Acer today announced the extension of its SpatialLabs stereoscopic 3D lineup to the Aspire line of laptops and Predator gaming monitors.

The new Aspire 3D 15 SpatialLabs Edition laptop delivers captivating 3D content for entertainment and creation on its 15.6-inch UHD display; It also comes with a suite of AI-powered SpatialLabs applications for 3D viewing and content creation, without the need for specialized glasses, delighting users when watching their favorite content and empowering developers to see their designs in their real 3D forms. With Microsoft Copilot in Windows 11, users can experience upscaled creativity and productivity with AI-powered task assistance, while Acer's suite of AI-supported solutions in Acer PurifiedView and PurifiedVoice elevate conference calls on the 3D laptop.

Acer announced new additions to its Aspire laptop line, showcasing an extensive range of performance and design options to support everyday computing needs.

The Aspire Vero 16 is the latest from its Vero product line, powered by the new Intel Core Ultra processors with Intel AI Boost and Wi-Fi 7 compatibility. Acer has committed to carbon neutrality for the Aspire Vero 16, following international standards for carbon footprint calculation and carbon neutrality. Actions are taken at each stage of the device lifecycle to minimize its carbon footprint, and then, high-quality carbon credits will be applied to attain carbon neutrality. The Intel Evo Edition laptop has increased the usage of post-consumer recycled (PCR) materials on the chassis, doubling that of the 2021 model, to combine eco-innovation and premium PC experiences on the device.

MSI, the globally renowned gaming brand, has collaborated with the esteemed game developer CAPCOM to mark the 20th anniversary of the Monster Hunter game series by introducing a carefully curated line of limited-edition PC products. The unveiling of these highly anticipated products will take place at CES 2024, where MSI will showcase concept prototypes at an exclusive booth. The official debut of these products is scheduled to coincide with the 20th-anniversary celebration of Monster Hunter.

Inspired by one of the series' most iconic monsters, the Rathalos, this collaboration aims to infuse the majestic aura and power of the Rathalos into a captivating range of limited-edition gaming peripherals. This includes gaming laptops, monitors, graphics cards, motherboards, cases, liquid coolers, and controllers. With these products, MSI invites gamers to embark on a journey into the captivating world of Monster Hunter, delivering a unique gaming experience that combines the superior craftsmanship of MSI with the classic gaming elements of CAPCOM.

According to the report from a journal called Fundamental Research, researchers from the Institute of Computing Technology at the Chinese Academy of Sciences have developed a 256-core multi-chiplet processor called Zhejiang Big Chip, with plans to scale up to 1,600 cores by utilizing an entire wafer. As transistor density gains slow, alternatives like multi-chiplet architectures become crucial for continued performance growth. The Zhejiang chip combines 16 chiplets, each holding 16 RISC-V cores, interconnected via network-on-chip. This design can theoretically expand to 100 chiplets and 1,600 cores on an advanced 2.5D packaging interposer. While multi-chiplet is common today, using the whole wafer for one system would match Cerebras' breakthrough approach. Built on 22 nm process technology, the researchers cite exascale supercomputing as an ideal application for massively parallel multi-chiplet architectures.

Careful software optimization is required to balance workloads across the system hierarchy. Integrating near-memory processing and 3D stacking could further optimize efficiency. The paper explores lithography and packaging limits, proposing hierarchical chiplet systems as a flexible path to future computing scale. While yield and cooling challenges need further work, the 256-core foundation demonstrates the potential of modular designs as an alternative to monolithic integration. China's focus mirrors multiple initiatives from American giants like AMD and Intel for data center CPUs. But national semiconductor ambitions add urgency to prove domestically designed solutions can rival foreign innovation. Although performance details are unclear, the rapid progress shows promise in mastering modular chip integration. Combined with improving domestic nodes like the 7 nm one from SMIC, China could easily create a viable Exascale system in-house.

