Phoronix reports on Valve's "Steam Survey" results for December 2024, saying the new numbers "reflect a nice upward trend for the Linux gaming statistics and a high point in recent times." In November the Steam Survey reflected a 2.03% marketshare for Linux... Roughly inline with what we have been seeing for Linux right at around the 2% threshold. With the just-published December survey numbers, there is a 0.29% increase to 2.29%...! When looking at the Linux numbers, SteamOS Holo accounts for around 36% of all Linux gamers... SteamOS Holo being the operating system of the Steam Deck and beginning to appear on other devices as well... Driven in large part by the Steam Deck relying on a custom AMD SoC/APU and AMD being popular with Linux gamers/enthusiasts for their open-source driver support, AMD CPU use on Linux commands a 73.6% marketshare.
In fact, December "saw AMD reach another record-high share among participants of Valve's survey," according to TechSpot — "up 3.02% last month, taking its total to 38.7% as Intel fell slightly to 63.4%..." Elsewhere, Windows 11 is now comfortably the most popular OS in the survey. It pulled ahead another 2% to an almost 55% share in December as Windows 10 dropped to 42.3%... However, it's a different story when looking at global users: Windows 10's share has increased two months in a row to 62.7% while Windows 11 has declined to 34.1%. Rounding up the rest of the survey, 16GB of RAM remains the most popular amount of system RAM but it's lead is declining as second-place 32GB grows; a trend that is mirrored in the VRAM category...
Phoronix adds that the Windows percent "pulled back by 0.51% to 96.1% while Apple macOS also gained 0.22% going up to a 1.61% marketshare."

"I still can't quite believe that I'm using an Arm-powered Windows laptop every day," writes a senior editor at the Verge: After more than a decade of trying to make Windows on Arm a reality, Microsoft and Qualcomm finally nailed it this year with Copilot Plus PCs. These new laptops have excellent battery life and great performance — and the app compatibility issues that have plagued Windows on Arm are mostly a thing of the past (as long as you're not a gamer). Microsoft wanted 2024 to be "the year of the AI PC," but I think it was very much the year of Windows on Arm...

The key to Windows on Arm's revival this year was Qualcomm's Snapdragon X Elite processors, which were announced in April. They've provided the type of performance and power efficiency only previously available with Apple's MacBooks and challenged Intel and AMD to do better in the x86 space. After much debate over Microsoft's MacBook Air-beating benchmarks, the reviews rolled in and showed that Windows on Arm was indeed capable of matching and beating Apple's MacBook Air. Qualcomm even hired the "I'm a Mac" guy to promote Windows on Arm PCs, showing how confident it was in challenging Apple's laptop dominance.

Microsoft and Qualcomm also worked closely with developers to make key apps compatible, and it's now very rare to run into an app compatibility issue that can't be solved by a native Arm64 version or Microsoft's improved emulator. Even Google, which previously shunned Windows Phone, has created Arm64 versions of Chrome and Google Drive to support Microsoft's efforts. With developers continually providing native versions of their apps, it makes it a lot easier to switch to a Windows on Arm laptop. The only big exception is gaming, where x86 still reigns supreme for compatibility and performance...

It's hard not to see 2025 as the year that Windows on Arm continues to eat into the laptop space. A Dell leak revealed Qualcomm is preparing new chips for 2025, and the chip maker has also been rolling out cheaper Arm-based chips to bring laptop prices down.
The article acknowledges that both AMD and Intel "have the key advantage of game compatibility that Windows on Arm is definitely not ready for..." But "Given the Windows on Arm gaming situation, a new generation of Nvidia's GPUs could help generate fresh excitement around x86 laptops throughout 2025." And "Nvidia might also be planning to help the Windows on Arm effort. The chip maker has long been rumored to be planning to launch Arm PC chips as soon as 2025... Whatever happens to laptops in 2025, you can guarantee that there's going to be fierce competition between Intel, AMD, and Qualcomm."

But the author still complains about the dedicated Copilot key on his new WIndows-on-Arm laptop. "While the Copilot experience on Windows has gone through several confusing revisions, it's still a key I accidentally press and then get frustrated when a Copilot window appears."

