The US government is investigating the potential national security risks associated with China's involvement in the development of open-source RISC-V chip technology. According to a letter obtained by Reuters, the Department of Commerce has informed US lawmakers that it is actively reviewing the implications of China's work in this area. RISC-V, an open instruction set architecture (ISA) created in 2014 at the University of California, Berkeley, offers an alternative to proprietary and licensed ISAs like those developed by Arm. This open-source ISA can be utilized in a wide range of applications, from AI chips and general-purpose CPUs to high-performance computing applications. Major Chinese tech giants, including Alibaba and Huawei, have already embraced RISC-V, positioning it as a new battleground in the ongoing technological rivalry between the United States and China over cutting-edge semiconductor capabilities.

In November, a group of 18 US lawmakers from both chambers of Congress urged the Biden administration to outline its strategy for preventing China from gaining a dominant position in RISC-V technology, expressing concerns about the potential impact on US national and economic security. While acknowledging the need to address potential risks, the Commerce Department noted in its letter that it must proceed cautiously to avoid unintentionally harming American companies actively participating in international RISC-V development groups. Previous attempts to restrict the transfer of 5G technology to China have created obstacles for US firms involved in global standards bodies where China is also a participant, potentially jeopardizing American leadership in the field. As the review process continues, the Commerce Department faces the delicate task of balancing national security interests with the need to maintain the competitiveness of US companies in the rapidly evolving landscape of open-source chip technologies.

Google has officially joined the club of custom Arm-based, in-house-developed CPUs. As of today, Google's in-house semiconductor development team has launched the "Axion" CPU based on Arm instruction set architecture. Using the Arm Neoverse V2 cores, Google claims that the Axion CPU outperforms general-purpose Arm chips by 30% and Intel's processors by a staggering 50% in terms of performance. This custom silicon will fuel various Google Cloud offerings, including Compute Engine, Kubernetes Engine, Dataproc, Dataflow, and Cloud Batch. The Axion CPU, designed from the ground up, will initially support Google's AI-driven services like YouTube ads and Google Earth Engine. According to Mark Lohmeyer, Google Cloud's VP and GM of compute and machine learning infrastructure, Axion will soon be available to cloud customers, enabling them to leverage its performance without overhauling their existing applications.

Google's foray into custom silicon aligns with the strategies of its cloud rivals, Microsoft and Amazon. Microsoft recently unveiled its own AI chip for training large language models and an Arm-based CPU called Cobalt 100 for cloud and AI workloads. Amazon, on the other hand, has been offering Arm-based servers through its custom Graviton CPUs for several years. While Google won't sell these chips directly to customers, it plans to make them available through its cloud services, enabling businesses to rent and leverage their capabilities. As Amin Vahdat, the executive overseeing Google's in-house chip operations, stated, "Becoming a great hardware company is very different from becoming a great cloud company or a great organizer of the world's information."

During the Vision 2024 event, Intel announced that its upcoming Xeon processors will be branded under the new "Xeon 6" moniker. This rebranding effort aims to simplify the company's product stack and align with the recent changes made to its consumer CPU naming scheme. In contrast to the previous "x Generation Xeon Scalable", the new branding aims to simplify the product family. The highly anticipated Sierra Forest and Granite Ridge chips will be the first processors to bear the Xeon 6 branding, and they are set to launch in the coming months. Intel has confirmed that Sierra Forest, designed entirely with efficiency cores (E-cores), remains on track for release this quarter. Supermicro has already announced early availability and remote testing programs for these chips. Intel's Sierra Forest is set to deliver a substantial leap in performance. According to the company, it will offer a 2.4X improvement in performance per watt and a staggering 2.7X better performance per rack compared to the previous generation. This means that 72 Sierra Forest server racks will provide the same performance as 200 racks equipped with older second-gen Xeon CPUs, leading to significant power savings and a boost in overall efficiency for data centers upgrading their system.

Intel has also teased an exciting feature in its forthcoming Granite Ridge processors-support for the MXFP4 data format. This new precision format, backed by the Open Compute Project (OCP) and major industry players like NVIDIA, AMD, and Arm, promises to revolutionize performance. It could reduce next-token latency by up to 6.5X compared to fourth-gen Xeons using FP16. Additionally, Intel stated that Granite Ridge will be capable of running 70 billion parameter Llama-2 models, a capability that could open up new possibilities in data processing. Intel claims that 70 billion 4-bit models run entirely on Xeon in just 86 milliseconds. While Sierra Forest is slated for this quarter, Intel has not provided a specific launch timeline for Granite Ridge, stating only that it will arrive "soon after" its E-core counterpart. The Xeon 6 branding aims to simplify the product stack and clarify customer performance tiers as the company gears up for these major releases.