Intel Corporation today announced the appointment of Justin Hotard as executive vice president and general manager of its Data Center and AI Group (DCAI), effective Feb. 1. He joins Intel with more than 20 years of experience driving transformation and growth in computing and data center businesses, and is a leader in delivering scalable AI systems for the enterprise.

Hotard will become a member of Intel's executive leadership team and report directly to CEO Pat Gelsinger. He will be responsible for Intel's suite of data center products spanning enterprise and cloud, including its Intel Xeon processor family, graphics processing units (GPUs) and accelerators. He will also play an integral role in driving the company's mission to bring AI everywhere.

With our XPS portfolio, we have a long history of taking risks, being inquisitive and asking big design questions. At CES 2022, we showcased our vision of the future with XPS 13 Plus—an elegant and modern device, designed with simplicity at the core. The design turned heads and continues to do so today, with headlines calling it elegant, stylish, stunning, beautiful and our personal favorite—referring to the design as "the future is here."

This bold design has forever changed the ID of the XPS brand. Now, we are unifying the design across our XPS portfolio, introducing new screen sizes with the XPS 16 and XPS 14 and revamping the XPS 13 Plus to XPS 13. This trio of laptops share elements that eliminate distractions and place the focus on productivity.

The Video Electronics Standards Association (VESA) today announced that it has published an update to its Adaptive-Sync Display Compliance Test Specification (Adaptive-Sync Display CTS), which is the first publicly open standard for front-of-screen performance of variable refresh rate displays. Adaptive-Sync Display version 1.1a provides updated testing procedures and logo support for an emerging category of displays that can operate at different maximum refresh rates when resolution is reduced. This optional "Dual Mode" testing and logo support allows display OEMs with qualifying hardware to certify their products at two different sets of resolution and refresh rate (for example, 4K/144 Hz and 1080p/280 Hz).

Adaptive-Sync Display v1.1a also includes an update that allows display OEMs to achieve a higher AdaptiveSync Display refresh rate certification for displays that support an "overclocked" or faster mode option that is not enabled by default in the factory configuration. In such cases, the overclocked mode must support Adaptive-Sync-enabled GPUs in a non-proprietary manner, and the display must pass all of the rigorous Adaptive-Sync Display compliance tests in both its factory default mode, and completely retested a second time in the overclocking mode. Both the dual mode and overclocking changes to the Adaptive-Sync Display CTS v1.1a only apply to the VESA Certified AdaptiveSync Display logo program; they do not apply to the VESA Certified MediaSync Display logo program.To date, more than 100 products have been certified to the Adaptive-Sync Display standard. A complete list of Adaptive-Sync Display certified products can be found at https://www.adaptivesync.org/certified-products/.

Global semiconductor capacity is expected to increase 6.4% in 2024 to top the 30 million *wafers per month (wpm) mark for the first time after rising 5.5% to 29.6 wpm in 2023, SEMI announced today in its latest quarterly World Fab Forecast report.

The 2024 growth will be driven by capacity increases in leading-edge logic and foundry, applications including generative AI and high-performance computing (HPC), and the recovery in end-demand for chips. The capacity expansion slowed in 2023 due to softening semiconductor market demand and the resulting inventory correction.

Intel Corp and DigitalBridge Group, Inc., a global investment firm, today announced the formation of Articul8 AI, Inc. (Articul8), an independent company offering enterprise customers a full-stack, vertically-optimized and secure generative artificial intelligence (GenAI) software platform. The platform delivers AI capabilities that keep customer data, training and inference within the enterprise security perimeter. The platform also provides customers the choice of cloud, on-prem or hybrid deployment.

Articul8 was created with intellectual property (IP) and technology developed at Intel, and the two companies will remain strategically aligned on go-to-market opportunities and collaborate on driving GenAI adoption in the enterprise. Arun Subramaniyan, formerly vice president and general manager in Intel's Data Center and AI Group, has assumed leadership of Articul8 as its CEO.