"Over the course of 2024, Python has proven again and again why it's one of the most popular, useful, and promising programming languages out there," writes InfoWorld: The latest version of the language pushes the envelope further for speed and power, sheds many of Python's most decrepit elements, and broadens its appeal with developers worldwide. Here's a look back at the year in Python.

In the biggest news of the year, the core Python development team took a major step toward overcoming one of Python's longstanding drawbacks: the Global Interpreter Lock or "GIL," a mechanism for managing interpreter state. The GIL prevents data corruption across threads in Python programs, but it comes at the cost of making threads nearly useless for CPU-bound work. Over the years, various attempts to remove the GIL ended in tears, as they made single-threaded Python programs drastically slower. But the most recent no-GIL project goes a long way toward fixing that issue — enough that it's been made available for regular users to try out.

The no-GIL or "free-threaded" builds are still considered experimental, so they shouldn't be deployed in production yet. The Python team wants to alleviate as much of the single-threaded performance impact as possible, along with any other concerns, before giving the no-GIL builds the full green light. It's also entirely possible these builds may never make it to full-blown production-ready status, but the early signs are encouraging.

Another forward-looking feature introduced in Python 3.13 is the experimental just-in-time compiler or JIT. It expands on previous efforts to speed up the interpreter by generating machine code for certain operations at runtime. Right now, the speedup doesn't amount to much (maybe 5% for most programs), but future versions of Python will expand the JIT's functionality where it yields real-world payoffs.
Python is now more widely used than JavaScript on GitHub (thanks partly to its role in AI and data science code).

Berlin-based T2 Linux developer René Rebe is also long-time Slashdot reader ReneR — and popped by with a special announcement for the holidays: The T2 Linux team has unveiled T2 Linux SDE 24.12, codenamed "Sky's the Limit!", delivering a massive update for this highly portable source-based Linux distribution... With 3,280 package updates, 206 new features, and the ability to boot on systems with as little as 512MB RAM, this release further strengthens T2 Linux's position as the ultimate tool for developers working across diverse hardware and embedded systems.
Some highlights from Rene's announcement:

• "The release includes 37 pre-compiled ISOs with Glibc, Musl, and uClibc, supporting 25 CPU architectures like ARM(64), RISCV(64), Loongarch64, SPARC(64), and vintage retro computing platforms such as M68k, Alpha, and even initial Nintendo Wii U support added."

• " The Cosmic Desktop, a modern Rust-based environment, debuts alongside expanded application support for non-mainstream RISC architectures, now featuring LibreOffice, OpenJDK, and QEMU."

And T2sde.org gives this glimpse of the future:

"While initially created for the Linux kernel, T2 already has proof-of-concept support for building 'home-brew' pkg for Other OS, including: BSDs, macOS and Haiku. Work on alternative micro kernels, such as L4, Fuchsia, RedoxOS or integrating building 'AOSP' Android is being worked on as well."

"Single-board computer maker Raspberry Pi is updating its cute little computer-meet-keyboard device with better specifications..." reports TechCrunch.

They call the new $90 Raspberry Pi 500 "not as intimidating" because "when you look at the Raspberry Pi 500, you can't see any chipsets or printed circuit board... The idea with the Raspberry Pi 500 is that you can plug in a mouse and display, and you're ready to hit the ground running." When it comes to specifications, the Raspberry Pi 500 features a 64-bit quad-core Arm processor (the same one as the Raspberry Pi 5 uses); 8GB of RAM; 2 micro-HDMI ports, with support for up to two 4K displays; 3 traditional USB ports (but no USB-C besides the power port unfortunately); a Gigabit Ethernet port; and a 40-pin expansion header. It comes with native Wi-Fi and Bluetooth support.