AMD today announced the expansion of the AMD Versal adaptive system on chip (SoC) portfolio with the new Versal AI Edge Series Gen 2 and Versal Prime Series Gen 2 adaptive SoCs, which bring preprocessing, AI inference, and postprocessing together in a single device for end-to-end acceleration of AI-driven embedded systems.

These initial devices in the Versal Series Gen 2 portfolio build on the first generation with powerful new AI Engines expected to deliver up to 3x higher TOPs-per-watt than first generation Versal AI Edge Series devicesi, while new high-performance integrated Arm CPUs are expected to offer up to 10x more scalar compute than first gen Versal AI Edge and Prime series devicesii.

All-in-one computers are often traditionally seen as lower-powered alternatives to traditional desktop workstations. However, a new offering from Alafia AI, a startup focused on medical imaging appliances, aims to shatter that perception. The company's upcoming Alafia Aivas SuperWorkstation packs serious hardware muscle, demonstrating that all-in-one systems can match the performance of their more modular counterparts. At the heart of the Aivas SuperWorkstation lies a 128-core Ampere Altra processor, running at 3.0 GHz clock speed. This CPU is complemented by not one but three NVIDIA L4 GPUs for compute, and a single NVIDIA RTX 4000 Ada GPU for video output, delivering a combined 28,416 CUDA cores for accelerated parallel computing tasks. The system doesn't skimp on other components, either. It features a 4K touch display with up to 360 nits of brightness, an extensive 2 TB of DDR4 RAM, and storage options up to an 8 TB solid-state drive. This combination of cutting-edge CPU, GPU, memory, and storage is squarely aimed at the demands of medical imaging and AI development workloads.

The all-in-one form factor packs this incredible hardware into a sleek, purposefully designed clinical research appliance. While initially targeting software developers, Alafia AI hopes that institutions that can optimize their applications for the Arm architecture can eventually deploy the Aivas SuperWorkstation for production medical imaging workloads. The company is aiming for application integration in Q3 2024 and full ecosystem device integration by Q4 2024. With this powerful new offering, Alafia AI is challenging long-held assumptions about the performance limitations of all-in-one systems. The Aivas SuperWorkstation demonstrates that the right hardware choices can transform these compact form factors into true powerhouse workstations. Especially with a combined total output of three NVIDIA L4 compute units, alongside RTX 4000 Ada graphics card, the AIO is more powerful than some of the high-end desktop workstations.

DFI, the world's leading brand in embedded motherboards and industrial computers, proudly announced the launch of its innovative product lineup featuring Windows on Arm (WoA) at Embedded World 2024. DFI NXP products deliver high power efficiency and seamlessly integrate Windows on Arm, introducing a new era in computing where the traditional stronghold of Windows on x86 processors is evolving.

Arm and Microsoft revealed a compelling study that projected an 81% growth in the Windows on Arm market within the next five years. DFI's commitment to embracing this dynamic landscape is evident in its latest product offerings, designed to unlock the true potential of WoA. The diverse NXP product lineup included Single Board Computers, system-embedded Box PCs, and Panel PCs tailored to various customer needs.

Arm China is making strides in the AI accelerator market with its new neural processing unit (NPU) called Zhouyi. The company aims to integrate the NPU into low-cost domestic CPUs, potentially giving it an edge over competitors like AMD and Intel. Initially a part of Arm Holdings, which licensed IP in China, Arm China took on a new strategy of developing its own IP specifically for Chinese customers a few years ago. While the company does not develop high-performance general-purpose cores, its Zhouyi NPU could become a fundamental building block for affordable processors. A significant step forward is the upcoming addition of an open-source driver for Zhouyi to the Linux kernel. This will make the IP easy to program for software developers, increasing its appeal to chip designers.

Being an open-source driver, the integration in the Linux kernel brings assurance to developers that Zhouyi NPU could be the first in many generations from Arm China. While Zhouyi may not directly compete with offerings from AMD or Intel, its potential for widespread adoption in millions of devices could help Arm China acquire local customers with their IP. The project, which began three years ago with a kernel-only driver, has since evolved into a full driver stack. There is even a development kit board called EAIDK310, powered by Rockwell SoC and Zhouyi NPU, which is available on Aliexpress and Amazon. The integration of AI accelerator technology into the Linux ecosystem is a significant development, though there is still work to be done. Nonetheless, Arm China's Zhouyi NPU and open-source driver are essential to making AI capabilities more accessible and widely available in the domestic Chinese market.

