NVIDIA today announced its next-generation AI supercomputer—the NVIDIA DGX SuperPOD powered by NVIDIA GB200 Grace Blackwell Superchips—for processing trillion-parameter models with constant uptime for superscale generative AI training and inference workloads.

Featuring a new, highly efficient, liquid-cooled rack-scale architecture, the new DGX SuperPOD is built with NVIDIA DGX GB200 systems and provides 11.5 exaflops of AI supercomputing at FP4 precision and 240 terabytes of fast memory—scaling to more with additional racks.

Close monitoring of AMD engineering activities—around mid-February time—revealed the existence of a new set of patches for GNU Compiler Collection (GCC). At the time, news reports put spotlights on Team Red's "znver5" enablement—this target indicated that staffers were prepping Zen 5 processor microarchitecture with an expanded AVX instruction set (building on top of Zen 4's current capabilities). Phoronix's Michael Larabel has fretted over AMD's relative silence over the past month—regarding a possible merging of support prior to the stable release of GCC 14.

He was relieved to discover renewed activity earlier today: "AMD Zen 5 processor enablement has been merged to GCC Git in time for the GCC 14.1 stable release that will be out in the coming weeks. It was great seeing AMD getting their Zen 5 processor enablement upstreamed ahead of any Ryzen or EPYC product launches and being able to do so in time for the annual major GNU Compiler Collection feature release." Team Red is inching ever closer to the much anticipated 2024 rollout of next-gen Ryzen 9000 processors, please refer to a VideoCardz-authored timeline diagram (below)—"Granite Ridge" is an incoming AM5 desktop CPU family (reportedly utilizing Zen 5 and RDNA 2 tech), while "Strix Point" is scheduled to become a mobile APU series (Zen 5 + RDNA 3.5).

Zhaoxin finally released its oft-delayed KX-7000 CPU series last December—the Chinese manufacturer claimed that its latest "Century Avenue Core" uArch consumer/desktop-oriented range was designed to "deliver double the performance of previous generations." Freshly discovered Geekbench 6.2.2 results indicate that Zhaoxin has succeeded on that front—Wccftech has pored over these figures, generated by an: "entry-level Zhaoxin KX-7000 CPU which has 8 cores, 8 threads, 4 MB of L2, and 32 MB of L3 cache. This chip was running at a base clock of 3.0 GHz and a boost clock of 3.3 GHz which is below its standard 3.6 GHz boost profile."

The new candidate was compared to Zhaoxin's previous-gen KX-U6780A and KX-6000G models. Intel's Core i3-10100F processor was thrown in as a familiar Western point of reference. The KX-7000 scored: "823 points in single-core, and 3813 points in multi-core tests. For comparisons, the Intel's Comet Lake CPU with 4 cores and 8 threads plus a boost of up to 4.3 GHz offers a much higher score. It's around 75% faster in single and 17% faster in multi-core tests within the same benchmark." The higher clock speeds, doubled core counts and TDPs do deliver "twice the performance" when compared to direct forebears—mission accomplished there. It is clear that Zhaoxin's latest CPU architecture cannot keep up with a generations old Team Blue design. Loongson's 3A6000 processor is a very promising prospect—reports suggest that this chip is somewhat comparable to mainstream AMD Zen 4 and Intel Raptor Lake products.

Sony is preparing to launch its next-generation PlayStation 5 Pro console in the Fall of 2024, right around the holidays. We previously covered a few graphics details about the console. However, today, we get more details about the CPU and the overall system, thanks to the exclusive information from Insider Gaming. Starting off, the sources indicate that PS5 Pro system memory will get a 28% bump in bandwidth, where the standard PS5 console had 448 GB/s, and the upgraded PS5 Pro will get 576 GB/s. Apparently, the memory system is more efficient, likely coming from an upgrade in memory from the GDDR6 SDRAM of the regular PS5. The next upgrade is the CPU, which has special modes for the main processor. The CPU uArch is likely the same, with clocks pushed to 3.85 GHz, resulting in a 10% frequency increase.