More importantly, this device brings us back Raspberry Pi's roots. Raspberry Pi computers were originally intended for educational use cases... The Raspberry Pi 500 draws inspiration from the not-for-profit Raspberry Pi Foundation's roots. It's the perfect first computer for school. In many ways, it's much better than a Chromebook or an iPad because it is both cheap and highly customizable — encouraging creative thinking. The Raspberry Pi 500 comes with a 32GB SD card preloaded with Raspberry Pi OS, a Debian-based Linux distribution...

In other news, Raspberry Pi has announced another brand-new product: the Raspberry Pi Monitor. It's a 15.6-inch 1080p monitor with a price-tag of $100.
Tom's Hardware calls the Pi 500 "a superb update" to the original computer-in-a-keyboard Raspberry Pi 400: Having the ports at the back makes total sense. It tidies up the cables, and means that we only need one thick edge, the rest can be as thin as possible... [P]assive cooling performance is remarkable, even when overclocked to 3 GHz...! I did have to adjust the voltage to keep everything stable, but once I found the magic numbers, the system was stable and performed remarkably well... [I]t ran buttery smooth and surprisingly, cool under stress. I'd consider this a successful overclock and one that I would happily keep as a permanent addition...

Just like the Raspberry Pi 400, the Pi 500 is there to be a 21st century equivalent to the home computers of the 1980s. You plug in to a wedge-shaped keyboard, hook up to your display, and start work. But the Raspberry Pi 500 has much more processing power than the Pi 400, and that means it can be a viable desktop computer for those that don't need an RTX 4090 or a power-hungry CPU.

I like the Raspberry Pi 500. It's a powerful machine, in a pleasant package. I'm old enough to remember the 1980s home computer craze, and this, just like the Pi 400, reminds me of that time. But now we have much more power... The Raspberry Pi 500 is the kit that you buy as a gift for someone, or as a child's first computer. I can see this being used in schools and to an extent in offices around the world.

Bruce Perens, original co-founder of the Open Source Initiative, has responded to questions from Slashdot readers about a new alternative he's developing that hopefully helps "Post Open" developers get paid.

But first, "One of the things that's clear from the Slashdot patter is that people are not aware of what I've been doing, in general," Perens says. "So, let's start by filling that in..."

Read on for the rest of his wide-ranging answers....

An anonymous reader shared this report from the blog Windows Central: Microsoft has ended production on the Surface Studio 2+, its ultra-premium all-in-one desktop PC designed for creatives and commercial customers. Starting at a whopping $4,500, the Studio 2+ was the ultimate Windows all-in-one with the best touchscreen display on a unique hinge that allowed the screen to lay down like a draft board... So, if you're interested in buying a Surface Studio 2+, you better hurry, as whatever stock is remaining is all that's left. Unfortunately, it's likely that the end of production on the Surface Studio 2+ also marks an end to the Surface Studio line as a whole. My own sources tell me there's no Studio 2+ successor lined up currently.
Ars Technica points out that over the eight-year run of the Surface Studio, Microsoft only updated it twice. Like the Surface Laptop Studio, the desktop's claim to fame was a unique hinge design for its screen, which could reposition it to make it easier to draw on with the Surface Pen. But the desktop's high cost and its perennially outdated internal components made it a less appealing machine than it could have been...

The longest-lived Studio desktop was the Surface Studio 2, which was released in 2018 and wasn't replaced until a revised Surface Studio 2+ was announced in late 2022. It used an even higher-quality display panel, but it still used previous-generation internal components. This might not have been so egregious if Microsoft had updated it more consistently, but this model went untouched for so long that Microsoft had to lower Windows 11's system requirements specifically to cover the Studio 2 so that the company wouldn't be ending support for a PC that it was still actively selling.

The Studio 2+ was the desktop's last hurrah, and despite jumping two GPU generations and four CPU generations, it still didn't use the latest components available at the time. Again, more consistent updates like the ones Microsoft provides for the Surface Pro and Surface Laptop could have made this less of a problem, but the Studio 2+ once again sat untouched for two years after being updated.

