↩ Accueil

Vue lecture

Benchmarking The AMD EPYC 9V64H: Azure HBv5's Custom AMD CPU With HBM3

Nearly one year ago Microsoft announced the HBv5 virtual machines powered by a custom-designed AMD 4th Gen EPYC processor with high bandwidth memory (HBM3). Finally today the Azure HBv5 series is reaching general availability for those with memory-intensive HPC applications and other workloads. Microsoft kindly provided Phoronix with HBv5 access in advance to begin testing these new VMs with the AMD EPYC 9V64H CPUs featuring HBM memory, so here are some of the first independent benchmarks of these exciting processors powering Azure's new HPC VM instances.
  •  

Linux 6.19 Will Finally Support Intel's Adaptive Sharpness Filter "CASF" With Lunar Lake

Going all the way back to early 2024, Intel Linux engineers have been working on supporting an Adaptive Sharpening Filter new to Lunar Lake. While Lunar Lake later launched in September 2024, the Linux patches for this feature remained under review and discussion. Besides the Intel driver implementation itself for Lunar Lake and newer, it also ushers in a new DRM sharpness property to help standardize such functionality for user-space that could be used by other kernel graphics drivers. Finally with the upcoming Linux 6.19 kernel, this Intel Content Adaptive Sharpness Filter "CASF" feature is being introduced to the mainline kernel...
  •  

Open Container Initiative "OCI" Runtime Spec v1.3 Released With FreeBSD Support

The Open Container Initiative unveiled today the OCI Runtime Specification v1.3 update for this standard around operating system process and application containers. This runtime specification continues to evolve for outlining the configuration, execution environment, and lifecycle of a container. Notable with the v1.3 revision is introducing official FreeBSD support...
  •  

Intel's LLM-Scaler Updated With OpenAI's GPT-OSS Model Support

Back in August was the announcement of LLM-Scaler as part of Project Battlematrix. LLM-Scaler is a new Intel software project to provide optimized AI inference capabilities on Intel graphics hardware. A new beta release of LLM-Scaler "llm-scaler-vllm" is now available with expanded LLM model coverage...
  •  

libinput 1.30-rc1 Released With Lua Plugin Support

The libinput input handling library for the Linux desktop on both Wayland and X.Org based systems is rolling out Lua plug-in support. Out today is libinput 1.30-rc1 with the initial infrastructure for supporting plug-ins written in the Lua scripting language...
  •  

AMD Radeon AI PRO R9700 Offers Competitive Workstation Graphics Performance/Value

Last week the AMD Radeon PRO R9700 officially began shipping for that new AI-minded workstation/professional graphics card built on RDNA4 and packing 32GB of RAM to accommodate large language models (LLMs) especially with multi-GPU configurations. While the focus of the product has been all about AI workloads, you may be wondering about the graphics capabilities of the Radeon AI PRO R9700 given the lack of any other "Radeon PRO 9000" series product at this point. In today's testing is a look at the workstation graphics capabilities for the AMD Radeon AI PRO R9700.
  •  

RadeonSI ACO vs. LLVM Backends For AMD Strix Halo

With the RadeonSI Gallium3D driver now defaulting to the ACO compiler back-end for all Radeon GPUs rather than the conventional AMDGPU LLVM shader compiler back-end, I ran some quick comparison benchmarks on AMD Ryzen AI Max+ "Strix Halo" with Radeon 8060S Graphics for comparison...
  •  

Linux 6.19 To Support Microsoft's ACPI Fan Extensions

A few weeks back I reported on Linux kernel patches surfacing for implementing Microsoft's ACPI Fan Extensions. This should help some HP devices and hardware from other OEMs for obtaining fan information reporting under Linux. The good news now is that the patches should be part of the upcoming Linux 6.19 kernel cycle...
  •