At the 2023 International CES, Intel had announced its 65 W (locked) 13th Gen Core "Raptor Lake" desktop processors, but the star of the show then was the enthusiast-segment Core i9-13900KS Limited Edition processor. A picture of what is allegedly the i9-14900KS, suggests that Intel might repeat its last year's CES announcements, with the i9-14900KS. Last time around, they had the claim to launch the world's first 6 GHz processor, something that is also the latest maximum boost frequency of the current i9-14900K, so it remains to be see what the i9-14900KS brings to the table. A 6 GHz all-core boost for the P-cores, or a speed bump that lets it finally beat the $350 Ryzen 7 7800X3D at gaming? We'll find out next week in Vegas.

Ahead of its rumored January 8 announcement, various unreleased 14th Gen Intel Core desktop processors got listed on European e-tailer CoolMod. These are non-K (65 W) processor models. The lineup begins with the Core i3-14100F, a 4P+0E processor without integrated graphics, priced at €124.94. If you need the iGPU, it will cost you at least €25 more, for the i3-14100 at €149.96. The most hotly anticipated chip among the lineup, the Core i5-14400F is priced at €219.95. A notch up is the i5-14500, going for a steep €249.95. Interestingly, the store has the i5-14400 (witth the iGPU) listed at the same exact price. There is no i5-14600 listed.

The Core i7-14700F is priced at €384.95. This chip has an 8P+12E configuration, which is the same as the i7-14700K, but with lower base frequency, and tighter power limits. It lacks an iGPU, and if you need one, then the i7-14700 is listed at €409.95. At the upper crust of the lineup you have the Core i9-14900F at €574.96, which has the full 8P+16E core configuration, but lower clock speeds than the i9-14900K, and no iGPU, which can be had for €25 more, with the i9-14900 at €599.95. All prices are inclusive of taxes.

Intel is expanding immersion cooling collaborations with Taiwanese partners to strengthen its data center offerings for AI workloads. This includes developing an industry-first open IP complete immersion cooling solution and reference design. Partners like Kenmec and Auras Technology will be key in implementing Intel's advanced cooling roadmap. Intel is also cooperating with Taiwan's Industrial Research Institute on a new lab for certifying high-performance computing cooling technologies to international standards. With local ecosystem partners, Intel aims to accelerate next-generation cooling solutions for Taiwanese and global data centers. Advanced cooling allows packing more performance into constrained data center footprints, which is critical for AI's rapid growth. Intel touts a superfluid-based modular cooling system achieving 1500 Watts+ heat dissipation for high-density deployments.

Meanwhile, Kenmec offers a range of liquid cooling products, from Coolant Distribution Units (CDU) to customized Open Rack version 3 (ORv3) water cooling cabinets, with solutions already Intel-certified. Intel wants to solidify its infrastructure leadership as AI workloads surge by fostering an open, collaborative ecosystem around optimized cooling technologies. While progressing cutting-edge immersion and liquid cooling hardware, cultivating shared validation frameworks and best practices ensures broad adoption. With AI-focused data centers demanding ever-greater density, power efficiency, and reliability, cooling can no longer be an afterthought. Intel's substantial investments in a robust cooling ecosystem highlight it as a priority right alongside silicon advances. By lifting up Taiwanese partners as strategic cooling co-innovators, Intel aims to cement future competitiveness.

Chinese x86 CPU developer Zhaoxin is working on adding support in the Linux kernel for scheduling optimization on its processors featuring "preferred cores." Similar to asymmetric core designs from Intel and AMD, Zhaoxin's chips may have specific higher-performance cores the OS scheduler should target for critical workloads. To enable this, Zhaoxin has proposed Linux patches leveraging existing ACPI functionality to indicate per-core differences in max frequency or capabilities. The CPUfreq driver is updated to reflect this, allowing the scheduler to favor the designated high-performance cores when assigning threads and processes. This ensures tasks can dynamically take advantage of the faster cores to maximize performance. The approach resembles tuned scheduling, aware of core topology and heterogeneity already found in Intel and AMD processors.