Qualcomm's interest in acquiring Intel is cooling due to the complexity of the deal, Intel's debt, and regulatory hurdles. However, according to Bloomberg, Qualcomm may still explore acquiring certain divisions of Intel to expand into markets like PCs and networking. Tom's Hardware reports: [T]he proposed acquisition faced significant obstacles, including Intel's $50 billion debt, dropping CPU market share, and its struggling semiconductor manufacturing unit, an area where Qualcomm lacks expertise. A deal of this magnitude would also likely trigger extensive regulatory scrutiny, particularly in China, a key market for both companies.

Intel is undergoing significant restructuring under CEO Pat Gelsinger to reclaim its competitiveness in the semiconductor market in terms of products and process technologies. Still, for now, both Intel and Qualcomm are quite successful standalone companies. While the combination would make a formidable firm (probably facing unprecedented antitrust scrutiny), it does not make much sense for Qualcomm to make such a massive takeover. These factors have collectively made a complete takeover less appealing to Qualcomm. Meanwhile, selling off a part of the company to Qualcomm may not make sense for Intel.

Qualcomm aims to generate $22 billion in annual revenue by 2029 by expanding into markets like personal computers, networking, and automotive chips. Although Cristiano Amon, Qualcomm's chief executive, has stated that his company did not need a major takeover to achieve this goal, the company initiated preliminary discussions with Intel regarding a potential acquisition in September. Yet, it does not look like the deal is going to happen.

Lawrence Livermore National Laboratory's "El Capitan" supercomputer is now ranked as the world's most powerful, exceeding a High-Performance Linpack (HPL) score of 1.742 exaflops on the latest Top500 list. Engadget reports: El Capitan is only the third "exascale" computer, meaning it can perform more than a quintillion calculations in a second. The other two, called Frontier and Aurora, claim the second and third place slots on the TOP500 now. Unsurprisingly, all of these massive machines live within government research facilities: El Capitan is housed at Lawrence Livermore National Laboratory; Frontier is at Oak Ridge National Laboratory; Argonne National Laboratory claims Aurora. [Cray Computing] had a hand in all three systems.

El Capitan has more than 11 million combined CPU and GPU cores based on AMD 4th-gen EPYC processors. These 24-core processors are rated at 1.8GHz each and have AMD Instinct M1300A APUs. It's also relatively efficient, as such systems go, squeezing out an estimated 58.89 Gigaflops per watt. If you're wondering what El Capitan is built for, the answer is addressing nuclear stockpile safety, but it can also be used for nuclear counterterrorism.

An anonymous reader quotes a report from The Register: Framework CEO Nirav Patel had one of the bravest tech demos that we've seen at a conference yet -- modifying a Framework Laptop from x86 to RISC-V live on stage. In the five-minute duration of one of the Ubuntu Summit's Lightning Talks, he opened up a Framework machine, removed its motherboard, installed a RISC-V-powered replacement, reconnected it, and closed the machine up again. All while presenting the talk live, and pretty much without hesitation, deviation, or repetition. It was an impressive performance, and you can watch it yourself at the 8:56:30 mark in the video recording.

Now DeepComputing is taking orders for the DC-ROMA board, at least to those in its early access program. The new main board is powered by a StarFive JH7110 System-on-Chip. (Note: there are two tabs on the page, for both the JH7110 and JH7100, and we can't link directly to the latter.) CNX Software has more details about the SoC. Although the SoC has six CPU cores, two are dedicated processors, making it a quad-core 64-bit device. The four general-purpose cores are 64-bit and run at up to 1.5 GHz. It supports 8 GB of RAM and eMMC storage. [...]

In our opinion, RISC-V is not yet competitive with Arm in performance. However, this is a real, usable, general-purpose computer, based on an open instruction set. That's no mean feat, and it's got more than enough performance for less demanding work. It's also the first third-party main board for the Framework hardware, which is another welcome achievement. The company has now delivered several new generations of hardware, including a 16-inch model, and continues to upgrade its machines' specs.