However, this is only achieved in the "High CPU Frequency Mode," which steals the SoC's power from the GPU and downclocks it slightly to allocate more power to the CPU in highly CPU-intense settings. The GPU we discussed here is an RDNA 3 IP with up to 45% faster graphics rendering. The ray tracing performance can be up to four times higher than the regular PS5, while the entire GPU delivers 33.5 TeraFLOPS of FP32 single-precision computing. This comes from 30 WGP running BVH8 shaders vs the 18 WGPs running BVH4 shaders on the regular PS5. There are PSSR upscalers present, and the GPU can output 8K resolution, which will come with future software updates. Last but not least, the AI front also has a custom AI accelerator capable of 300 8-bit INT8 TOPS and 67 16-bit FP16 TeraFLOPS. Audio codecs are getting some love, as well, with ACV running up to 35% faster.

The HPC research projects DEEP-SEA, IO-SEA and RED-SEA are wrapping up this month after a three-year project term. The three projects worked together to develop key technologies for European Exascale supercomputers, based on the Modular Supercomputing Architecture (MSA), a blueprint architecture for highly efficient and scalable heterogeneous Exascale HPC systems. To achieve this, the three projects collaborated on system software and programming environments, data management and storage, as well as interconnects adapted to this architecture. The results of their joint work will be presented at a co-design workshop and poster session at the EuroHPC Summit (Antwerp, 18-21 March, www.eurohpcsummit.eu).

A 2019-signed export license has allowed Intel to supply laptop processors to Huawei, under an exclusive deal—this US Government approved arrangement was not viewed favorably by AMD. The rival chipmaker apparently missed out on the securing of a similar trade license back in 2021. According to a new Reuters report, Team Red and a handful of supporters have attempted to revoke Intel's license—worth hundreds of millions of dollars. Two anonymous sources allege that: "Intel has survived an effort to halt chip sales to Huawei...giving one of the world's largest chipmakers more time to sell to the heavily sanctioned Chinese telecoms company." Intel and Huawei's symbiosis is set to end later this year—folks on the inside reckon that the current US administration will not approve a renewal. Reports suggest that Qualcomm is not anticipating a renewal either—Huawei is an approved buyer of Snapdragon chips, but industry whispers indicate an eventual shift to in-house fare.

Intel, Huawei, US Commerce Department and the White House have declined to comment on the aforementioned scenario. Reuters also sent a query to AMD, but the publication did not receive a response. Earlier last year, a government official revealed that "Huawei's licensing policy" was under review, alongside a general push to scrap a number of trade deals. According to insiders, the same government official allegedly told companies—in private—that the US Commerce Department would fix "the licensing discrepancy." Another anonymous source believes that the agency shelved these plans late last year, for reasons unknown—they stressed that there is potential for a revival. Given the upcoming expiry of Intel and Huawei's arrangement—within the year—it makes little sense to implement a drastic change.

Thanks to Phoronix, we have discovered that AMD has recently released initial patches for performance monitoring and events related to their upcoming Zen 5 processors in the Linux kernel. These patches, sent out for review on the kernel mailing list, provide the necessary JSON files for PMU (Performance Monitoring Unit) events and metrics that will be exposed through the Linux perf tooling. As the patches consist of JSON additions and do not risk regressing existing hardware support, there is a possibility that they could be included in the upcoming Linux v6.9 kernel cycle. This would allow developers and enthusiasts to access detailed performance data for Zen 5 CPUs once they become available, helping with optimization and analysis of the next-generation processors.

The release of these patches follows AMD's publication of performance monitor counter documentation for AMD Family 1Ah Model 00h to 0Fh processors last week, confirming that these models represent the upcoming Zen 5 lineup. While Linux kernel 6.8 already includes some elements of Zen 5 CPU support, the upstream Linux enablement for these next-generation AMD processors is an ongoing process. Upon Phoronix examining the Zen 5 core and uncore events, as well as the metrics and mappings, it appears that they are mainly similar to those found in the current Zen 4 processors. This suggests that AMD has focused on refining and optimizing the performance monitoring capabilities of its new architecture rather than introducing significant changes. As the launch of Zen 5 CPUs draws closer, we await to see the performance and capabilities of these next-generation processors. With performance monitoring also getting a push, this could be a sign that Zen 5 launch is nearing.