Zhaoxin's patches don't specify which existing or upcoming CPUs will expose preferred core hints. The company likely wants the functionality in place for future server-class products where asymmetric designs make sense for efficiency. The new code contribution reflects Zhaoxin's broader upstreaming effort around Linux kernel support for its Yongfeng server CPU family. Robust open-source foundations are crucial for gaining developer mindshare and data center adoption. Adding sophisticated features like preferred core scheduling indicates that Zhaoxin's chips are maturing from essential x86 compatibility to more refined performance optimization. While still trailing Intel and AMD in cores and clocks, closing the software ecosystem and efficiency gap remains key to competitiveness. Ongoing Linux enablement work is laying the groundwork for more capable Zhaoxin silicon.

LG Electronics (LG) is expanding its LG gram series in 2024, offering consumers a wider selection of compelling choices, including the new LG gram Pro. The perfect blend of power and portability, LG gram series ultra-lightweight laptops combine high-end specifications with exceptionally slim yet durable designs and all-day battery life. All 2024 models come with the latest AI-enabled functions on LG gram Link app, simplifying tasks like file sharing, photo sharing and screen mirroring across LG gram, Android and iOS devices. U.S. pricing and availability will be announced at a later date.

LG's best-in-class LG gram Pro laptops (models 16Z90SP and 17Z90SP) come equipped with a Intel Core Ultra processor with hybrid architecture, an NVMe PCIe 4.0 SSD and an NVIDIA GeForce RTX 3050 graphics card. The new LG gram Pro laptops are also embedded with the Intel AI Boost, Intel's neural processing unit (NPU) that can handle AI workloads even without a network connection.

MINISFORUM's first Mini WorkStation MS-01, is officially available for pre-order on the official store. Tailored for tech-savvy gamers, this high-performance Mini WorkStation boasts the fastest network speed, strongest expansion capabilities, and maximum storage. It offers options with Intel Core i9-13900H and i9-12900H processors, starting at a price of $549 USD.

The MS-01 is powered by the Intel 13th generation's most robust mobile Core i9 processor, the i9-13900H, featuring 14 cores and 20 threads, a base frequency of 2.6 GHz, and a turbo boost frequency of 5.4 GHz. With the integrated 96EU Intel Iris Xe graphics, running at up to 1.5 GHz, it delivers outstanding flagship performance for tasks ranging from daily graphics processing to video production. In addition to its impressive performance, the MS-01 boasts a plethora of interfaces, enabling network transfer speeds of up to 65 Gbps, making it the fastest Mini PC in terms of network speed of MINISFORUM.

During the recent IEDM conference, TSMC previewed its process roadmap for delivering next-generation chip packages packing over one trillion transistors by 2030. This aligns with similar long-term visions from Intel. Such enormous transistor counts will come through advanced 3D packaging of multiple chipsets. But TSMC also aims to push monolithic chip complexity higher, ultimately enabling 200 billion transistor designs on a single die. This requires steady enhancement of TSMC's planned N2, N2P, N1.4, and N1 nodes, which are slated to arrive between now and the end of the decade. While multi-chipset architectures are currently gaining favor, TSMC asserts both packaging density and raw transistor density must scale up in tandem. Some perspective on the magnitude of TSMC's goals include NVIDIA's 80 billion transistor GH100 GPU—among today's largest chips, excluding wafer-scale designs from Cerebras.