Slashdot unixbhaskar writes: Linus has released a fresh Linux kernel for public consumption. Please give it a try and report any glitches to the maintainers for improvement. Also, please do not forget to express your appreciation to those tireless folks who did all the hard work for you.
The blog OMG Ubuntu calls it "one of the most biggest kernel releases for a while," joking that it's a "really real-time kernel." The headline feature in Linux 6.12 is mainline support for PREEMPT_RT. This patch set dramatically improves the performance of real-time applications by making kernel processes pre-emptible — effectively enabled proper real-time computing... Meanwhile, Linus Torvalds himself contributes a new method for user-space address masking designed to claw back some of the performance lost due to Spectre-v1 mitigations.

You might have heard that kernel devs have been working to add QR error codes to Linux's kernel panic BSOD screen (as a waterfall of error text is often cut off and not easily copied for ad-hoc debugging). Well, Linux 6.12 adds support for those during Direct Rendering Manager panics...

A slew of new RISC-V CPU ISA extensions are supported in Linux 6.12; hybrid CPU scaling in the Intel P-State driver lands ahead of upcoming Intel Core Ultra 2000 chips; and AMD P-State driver improves AMD Boost and AMD Preferred Core features.
More coverage from the blog 9to5Linux highlights a new scheduler called sched_ext, Clang support (including LTO) for nolibc, support for NVIDIA's virtual command queue implementation for SMMUv3, and "an updated cpuidle tool that now displays the residency value of cpuidle states for a clearer and more detailed view of idle state information when using cpuidle-info." Linux kernel 6.12 also introduces SWIG bindings for libcpupower to make it easier for developers to write scripts that use and extend the functionality of libcpupower, support for translating normalized error addresses reported by an AMD memory controller into system physical addresses using a UEFI mechanism called platform runtime mechanism (PRM), as well as simplified loading of microcode patches on AMD Zen and newer CPUs by using the family, model, and stepping encoded in the patch revision number...

Moreover, Linux 6.12 adds support for running as a protected guest on Android as well as perf and support for a bunch of new interconnect PMUs. It also adds the final conversions to the new Intel VFM CPU model matching macros, rewrites the PCM buffer allocation handling and locking optimizations, and improves the USB audio driver...

An anonymous reader shares a report: AMD has gained a substantial 5.7 percentage points of share of the desktop x86 CPU market in the third quarter compared to Q2, the largest quarterly share gain since we began tracking the market share reports in 2016. It also represents an incredible ten percentage point improvement over the prior year. AMD also raked in a strong increase in revenue share, jumping 8.5 percentage points over the prior quarter, indicating that it is selling a strong mix of higher-end CPU models.

During the quarter, AMD launched its new Ryzen 9000-series family of processors amid a scandal related to stability issues with Intel's Raptor Lake chips, which generated a flood of negative press for the company over the course of several months, and inventory adjustments for one of Intel's customers. AMD now commands 28.7% of the desktop processor market. AMD also continued to gain share in the laptop and server markets, though its gains on the desktop side of the business were the most impressive, according to Mercury Research.

"AMD's Ryzen 7 9800X3D debuts with impressive performance gains, powered by advanced 3D V-Cache technology and improved thermal efficiency," writes Slashdot reader jjslash. "While the CPU shines as a top choice right out of the gate, AMD's history of quick price cuts suggests waiting could yield even better value for savvy buyers." TechSpot reports: Today we're finally able to show you how AMD's new Ryzen 7 9800X3D performs, and spoiler alert -- it's a real weapon that solves the issues we encountered with the non-3D Zen 5 chips before this. Without question, this is the best CPU released since the 7800X3D, making this launch particularly exciting. [...] For now, the 9800X3D is mighty impressive, the undisputed king of gaming, and it marks a historic milestone. We don't think AMD has ever been this dominant over Intel, certainly not in the last 15 years.

After closing a $69 billion deal to buy virtualization technology company VMware a year ago, Broadcom wasted no time ushering in big changes to the ways customers and partners buy and sell VMware offerings -- and many of those clients aren't happy. ArsTechnica: To get a deeper look at the impact that rising costs and overhauls like the end of VMware perpetual license sales have had on VMware users, Ars spoke with several companies in the process of quitting the software due to Broadcom's changes. Here's what's pushing them over the edge.