Intel today announced the release of Continuous Profiler to open source -- serving as an example of the company's open ecosystem approach to catalyze innovation and boost productivity for developers. The optimization agent is actively used by companies including ironSource, ShareChat and Snap Inc. to identify production bottlenecks and optimization opportunities. Developed by Intel Granulate and contributed to the open source community, Continuous Profiler is a solution that combines multiple profilers into one view as a flame graph. This unified view offers developers, performance engineers and DevOps a continuous and autonomous way to identify runtime inefficiencies.

"Continuous Profiler has been at the heart of what we've been doing at Intel Granulate. By helping developers identify bottlenecks in the code, businesses can optimize their applications more easily and effectively," said Asaf Ezra, general manager of Intel Granulate. Determining why central processing units (CPUs) are busy is a routine task for performance analysis in any testing and production environment. Continuous Profiler delivers a flame graph of the hottest code paths. "This visualized view makes it immediately obvious where CPU is consumed so you can find cost savings, eliminate bottlenecks, improve throughput, and reduce latency and performance regressions," said Brendan Gregg, Intel Fellow. "In today's complex environment, however, flame graphs can unearth so many performance wins that it becomes laborious to apply them all. Intel Granulate automates this task, allowing companies to realize these performance wins now and in the future as Intel develops more optimizations."

As of two days ago, the NVX System Integrators store (via Carousell Singapore) has allowed customers to pre-order the oft-leaked Intel Core i9-14900KS CPU—a S$1059 (~$794 USD) spend secures a "BX8071514900KS" Special Edition retail package for in-store pick only. Another pre-release discovery arrives courtesy of the ever vigilant tech watcher; momomo_us—SE Computer, a store located in the bustling streets of Kowloon, Hong Kong, has listed the incoming flagship Raptor Lake Refresh part with a price of HK$5500 (~$709.70 USD). An accompanying image appears to be a placeholder, since warehouse leaks have displayed "Special Edition" text on Intel's signature blue retail boxes.

Privileged members of the overclocking community are already playing around with Intel's selectively-binned 14th Gen Core processor—but mere mortals will have to wait patiently for an official retail rollout. VideoCardz has spent part of their weekend doing detective work—several early store listings point to a possible March 14 commencement. The graphics card news specialist has scoured online entities across Asia, France and Canada for price comparison purposes: "it appears that the KS 'Special Edition' variant is set to cost 19 to 30% more than the K variant. Pricing varies depending on the size of the retailer, where the offer was placed, and the region it is being sold." They thoroughly recommend that potential customers avoid pre-ordering the Intel Core i9-14900KS—asking prices could stabilize post-launch, and e-tailers rarely sell through the first batch of niche "KS" CPUs.

Konstantin Seurer, a Mesa developer, has spent the past couple of months working on CPU-based Vulkan ray tracing—naturally, some folks will express scepticism about this project's practicality. Seurer has already set expectations with a brief message: "don't ask about performance." His GitLab merge request page attracted Michael Larabel's attention—the Phoronix founder and principal author was suitably impressed with Seurer's coding wizardry. He: "managed to implement support for VK_KHR_acceleration_structure, VK_KHR_deferred_host_operations, and VK_KHR_ray_query for Lavapipe. This Lavapipe Vulkan ray tracing support is based in part on porting code from the emulated ray tracing worked on for RADV with older Radeon GPUs." A lone screenshot provided evidence of Quake II running at 1 FPS with Vulkan ray tracing enabled—this "atrocious" performance was achieved thanks to a Mesa Lavapipe driver "implementing the Vulkan API for CPU-based execution."

VideoCardz has highlighted an older example of CPU-based rendering techniques: "this is not the first time we heard about ray tracing on the CPU in Quake. In 2008, Intel demonstrated Enemy Territory: Quake Wars running at 720p resolution at 14 to 29 FPS on 16 core and 20-35 FPS at 24 core CPUs (quad-socket). The basic implementation of ray tracing in 2008 is not comparable to complex ray tracing techniques designed for GPUs, thus the performance on modern system is actually much lower. Beyond that, that game was specifically designed for the Intel architecture and used a specific API to achieve that. Sadly, the original ET demo is no longer available, it would be interesting to see how it performs today." CPU-based Vulkan ray tracing is expected to hit public distribution channels with the rollout of Mesa 24.1. Several members of the Phoronix community reckon that modern AMD Threadripper PRO processors have the potential to post double-digit in-game frame rates.