Yet TSMC's roadmap calls for more than doubling that, first with over 100 billion transistor monolithic designs, then eventually 200 billion. Of course, yields become more challenging as die sizes grow, which is where advanced packaging of smaller chiplets becomes crucial. Multi-chip module offerings like AMD's MI300X and Intel's Ponte Vecchio already integrate dozens of tiles, with PVC having 47 tiles. TSMC envisions this expansion to chip packages housing more than a trillion transistors via its CoWoS, InFO, 3D stacking, and many other technologies. While the scaling cadence has recently slowed, TSMC remains confident in achieving both packaging and process breakthroughs to meet future density demands. The foundry's continuous investment ensures progress in unlocking next-generation semiconductor capabilities. But physics ultimately dictates timelines, no matter how aggressive the roadmap.

LG Electronics (LG) is ready to unveil its innovative smart home Artificial Intelligence (AI) agent at CES 2024. LG's smart home AI agent boasts robotic, AI and multi-modal technologies that enable it to move, learn, comprehend and engage in complex conversations. An all-around home manager and companion rolled into one, LG's smart life solution enhances users' daily lives and showcases the company's commitment to realizing its "Zero Labor Home" vision.

With its advanced 'two-legged' wheel design, LG's smart home AI agent is able to navigate the home independently. The intelligent device can verbally interact with users and express emotions through movements made possible by its articulated leg joints. Moreover, the use of multi-modal AI technology, which combines voice and image recognition along with natural language processing, enables the smart home AI agent to understand context and intentions as well as actively communicate with users.

Intel has secured a $3.2 billion grant from the Israeli government for constructing a new $25 billion chip fabrication facility in southern Israel. This represents the company's largest-ever investment in a manufacturing facility. Intel's expansion aims to strengthen global semiconductor supply chains and reduce reliance on singular geographies like Taiwan. The new Fab 38 plant will be built alongside Intel's existing Fab 28 facility in Kiryat Gat. Construction has already begun, with operations slated to start in 2028 and serve until 2035. Intel expects to create thousands of local jobs as well. The company will receive a reduced 7.5% corporate tax rate and has committed to $16.6 billion in local procurement. The grant comes amid Israel's ongoing conflict with Palestinian militant group Hamas.

However, Intel's decades-long presence and investments in the country showcase economic priorities persevering. Its key processor technology was and is being designed in Israel labs. The Kiryat Gat expansion aligns with Intel CEO Pat Gelsinger's strategy of manufacturing diversification through mega-investments across the US, Europe, and Israel. It follows the company's record $20 billion fab project in Ohio. With significant government subsidies at each site, Intel aims to restore market dominance against rivals like AMD and Nvidia through scale of manufacturing. The new Israeli fab will complement Intel's lineup of leading-edge technologies and help maintain Israel's reputation as a global semiconductor hub.

In the era of high-tech development and the ever-increasing demand for data processing power, data centers are consuming more energy and generating excess heat. As a global leader in thermal solutions, SUNON is at the forefront, offering a diverse range of cutting-edge liquid cooling solutions tailored to advanced data centers equipped with high-capacity CPU and GPU computing for AI, edge, and cloud servers.

SUNON's liquid cooling design services are ideally suited for modern data centers, generative AI computing, and high-performance computing (HPC) applications. These solutions are meticulously customized to fit the cooling space and server density of each data center. With their compact yet comprehensive design, they guarantee exceptional cooling efficiency and reliability, ultimately contributing to a significant reduction in a client's total cost of ownership (TCO) in the long term. In the pursuit of net-zero emissions standards, SUNON's liquid cooling solutions play a pivotal role in enhancing corporate sustainability. They o ff er a win-win scenario for clients seeking to transition toward greener and more digitalized operations.

UltrabookReview, which recently took the ASUS Zenbook 14 OLED UX3405 for a spin, noticed something interesting with the Intel Core Ultra 155H "Meteor Lake" processor powering it—apparently Intel is still working with its device partners to improve performance and efficiency, and a UEFI firmware update (BIOS update) from ASUS improves the processor's performance/Watt. The reviewer compares the notebook with its original BIOS version 201, to the updated version 203, and notices improvements in performance/Watt at 28 W. The firmware apparently updates the notebook's power management. The improvements are most apparent with Cinebench R23, where the best-run score with the original 201 firmware was 12357 points, and the updated 203 firmware was 13873 points (a 12.25% improvement). You can catch the review in the source link below.

