was finally unblocked. While it's been part of the kernel since Linux 7.2, it's been disabled by default -- except that is now changing.

Following last week's main set of memory management "MM" related updates for Linux 7.3, another batch of MM code updates were submitted and merged today as we prepare to close out the Linux 7.3 merge window. There are a few optimization patches that stand out along with other mostly small fixes/changes.

Back in July ROCm 7.14 was announced as their new production release built atop TheRock build system and introducing Ryzen AI 400 series support. The versioning choice was a bit odd since ROCm 7.2 was the stable release at the time while ROCm 7.9+ turned into "tech preview" releases. With ROCm 7.14, it was declared stable. In clearing up that versioning mess, they have done a major version bump... to ROCm 10.0.

Earlier this week I showed off some of the very nice Btrfs performance gains on Linux 7.3. For those wondering what kernel optimizations may have carried over to other file-systems or other file-system specific enhancements, here are Linux 7.2 vs. 7.3 Git performance benchmarks across Btrfs, EXT4, F2FS, and XFS on the same system.

With the never-ending quest for greater I/O performance in the HPC space and the demands all the more relentless in the AI era, the Linux kernel block subsystem activity continues to be as vibrant as ever along with the ongoing innovations in the IO_uring space.

For those interested in making use of the recently released DeepSeek V4 Flash model, AMD developers have released Lemonade 11.8 that now makes it rather trivial to get DeepSeek V4 Flash up and running on AMD Ryzen AI+ Max "Strix Halo" systems.

Werner Koch announced today the release of Libgcrypt 1.12.3 with various bug fixes and more exciting are the performance improvements.

Merged back in 2023 was Intel ANV Vulkan Video support for H.265 decoding. But it's been slightly out of compliant with the Vulkan spec, which is now fixed with the newest code for Mesa 26.3 by engaging the HuC firmware.

The AppArmor improvements have been merged for Linux 7.3 for this kernel security module providing per-program Linux application security controls around system resources. Most notable this cycle is being able to load user-space compressed policies.

The LLVM/Clang compiler toolchain merged overnight better support for the nearly decade-old AMD Zen 1 processors and also helps with Zen+ and Zen 2 processors too. This latest work thanks to the open-source community is for providing more informed instruction scheduling around PDEP and PEXT that end up being quite costly for these original Zen processors.

The Network File-System (NFS) improvements for both the client and server code have been merged for the nearly-over Linux 7.3 merge window.

The Asahi Linux crew working to bring Linux support to Apple Silicon hardware is out today with a new status update on their initiatives, largely around Apple M3 bring-up as well as some M4/M5 achievements.

Patches sent out to the Linux kernel mailing list today can provide much more efficient Zstd compression and decompression by addressing a very unfortunate oversight in the existing code.

KSMBD as the in-kernel SMB3/CIFS server for higher performance and lower resource usage than user-space SMB/CIFS protocol implementations is becoming even more useful with the in-development Linux 7.3 kernel.

Last week I provided a look at the Intel Xeon 600 series Hyper Threading performance with the Xeon 678X "Granite Rapids WS" processor for HT/SMT on and off. That was interesting while another reader request was to look at the CPU core scaling performance for this high-end workstation processor. Here are those benchmarks for showing the performance, power, and frequency/thermal impact of the Xeon 678X when limited to 6 cores, 12 cores, 24 cores, 48 cores, and then the 48 cores + HT default configuration.

Haiku R1 Beta 5 came out in September 2024 while out today is the long-awaited sixth beta for this open-source operating system inspired by BeOS. This beta release also comes one week ahead of the project's 25th anniversary.

AMD's compiler team is proposing a new LLVM Clang compiler option, -fenable-readonly-thp for implementing instruction Transparent Huge Pages "iTHP" at compile and link-time. With -fenable-readonly-thp, they are finding more performance out of SPEC CPU, Geekbench, and other workloads from the arranging of 2MB segment alignment at link time and allowing the executable text range can be promoted to huge pages.

Earlier this month when benchmarking six Linux distributions on the new Framework Laptop 13 Pro powered by Intel Core Ultra Series 3 "Panther Lake", the performance was strangely slow on Fedora Workstation 44. When digging further into it, the performance loss was with Fedora 44 using Tuned-PPD by default where as other Linux distributions default to Power Profiles Daemon. Ultimately, after Red Hat engineers got involved, was found to be a bug within the Intel P-State kernel driver exhibited by Tuned-PPD. The latest Linux kernel already has a fix in place and will be back-ported to Fedora 44.

Intel is preparing to introduce a new Linux driver named "BFF" for dealing with aging processor silicon where bits may become stuck over time.

Armbian as the Debian/Ubuntu-derived distribution that provides an optimized platform for ARM and RISC-V single board computers is out today with a major update.