HP Inc. today announced the industry's largest portfolio of AI PCs leveraging the power of AI to enhance productivity, creativity, and user experiences in hybrid work settings.

In an ever-changing hybrid work landscape, workers are still struggling with disconnection and digital fatigue. HP's 2023 Work Relationship Index reveals that only 27% of knowledge workers have a healthy relationship with work, and 83% believe it's time to redefine our relationships with work. Most employees believe AI will open new opportunities to enjoy work and make their jobs easier, but they need the right AI tools and technology to succeed.

NVIDIA and HP Inc. today announced that NVIDIA CUDA-X data processing libraries will be integrated with HP AI workstation solutions to turbocharge the data preparation and processing work that forms the foundation of generative AI development.

Built on the NVIDIA CUDA compute platform, CUDA-X libraries speed data processing for a broad range of data types, including tables, text, images and video. They include the NVIDIA RAPIDS cuDF library, which accelerates the work of the nearly 10 million data scientists using pandas software by up to 110x using an NVIDIA RTX 6000 Ada Generation GPU instead of a CPU-only system, without requiring any code changes.

Simply NUC, Inc, a leading custom computing company, proudly announced the expansion of the Onyx product line with Onyx Pro, a revolutionary Mini Workstation designed to cater to diverse computing needs. Powered by the Intel Core i9 vPro "Raptor Lake" 13900H CPU, Intel IRIS Xe integrated graphics, and featuring optional graphics cards such as NVIDIA T1000, Radeon Pro WX 3200, and Intel Arc A40, the Onyx Pro redefines computing in a compact form factor.

"Introducing the Onyx Pro marks a pivotal moment for Simply NUC." said Jonny Smith, CEO of Simply NUC "Powered by Intel Core i9 vPro "Raptor Lake", it's our first product with 10G fiber (x2) and standard quad network ports. With unmatched performance, AI-readiness, and advanced networking, Onyx Pro sets a new standard for compact workstations."

Panasonic Connect today announced the latest iterations of its TOUGHBOOK G2 and 33 detachable rugged tablets. The 10.1-inch G2mk2 and 12-inch 33mk3 deliver market-leading ruggedness, battery life, customisation, connectivity and performance that provide the modern mobile worker with a balanced solution, regardless of the task, application or environment.

Unrivalled performance for any application
Panasonic's TOUGHBOOK G2mk2 and 33mk3 devices feature market-leading performance, enhanced connectivity and increased modularity to adapt to different mobile worker requirements.

The AI infrastructure of today is mostly fueled by the expansion that relies on GPU-accelerated servers. Google, one of the world's largest hyperscalers, has noted that CPUs are still a leading compute for AI/ML workloads, recorded on their Google Cloud Services cloud internal analysis. During the TechFieldDay event, a speech by Brandon Royal, product manager at Google Cloud, explained the position of CPUs in today's AI game. The AI lifecycle is divided into two parts: training and inference. During training, massive compute capacity is needed, along with enormous memory capacity, to fit ever-expanding AI models into memory. The latest models, like GPT-4 and Gemini, contain billions of parameters and require thousands of GPUs or other accelerators working in parallel to train efficiently.

On the other hand, inference requires less compute intensity but still benefits from acceleration. The pre-trained model is optimized and deployed during inference to make predictions on new data. While less compute is needed than training, latency and throughput are essential for real-time inference. Google found out that, while GPUs are ideal for the training phase, models are often optimized and run inference on CPUs. This means that there are customers who choose CPUs as their medium of AI inference for a wide variety of reasons.

The existence of Intel's upcoming Core i9-14900KS processor has been confirmed by a series of insider leaks and premature retail listings—an "alleged" example was photographed and appeared online right at the start of 2024. French e-tail listings produced evidence of two packages—a traditional retail box version, and a barebones tray option for OEM purposes. Earlier today, the I_Leak_VN social media account uploaded proof of a single "Special Edition" box sitting in an unnamed Vietnamese warehouse—it is not immediately clear whether units have reached retail facilities, or have just arrived on Southeast Asian shores. The embargo-busting post seemingly corroborates global insider information/whispers about distribution networks receiving stock—possibly in preparation for a rumored mid-March launch. VideoCardz believes that Vietnamese customers will be paying roughly $765 a pop—30% pricier than the current cost of 14th Gen Core flagship ownership.