Mini PC designer Geekom is bring three innovative desktops to the 2024 International CES, based on the very latest mobile processors by Intel and AMD. These boxes are hinged on MoDT (mobile on desktop) hardware, meaning that energy efficient mobile processors are crammed into compact desktop cases, and wired out with all the connectivity they can put out. The three mini PC models Geekom is launching includes the IT14 Pro, the A8 Max, and the APro8 Max. The Geekcom IT14 Pro comes in a 0.7-liter chassis (about the size of a NUC), and is powered by an Intel Core Ultra 7 155H "Meteor Lake" processor configured with 6P+8E+2LP cores, or 16-core/22-thread. The desktop relies entirely on the maxed out Arc iGPU with all its 8 Xe cores enabled (128 EU). The NPU is also enabled. The company didn't reveal the memory, storage, or WLAN configuration of this desktop, yet.

The A8 Max is based on a similar 1-liter class chassis, but uses an AMD Ryzen 7 8840HS or Ryzen 9 8940HS "Hawk Point" processor, both of which are 8-core/16-thread "Zen 4," and configured with the full Radeon 780M iGPU available (12 CU or 768 stream processors). The star attraction here is the updated Ryzen AI NPU, which drives up the AI inference performance of these chips to 39 TOPS, compared to 34 TOPS of the Intel "Meteor Lake" chips. The APro8 Max is a based on a physically larger chassis that looks a bit like a game console. It's based on mostly the same hardware as the A8 Max, but with an added Radeon RX 7600M XT discrete GPU, which should give it the ability to offer maxed out AAA gaming at 1080p, or power productivity workloads at 4K UHD. We shoud know more about these three in Vegas next month.

Intel's entry-level 14th Gen Core desktop processor, the Core i3-14100, got its first retailer listing, with ShopBLT putting it up for $150.24. The 4-core/8-thread chip that only has performance cores (P-cores), is based on the same H0 silicon that drives the Core i5-12600, which physically lacks E-cores. Intel has been reusing its "Alder Lake" silicon across the non-K variants of its 13th Gen and now 14th Gen Core i3 and Core i5 processor SKUs. One way to spot them is by the size of their dedicated L2 caches for the P-cores, which is 1.25 MB, compared to 2 MB on the 8P+16E "Raptor Lake-S" silicon used to carve out Core i7 and Core i9 SKUs across the 13th Gen and 14th Gen.

The Core i3-14100 offers a tiny speed bump over its predecessor, the i3-13100. With the base frequency set at 3.50 GHz, and boost frequency probably at 4.70 GHz, compared to the 3.40 GHz and 4.50 GHz of the i3-13100. Each of the four P-cores has 1.25 MB of L2 cache, and they share 12 MB of L3 cache. The chip gets the same I/O as the rest of the lineup, with a dual-channel DDR4/DDR5 memory interface, and PCIe connectivity that includes a Gen 5 x16, a CPU-attached Gen 4 x4 for NVMe slots, and a DMI 4.0 x8 chipset bus. The iGPU on offer is the UHD Graphics 730 based on Xe-LP, with 24 EU, compared to the 32 that's standard with higher 14th Gen Core desktop processor models. The chip has a processor base power of 60 W, and a possible maximum turbo power of 110 W. Intel is expected to announce its locked 14th Gen Core desktop processor lineup in January 2024, which should include the i3-14100, and its cheaper sibling, the i3-14100F, which lacks integrated graphics.

