Vue normale

Reçu aujourd’hui — 25 octobre 2025
Reçu hier — 24 octobre 2025

OpenGL Sees New Extensions Added To The Registry

24 octobre 2025 à 20:11
It's been rare in recent years seeing any new OpenGL extensions given the wild success these days of the Vulkan API with its vast hardware adoption and increasing software support around that modern graphics and compute API. Yet this October has been unusual with now seeing multiple new OpenGL extensions merged to the OpenGL registry...

The Latest Sheaves Work To Hopefully Improve Linux Performance

24 octobre 2025 à 17:49
Merged for Linux 6.18 was a new feature called Sheaves as an opt-in, per-CPU array-based caching layer. Plus there is a per-NUMA-node cache of Sheaves called a "Barn". In continuing to build out the Linux kernel usage of Sheaves, a set of initial patches were posted this week to replace the CPU slabs with Sheaves within the slub allocator code...

AMD EPYC Turin vs. Intel Xeon 6 Granite Rapids vs. Graviton4 Benchmarks With AWS M8 Instances

24 octobre 2025 à 15:00
With Amazon recently launching their M8a AWS instances powered by 5th Gen AMD EPYC "Turin", for their M8 class instance types there now are all the latest-generation CPU options with AMD EPYC Turin (M8a), Intel Xeon 6 Granite Rapids (M8i), and their in-house Graviton4 processors (M8g). After recently looking at the M7a vs. M8a performance with Amazon EC2, many Phoronix readers expressed interest in seeing an M8a vs. M8i vs. M8g performance showdown so here are those benchmarks.

New Code Allows VCE 1.0 Video Acceleration To Work On AMDGPU Driver For GCN 1.0 GPUs

24 octobre 2025 à 10:22
Valve contractor Timur Kristóf for their Linux graphics driver team has been working on improving Linux driver support for old AMD Radeon GCN 1.0 and GCN 1.1 generation GPUs. This has been about improving the AMDGPU driver to fill remaining gaps in GCN 1.0/1.1 support with those graphics cards by default relying on the older "Radeon" DRM kernel graphics driver compared to the AMDGPU driver used by default with GCN 1.2 and later. Another feature gap for AMDGPU is now being addressed with Video Coding Engine 1.0 support...

Linux's Kconfig Is No Longer Orphaned

24 octobre 2025 à 09:55
Back in August, open-source developer Masahiro Yamada stepped down from maintaining the Kconfig and Kbuild areas of the Linux kernel. While Kbuild maintainership was quickly passed on, no one immediately stepped up to maintain Kconfig as the infrastructure code for configuring the Linux kernel builds. That led to Kconfig officially being orphaned code within the kernel but now that situation has been addressed...

Intel Begins Adding Nova Lake Xe3P To Linux OpenGL/Vulkan Drivers - Some Will Lack Ray-Tracing

24 octobre 2025 à 00:36
Intel recently began sending out Xe3P kernel graphics driver patches for Nova Lake that will begin landing in the upcoming Linux 6.19 kernel cycle. Now on the user-space side, merged today for Mesa 26.0 were the first enablement patches for Xe3P Nova Lake for their open-source OpenGL and Vulkan drivers on Linux...
Reçu avant avant-hier

AMD Radeon AI PRO R9700 Hitting Retailers Next Week For $1299 USD

23 octobre 2025 à 19:14
Back in May AMD announced the Radeon AI PRO R9700 with 128 AI accelerators, 32GB of GDDR6 video memory, and other advantages for this AI-focused RDNA4 based graphics card over the RDNA3-based Radeon PRO W7900. The Radeon AI PRO R9700 was supposed to be available in July while today AMD announced it will be going on sale next week...

Linux's Proposed Cache Aware Scheduling Benchmarks Show Big Potential On AMD EPYC Turin

23 octobre 2025 à 14:50
The past number of months has seen a lot of work by Intel Linux kernel engineers on cache-aware scheduling / load balancing for helping modern CPUs that have multiple caches. With cache aware scheduling, tasks that will likely share resources could be aggregated into the same cache domain to enjoy better cache locality. With the cache aware scheduling patches recently updated and now working past the "request for comments" stage, I was eager to try out these new patches. Especially with a 44% time reduction reported for one of the benchmarks, I was eager to run some tests and the first of those results are being shared today.
❌