Qualcomm Technologies, Inc. unveiled its latest advancements in artificial intelligence (AI) at Mobile World Congress (MWC) Barcelona. From the new Qualcomm AI Hub, to cutting-edge research breakthroughs and a display of commercial AI-enabled devices, Qualcomm Technologies is empowering developers and revolutionizing user experiences across a wide range of devices powered by Snapdragon and Qualcomm platforms.

"With Snapdragon 8 Gen 3 for smartphones and Snapdragon X Elite for PCs, we sparked commercialization of on-device AI at scale. Now with the Qualcomm AI Hub, we will empower developers to fully harness the potential of these cutting-edge technologies and create captivating AI-enabled apps," said Durga Malladi, senior vice president and general manager, technology planning and edge solutions, Qualcomm Technologies, Inc. "The Qualcomm AI Hub provides developers with a comprehensive AI model library to quickly and easily integrate pre-optimized AI models into their applications, leading to faster, more reliable and private user experiences."

A handful of Canadian online stores were a good source of pre-release "Raptor Lake Refresh" information in 2023—that tradition continues into the new year, with DirectDial publishing Intel Core i9-14900KS CPU specifications. This premature listing was highlighted by momomo_us, everyone's favorite PC hardware sleuth—prior to this week's discovery, they tracked down two Core i9-14900KS packages in France. The upcoming special edition flagship Raptor Lake Refresh SKU is expected to launch midway through next month—DirectDial's product page mentions that the item is a "New Arrival," with its status listed as "backordered." The BX8071514900KS part code also appeared on PC21 France's online store—confirming that both places will be offering Intel's retail packaged version. Canadian customers could be paying CA$1005 (~$740 USD) on launch day—the French leak outed a possible initial price of €768.34 (~$828 USD).

Intel's 14th Gen Core i9-14900KS is a "Tetracosa-core (24-Core) 3.20 GHz Processor" according to the DirectDial listing—basic specifications appeared online earlier in the month, so there are no big surprises here: 36 MB L3 Cache, 32 MB L2 Cache, 64-bit Processing, 6.2 GHz Overclocking Speed, Socket LGA-1700 and an Intel UHD 770 integrated graphics solution. The i9-14900KS's Thermal Design Power (TDP) max. spec is listed as 150 W, while its Thermal Specification is set at a maximum of 212°F (100°C). A mid-February HKEPC report put the spotlight on leaked OCCT results—the test unit was tracked with a 409 W maximum package power draw at stock speeds—the processor's PL2 power limit was unlocked via BIOS tweaks. High-end PC enthusiasts expected to Team Blue to unveil the selectively-binned special edition SKU at CES 2024—based on past traditions—but their Core i9-14900KS remained under wraps. We hope to see an official unveiling in March.

Jon Peddie Research reports the growth of the global PC-based graphics processor unit (GPU) market reached 76.2 million units in Q4'23 and PC CPU shipments increased an astonishing 24% year over year, the biggest year-to-year increase in two and a half decades. Overall, GPUs will have a compound annual growth rate of 3.6% during 2024-2026 and reach an installed base of almost 5 billion units at the end of the forecast period. Over the next five years, the penetration of discrete GPUs (dGPUs) in the PC will be 30%.

AMD's overall market share decreased by -1.4% from last quarter, Intel's market share increased 2.8, and Nvidia's market share decreased by -1.36%, as indicated in the following chart.

Samsung Electronics is making 2024 the year of the AI PC with the release of its most powerful and intelligent Galaxy Book product line yet, the Galaxy Book4 series. This latest lineup—consisting of the Galaxy Book4 Ultra, Galaxy Book4 Pro and Galaxy Book4 Pro 360—offers intelligent performance, enhanced security and a vivid, interactive display, all in an ultra-portable design. From the new Intel Core Ultra Processor to the suite of AI features, the Galaxy Book4 series is packed with cutting-edge technology that aims to not only simplify but amplify users' computing experience.