For some, VMware prices more than tripled under Broadcom Broadcom closed its VMware acquisition in November 2023, and by December 2023, the company announced that it would stop selling perpetual VMware licenses. VMware products were previously sold under 8,000 SKUs, but they have now been combined into a few bundle packages. Additionally, higher CPU core requirements per CPU subscription have made VMware more expensive for some reseller partners.

"As on-premises virtualization projects move from [enterprise license agreements] and perpetual licenses to new bundling, socket-to-core ratios, and consumption models, the costs and pricing can increase two or three times," Gartner's 2024 Hype Cycle for Data Center Infrastructure Technologies report that released in June reads. Numerous VMware customers I spoke with said their VMware costs rose 300 percent after Broadcom's takeover. Some companies have cited even higher price hikes -- including AT&T, which claimed that Broadcom proposed a 1,050 percent price hike. AT&T is suing Broadcom over perpetual license support and says it has looked into VMware alternatives.

Apple launched a dramatically smaller Mac Mini desktop computer on Tuesday, powered by its new M4 processor and featuring ray tracing capabilities for the first time. The redesigned Mini measures just 5 inches square, roughly half the size of its predecessor, while delivering up to 1.8 times faster CPU performance compared to the M1 model.

The base version starts at $599, while the more powerful M4 Pro variant begins at $1,399. The M4 Pro model sports 14 CPU cores and 20 GPU cores, with support for up to 64GB of RAM and 8TB storage. It introduces Thunderbolt 5 connectivity, offering data transfer speeds up to 120 Gb/s. Apple has revamped the port configuration, adding front-facing USB-C ports and a headphone jack. The rear features Ethernet, HDMI, and three Thunderbolt ports, though USB-A ports have been eliminated. The new Mini supports up to three 6K displays with the M4 Pro chip.

Apple has updated the iMac lineup with an M4 chip. The new iMac, announced this morning, includes an M4 chip with an 8-core CPU and up to a 10-core GPU. The entry-level model costs $1,299 with two Thunderbolt USB-C 4 ports, while the higher-end models start at $1,499 and have four ports. The Verge: It's also bundled with accessories that now use USB-C charging ports instead of Lightning. Like the prior model, the new iMac has a 24-inch, 4.5K display. However, Apple is offering a new "nano-texture glass option" for $200 extra, which is supposed to help reduce reflections and glare.

Additionally, the iMac's base RAM has been doubled to 16GB over the prior model, with the ability to configure the higher-end option with up to 32GB. Apple's new iMac also comes with a 12MP webcam, along with new Apple Intelligence features that are starting to roll out today, such as AI-powered writing and editing features and a redesigned Siri.

An anonymous reader shared this report from the Verge: Ever wondered why some of your Instagram videos tend to look blurry, while others are crisp and sharp? It's because, on Instagram, the quality of your video apparently depends on how many views it's getting.

Here's part of Mosseri's explanation, from the video, which was reposted by a Threads user today. "In general, we want to show the highest-quality video we can ... But if something isn't watched for a long time — because the vast majority of views are in the beginning — we will move to a lower quality video. And then if it's watched again a lot then we'll re-render the higher quality video...."

The shift in quality "isn't huge," Mosseri said in response to another Threads user, who'd asked if that approach disadvantaged smaller creators. That's "the right concern," he told them, but said people interact with videos based on its content, not its quality. That's consistent with how Meta has described its approach before... Meta wrote in a blog [post] that in order to conserve computing resources for the relatively few, most watched videos, it gives fresh uploads the fastest, most basic encoding. After a video "gets sufficiently high watch time," it receives a more robust encoding pass.
"It works at an aggregate level, not an individual viewer level," Mosseri wrote later on Threads. "We bias to higher quality (more CPU intensive encoding and more expensive storage for bigger files) for creators who drive more views. It's not a binary theshhold, but rather a sliding scale."

It was originally created back in 2005 by Sun Microsystems for its proprietary Solaris Unix systems, "for troubleshooting kernel and application problems on production systems in real time," explains Wikipedia. "DTrace can be used to get a global overview of a running system, such as the amount of memory, CPU time, filesystem and network resources used by the active processes," explains its Wikipedia entry.