ASRock Industrial releases the NUC Ultra 100 Motherboard Series with breakthrough powered by Intel Core Ultra processors (Meteor Lake-H). Presenting a 3D performance hybrid architecture that supports up to 14 cores and 20 threads, complemented by the latest integrated Intel ARC Graphics and the pioneering Intel NPU AI engine. The NUC Ultra 100 Motherboard Series are designed in NUC form factor, providing two DDR5-5600 MHz memory up to 96 GB, triple storages, 4K quad displays, 2.5G dual LAN, one USB4/Thunderbolt, and four USB 3.2 Gen 2. This advancement expands into enhanced creativity, efficiency, and collaboration using AI across diverse areas such as entertainment, corporate functions, smart retail, kiosks, digital signage, smart cities, embedded industries, Edge AIoT applications, and more.

The NUC Ultra 100 Motherboard Series encompass NUC-155H and NUC-125H models, powered by Intel Core Ultra 7/5 processors 155H/125H (Meteor Lake-H). The Series feature the upgraded dual-channel SO-DIMM DDR5 5600 MHz up to 96 GB memory, plus support for up to 4K quad displays with one DP 2.1 (from USB4), one DP 1.4a (from Type-C), and two HDMI 2.0b with Intel ARC Graphics, providing immersive experience. Notable upgrades extend to the triple storages of one M.2 Key M (2242/2280), one M.2 Key M (2242) with PCIe Gen4x4 for SSD, and one SATA 3.0. Moreover, rich I/O connectivity and expansion include one USB4/Thunderbolt 4, four USB 3.2 Gen 2 (Type-C/Type-A), 2.5G dual LAN, and one M.2 Key E (2230) with PCIe x1, USB 2.0 and CNVi for wireless. The Series also provide 12-24 V DC-in jack for flexible power input, -20°C ~ 70°C wide operating temperature, plus TPM support with Intel Platform Trust Technology (PTT) for enhanced security.

GIGABYTE Technology, a leading global powerhouse in motherboards, graphics cards, and cutting-edge hardware solutions, proudly announces that GIGABYTE DDR5 motherboards deliver breakthrough support for a memory capacity of single DIMM 64 GB with the latest Kingston FURY Renegade DDR5 memory. The 4DIMM model boosts the memory capacity up to 256 GB, while the 2DIMM model has a maximum capacity of up to 128 GB.⁠

With innovative layout design and top-notch components, GIGABYTE motherboards have played a leading role in memory performance. From the Intel 700 and 600 series to the AMD 600 series, GIGABYTE DDR5 motherboards will support a memory capacity of single DIMM 64 GB through BIOS update. The updated BIOS and memory support list will be available on the GIGABYTE official website, coinciding with the launch of the latest Kingston FURY Renegade DDR5 memory. Please stay tuned to the GIGABYTE official website for further information.

Intel's software team has added support in its open-source Linux drivers for an unannounced Habana "Gaudi2C" AI accelerator variant. Little is documented about the mystery Gaudi2C, which shares a core identity with Intel's flagship Gaudi2 data center training and inference chip, otherwise broadly available. The new revision is distinguished only by a PCI ID of "3" in the latest patch set for Linux 6.8. Speculations circulate that Gaudi2C may be a version tailored to meet China-specific demands, similar to Intel's Gaudi2 HL-225B SKU launched in July with reduced interconnect links. With US export bans restricting sales of advanced hardware to China, including Intel's leading Gaudi2 products, creating reduced-capability spinoffs that meet export regulations lets Intel maintain crucial Chinese revenue.

Meanwhile, Intel's upstream Linux contributions remain focused on hardening Gaudi/Gaudi2 support, now considered "very stable" by lead driver developer Oded Gabbay. Minor new additions reflect maturity, not instability. The open-sourced foundations contrast NVIDIA's proprietary driver model, a key Intel competitive argument for service developers using Habana Labs hardware. With the SynapseAI software suite reaching stability, some enterprises could consider Gaudi accelerators as an alternative to NVIDIA. And with Gaudi3 arriving next year, the ecosystem will get a better competitive advantage with increased performance targets.