Visitors discovered the Galaxy Book4 series' full capabilities inside Samsung's booth at Mobile World Congress (MWC) 2024, the world's largest mobile exhibition held from February 26-29 in Barcelona, Spain. Samsung Newsroom sat down with Mincheol Lee, Head of Galaxy Eco Biz Team, Mobile eXperience Business at Samsung Electronics, and David Feng, Vice President of Client Computing Group and General Manager of Client Segments at Intel, to explore how the advancements in the Galaxy Book4 series can enrich the lives of users.

Supermicro, Inc. (NASDAQ: SMCI), a Total IT Solution Provider for AI, Cloud, Storage, and 5G/Edge, delivers an expanded portfolio of purpose-built infrastructure solutions to accelerate performance and increase efficiency in 5G and telecom workloads. With one of the industry's most diverse offerings, Supermicro enables customers to expand public and private 5G infrastructures with improved performance per watt and support for new and innovative AI applications. As a long-term advocate of open networking platforms and a member of the O-RAN Alliance, Supermicro's portfolio incorporates systems featuring 5th Gen Intel Xeon processors, AMD EPYC 8004 Series processors, and the NVIDIA Grace Hopper Superchip.

"Supermicro is expanding our broad portfolio of sustainable and state-of-the-art servers to address the demanding requirements of 5G and telco markets and Edge AI," said Charles Liang, president and CEO of Supermicro. "Our products are not just about technology, they are about delivering tangible customer benefits. We quickly bring data center AI capabilities to the network's edge using our Building Block architecture. Our products enable operators to offer new capabilities to their customers with improved performance and lower energy consumption. Our edge servers contain up to 2 TB of high-speed DDR5 memory, 6 PCIe slots, and a range of networking options. These systems are designed for increased power efficiency and performance-per-watt, enabling operators to create high-performance, customized solutions for their unique requirements. This reassures our customers that they are investing in reliable and efficient solutions."

Intel CEO Pat Gelsinger engaged with press/media representatives following the conclusion of his IFS Direct Connect 2024 keynote speech—when asked about Team Blue's ongoing relationship with TSMC, he confirmed that their manufacturing agreement has advanced from "5 nm to 3 nm." According to a China Times news article: "Gelsinger also confirmed the expansion of orders to TSMC, confirming that TSMC will hold orders for Intel's Arrow and Lunar Lake CPU, GPU, and NPU chips this year, and will produce them using the N3B process, officially ushering in the Intel notebook platform that the outside world has been waiting for many years." Past leaks have indicated that Intel's Arrow Lake processor family will have CPU tiles based on their in-house 20A process, while TSMC takes care of the GPU tile aspect with their 3 nm N3 process node.

That generation is expected to launch later this year—the now "officially confirmed" upgrade to 3 nm should produce pleasing performance and efficiency improvements. The current crop of Core Ultra "Meteor Lake" mobile processors has struggled with the latter, especially when compared to rivals. Lunar Lake is marked down for a 2025 launch window, so some aspects of its internal workings remain a mystery—Gelsinger has confirmed that TSMC's N3B is in the picture, but no official source has disclosed their in-house manufacturing choice(s) for LNL chips. Wccftech believes that Lunar Lake will: "utilize the same P-Core (Lion Cove) and brand-new E-Core (Skymont) core architecture which are expected to be fabricated on the 20A node. But that might also be limited to the CPU tile. The GPU tile will be a significant upgrade over the Meteor Lake and Arrow Lake CPUs since Lunar Lake ditches Alchemist and goes for the next-gen graphics architecture codenamed "Battlemage" (AKA Xe2-LPG)." Late January whispers pointed to Intel and TSMC partnering up on a 2 nanometer process for the "Nova Lake" processor generation—perhaps a very distant prospect (2026).

Last week, AMD's Ryzen 8000GE desktop APU lineup appeared online—four lower power (TDP of 35 W) SKUs are set to join the already released 65 W TDP AM5 "Hawk Point" family. GucksTV has acquired a flagship 8000GE model, albeit in engineering sample form—a Hong Kong-based Ebay Store lists "AMD Ryzen 7 8700GE ES Tray" processors. At the time of writing only one unit remains in stock, priced at $298.99 with the option for free international delivery. The "hugohk" shop appears to specialize in supplying all sorts of Team Red engineering sample CPUs. GucksTV's German language video review pitches the Ryzen 7 8700GE engineering sample against the finalized retail release Ryzen 7 8700 APU.

