NVIDIA GeForce RTX 3000 Series Launches With Impressive Specs, Competitive Pricing

As widely expected amid a constant flow of rumors and leaks in recent weeks, NVIDIA just revealed their GeForce RTX 3000 "Ampere" series.

NVIDIA has announced the GeForce RTX 3070 / RTX 3080 / RTX 3090 as the successors to the RTX 2080 Ti, RTX 2080 SUPER, and RTX 2070 SUPER models.

The RTX 3090 tops out at 5248 CUDA cores with 24GB of

New/Updated Benchmarks For August From TensorFlow Lite To ASTCENC

In addition to the new OpenBenchmarking.org now out in public "alpha" , a number of new and updated test profiles were published in August for users of our open-source, cross-platform automated benchmarking software.

When it comes to new tests/benchmarks added over the course of August, the additions include:

tensorflow-lite - Complementing the existing TensorFlow benchmarks, TensorFlow Lite is now available as a benchmark for evaluating the performance of this implementation focused for inference on the edge.

astcenc - The Arm-developed

AMD ACO Back-End Sees Thorough Documentation Added, Explanation Of Architecture

With the soon to be released Mesa 20.2, the RADV Vulkan driver is using the ACO back-end by default that's been developed with funding by Valve as an alternative to AMD's official "AMDGPU" LLVM back-end. For those wondering how this shader compiler back-end compares and more intricate details of its design, some extensive documentation has finally been added to the Mesa tree.

Merged today to Mesa Git is some detailed documentation concerning the design of the ACO compiler back-end

Qt 6.0 Now Under Feature Freeze

The Qt Company has announced the feature freeze for the big Qt 6.0 toolkit milestone.

No more feature work is happening for Qt 6.0 in order to make this month's planned Qt 6.0 Alpha release followed by beta releases in October, the Qt 6.0 release candidate in November, and ideally releasing Qt 6.0.0 in December.

Qt 6.0 has a lot of work on its graphics stack, continued Wayland improvements, big improvements for QML, improved C++

Intel Sapphire Rapids Target Added To LLVM/Clang 12.0

Intel developers engaging with upstream LLVM have been adding AMX support and other new features for next year's Xeon " Sapphire Rapids " while as of a few days ago in LLVM 12 Git is the actual enabling of -march=sapphirerapids support.

Back in July for GCC 11 the GNU compiler added -march=sapphirerapids and now similarly for LLVM 12 due out in early 2021 is also the same -march=sapphirerapids target.

Using -march=sapphirerapids for Clang on top of Ice Lake

Creative SoundBlaster AE-7 Sound Card To Be Supported By Linux 5.10

Creative Labs last year released the high-end SoundBlaster AE-7 sound card. Sadly the company is back in their state where they do not provide official Linux support, but coming up for Linux 5.10 is the support for this sound card thanks to Connor McAdams who has worked on supporting prior SoundBlaster hardware under Linux.

The SoundBlaster AE-7 was released last year as a "hi-res PCI-e DAC and Amp sound card" with "audiophile-grade components" with Sound Core3D
Continue reading...

Open Source LLM

Intel mOS, Cachy, Mozilla Layoffs Were The Open-Source Buzz Of August

August was an interesting month in terms of Linux/open-source activity though still another tough month during the coronavirus pandemic.

During the month of August on Phoronix were 273 original news articles and just 10 featured Linux hardware reviews/featured articles. The news count is still close to the average of 10 new/original news articles each and every day of the year while the review/featured count is off the usual track of around one per day... That is due principally due to declining

Intel Still Working To Tune Linux Power Efficiency For CPU Power-Sharing Scenarios

Going back to earlier this year has been work on an "adaptive" mode for P-State to improve GPU bound efficiency when the CPU is forced to share a power/thermal budget with other components like onboard graphics. That work is still advancing and an update was provided on it last week.

This work has been under investigation and development for a number of months now for cases where ramping up the CPU frequency in an effort to improve performance may not be as beneficial as remaining in a lower power state so the

LLVM Merges Machine Function Splitter For ~32% Reduction In TLB Misses

At the beginning of August we reported on Google engineers proposing the Machine Function Splitter to LLVM as a means of making binaries up to a few percent faster thanks to this code generation optimization pass for splitting code functions into hot and cold portions. That work has now been merged into LLVM 12.0 with very promising results.

The LLVM Machine Function Splitter was merged prior to the weekend into the Git code-base for what will be LLVM 12.0 early next year. Making use of this optimization pass ensures

Many Linux Developers Are Ecstatic Over Fedora On Lenovo Systems

As noted this weekend, Lenovo has begun offering Fedora pre-loaded on their systems beginning with the ThinkPad X1 Carbon Gen 8 laptop. Red Hat's Christian Schaller who serves as the senior manager for desktop chimed in with some additional thoughts and details on this achievement.

Schaller has penned a lengthy blog post covering the milestone of Fedora now being available from the Lenovo web store as part of the X1 Carbon while more models are to come. Among the highlights from his post:

- As noted this weekend,