But this week, Gentoo announced: The real, mythical DTrace comes to Gentoo! Need to dynamically trace your kernel or userspace programs, with rainbows, ponies, and unicorns — and all entirely safely and in production?! Gentoo is now ready for that!

Just emerge dev-debug/dtrace and you're all set. All required kernel options are already enabled in the newest stable Gentoo distribution kernel...

Documentation? Sure, there's lots of it. You can start with our DTrace wiki page, the DTrace for Linux page on GitHub, or the original documentation for Illumos. Enjoy!
Thanks to Heraklit (Slashdot reader #29,346) for sharing the news.

MojoKid writes: Intel has lifted the embargo on independent reviews of its new Core Ultra 200S series Arrow Lake-S processors, which mark a shift in its desktop CPU strategy with symmetrical core/thread counts (no Hyperthreading) and a dedicated 13 TOPS NPU. This series features a disaggregated tiled design for the first time in Intel's desktop chips, focusing on efficiency and power reduction. The Core Ultra 5 245, priced around $300, and the Ultra 9 285K at $589 deliver strong performance, particularly in creator workloads, competing well with AMD's Ryzen CPUs, while the Ultra 9 285K's price undercuts AMD's Ryzen 9 9950X significantly. While gaming performance shows slight regression in spots, the new chips are much more power-efficient than their predecessors. Overall, the platform offers leading-edge features, competitive pricing, and solid performance for creators, gamers and workstation pros.

An anonymous reader quotes a report from Ars Technica: Qualcomm has a new chip for flagship phones, and the best part is that it uses an improved version of the Oryon CPU architecture that the Snapdragon X Elite chips brought to Windows PCs earlier this year. The Snapdragon 8 Elite is the follow-up to last year's Snapdragon 8 Gen 3 -- yet another change to the naming convention that Qualcomm uses for its high-end phone chips, though, as usual, the number 8 is still involved. The 8 Elite uses a "brand-new, 2nd-generation Qualcomm Oryon CPU" with clock speeds up to 4.32 GHz, which Qualcomm says will improve performance by about 45 percent compared to the Snapdragon 8 Gen 3.

Rather than a mix of large, medium, and small CPU cores as it has used in the past, the 8 Elite has two "Prime" cores for hitting that high peak clock speed, while the other six are all "Performance" cores that peak at a lower 3.53 GHz. But it doesn't look like Qualcomm is using a mix of different CPU architectures anymore, choosing to distinguish the higher-performing core from the lower-performing ones by clock speed alone. Qualcomm promises a similar 40 percent performance boost from the new Adreno 830 GPU. The chip also includes a marginally improved Snapdragon X80 5G modem, up from an X75 modem in the Snapdragon 8 Gen 3 -- its main improvement appears to be support for additional antennas, for a total of six, but the download speed still tops out at a theoretical 10Gbps. Wi-Fi 7 support appears to be the same as in the 8 Gen 3, but the 8 Elite does support the Bluetooth 6.0 standard, up from Bluetooth 5.4 in the 8 Gen 3.

Qualcomm says the new chip's CPU features "44% improved power efficiency" and "40% greater power efficiency" for the GPU, which ought to keep power usage in line despite the performance improvements -- these gains are probably attributable to the new 3 nm TSMC manufacturing process, compared to the 4 nm process used for the Snapdragon 8 Gen 3. And no 2024 chip announcement would be complete without some kind of AI mention: Qualcomm's image signal processor is now an "AI ISP," which Qualcomm says "recognizes and enhances virtually anything in the frame, including faces, hair, clothing, objects, backgrounds, and beyond." These capabilities can allow it to remove objects from the background of photos, among other things, using the on-device processing power of the chip's Hexagon neural processing unit (NPU). The NPU is 45 percent faster than the one in the Snapdragon 8 Gen 3. Phones using the Snapdragon 8 Elite should begin appearing in "the coming weeks."