AMD has not made any official release date announcements regarding the leaked Ryzen 8000GE range, but VideoCardz believes that "expectations are high that these variants will hit the market soon through system integrators." The GucksTV comparison video shows that: "On average, the single-core of 8700GE performance drops by 5%, while multi-core is 17% below 8700G. For graphics, that's a 23% average drop in performance while requiring 52% less power." The reviewer noted that his engineering sample was not allowing access to memory OC profiles, until a motherboard BIOS update was implemented (most likely via Beta firmware)—granting 6400 MT/s instead of the normal JEDEC rate of 5200 MT/s. The test platform utilized an ASRock A620I Lightning WiFi Mini-ITX mainboard—finalized Ryzen 7 8700GE APUs could be ideal candidates for usage in quiet/low temperature compact form factor systems.

Last year, Arm introduced its Neoverse Compute Subsystem (CSS) for the N2 and V2 series of data center processors, providing a reference platform for the development of efficient Arm-based chips. Major cloud service providers like AWS with Graviton 4 and Trainuium 2, Microsoft with Cobalt 100 and Maia 100, and even NVIDIA with Grace CPU and Bluefield DPUs are already utilizing custom Arm server CPU and accelerator designs based on the CSS foundation in their data centers. The CSS allows hyperscalers to optimize Arm processor designs specifically for their workloads, focusing on efficiency rather than outright performance. Today, Arm has unveiled the next generation CSS N3 and V3 for even greater efficiency and AI inferencing capabilities. The N3 design provides up to 32 high-efficiency cores per die with improved branch prediction and larger caches to boost AI performance by 196%, while the V3 design scales up to 64 cores and is 50% faster overall than previous generations.

Both the N3 and V3 leverage advanced features like DDR5, PCIe 5.0, CXL 3.0, and chiplet architecture, continuing Arm's push to make chiplets the standard for data center and cloud architectures. The chiplet approach enables customers to connect their own accelerators and other chiplets to the Arm cores via UCIe interfaces, reducing costs and time-to-market. Looking ahead, Arm has a clear roadmap for its Neoverse platform. The upcoming CSS V4 "Adonis" and N4 "Dionysus" designs will build on the improvements in the N3 and V3, advancing Arm's goal of greater efficiency and performance using optimized chiplet architectures. As more major data center operators introduce custom Arm-based designs, the Neoverse CSS aims to provide a flexible, efficient foundation to power the next generation of cloud computing.

Phoronix has spotted intriguing new Linux kernel patches for Intel Core Ultra "Meteor Lake" processors—the Monday morning notes reveal in-house software engineers are implementing default power profile adjustments. Meteor Lake CPUs have been operating on a default "balanced_performance" mode since their December 2023 launch—Linux adjustments will affect the processor's Energy Performance Preference (EPP) under Linux (similar to Windows Power Plans). Michael Larabel (Phoronix head honcho) laid out some history: "We've seen EPP overrides/tuning in the past within the Intel P-State driver for prior generations of Intel processors and this is much the same here. The ACPI EPP value is typically a range from 0 to 255 for indicating the processor/system power to performance preference."

He continued onto present day circumstances: "To date though the Intel P-State EPP override/tuning has been focused on the default "balanced_performance" mode while the first patch (from Monday) allows for model-specific EPP overrides for all pre-defined EPP strings. The second patch then goes ahead and updates the EPP values for Meteor Lake so that the balanced_performance default is now treated as 115 rather than 128 and the "performance" EPP is set to 16 rather than 0." Larabel is hopeful that a public release will coincide with the "upcoming Linux v6.9 cycle." Intel software engineers reckon that their tweaks/overrides have produced higher performance results—for "small form factor devices"—while reducing CPU temperatures and thermal throttling. Meteor Lake is considered to be quite energy inefficient when compared to the closest mobile processor architectures from AMD and Apple. Team Blue's next-gen Arrow Lake family is expected to launch later this year, but the current crop of CPUs require a bit of TLC and optimization in the meantime.