Google has just released an Arm-optimized version of its popular Chrome browser for Windows PCs. This new version is designed to take full advantage of Arm-based devices' hardware and operating system, promising users a faster and smoother browsing experience. The Arm-optimized Chrome for Windows has been developed in close collaboration with Qualcomm, ensuring that Chrome users get the best possible experience on current Arm-compatible PCs. Hiroshi Lockheimer, Senior Vice President at Google, stated, "We've designed Chrome browser to be fast, secure, and easy to use across desktops and mobile devices, and we're always looking for ways to bring this experience to more people." Early testers of the Arm-optimized Chrome have reported significant performance improvements compared to the x86-emulated version. The new browser is rolling out starting today and will be available on existing Arm devices, including PCs powered by Snapdragon 8cx, 8c, and 7c processors.

Shortly, Chrome will receive an even more performant chip boost with Qualcomm's upcoming Snapdragon X Elite SoC launch. Cristiano Amon, President and CEO of Qualcomm, expressed his excitement about the collaboration, saying, "As we enter the era of the AI PC, we can't wait to see Chrome shine by taking advantage of the powerful Snapdragon X Elite system." Qualcomm's Snapdragon X Elite devices are expected to hit the market in mid-2024 with "dramatic performance improvement in the Speedometer 2.0 benchmark" on reference hardware. Being one of the most essential applications, getting a native Chrome build to run on Windows-on-Arm is a significant step for the platform, promising more investment from software makers.

Intel and Arm have signed a memorandum of understanding that finalizes the Emerging Business Initiative, their collaboration to support the startup community. The initiative builds on the April 2023 multi-generation agreement to enable chip designers to build low-power compute system-on-chips (SoCs) on the Intel 18A process. Together, the companies will provide essential intellectual property (IP) and manufacturing support, while also making financial assistance available, to foster innovation and growth for startups developing a range of devices and servers built on Arm-based SoCs and manufactured by Intel Foundry. The Emerging Business Initiative was announced last month at Intel Foundry Direct Connect in San Jose, California.

"Intel Foundry and Arm share the belief that for technology to benefit everyone, the building blocks of innovation must be available to anyone. Startups play a crucial role in bringing the great promise of transformations like AI to reality. The Emerging Business Initiative provides a path for new companies to leverage leading-edge Arm-based SoCs and Intel Foundry's global manufacturing capabilities to make their ideas real," said Stuart Pann, Intel senior vice president and general manager of Foundry Services.

Qualcomm's "Windows on Snapdragon, a Platform Ready for your PC Games" GDC presentation attracted a low number of attendees according to The Verge's Sean Hollister (senior editor). The semiconductor firm is readying its Snapdragon X Elite mobile chipset family for launch around mid-2024—prototypes and reference devices have been popping up lately. Leaked Samsung Galaxy Book 4 Edge specs suggest that Qualcomm's ARM-based solution is ready to take on Apple's M3 chipset series. Gaming is not a major priority for many owners of slimline notebooks, but Apple has made efforts to unleash some of its silicon's full potential in that area. Snapdragon Studios' GDC showcase outlined a promising future for their X Elite chips—according to Hollister's coverage of the GDC session, Qualcomm's principal engineer told "game developers (that) their titles should already work on a wave of upcoming Snapdragon-powered Windows laptops—no porting required."

Issam Khalil's presentation covered three different porting paths: x64 emulation, ARM64, and a hybrid approach (via an "ARM64EC" driver). He demonstrated tools that will be available for games developers to start enabling titles on Windows + Snapdragon platforms. The Snapdragon X Elite is capable of running x86/64 games at "close to full speed" via emulation, as claimed in presentation slides. Khalil posits that developers are not required to change the code or assets of their games to achieve full speed performance. Adreno GPU drivers have been prepped for DX11, DX12, Vulkan, and OpenCL—mapping layers were utilized to grant support for DX9 and OpenGL (up to v4.6). Specific titles were not highlighted as fully operational on Snapdragon X Elite-based devices, but the team has spent time combing through "top games" on Steam.

NVIDIA has been offering its GPU IP for more than a decade now ever since the introduction of Kepler uArch, and its IP has had relatively low traction in other SoCs. However, that trend seems to be reaching an inflection point as NVIDIA has given MediaTek a license to use its GPU IP to produce the next generation of processors for the auto industry. The newest MediaTek Dimensity Auto Cockpit family consists of CX-1, CY-1, CM-1, and CV-1, where the CX-1 targets premium vehicles, CM targets medium range, and CV targets lower-end vehicles, probably divided by their compute capabilities. The Dimensity Auto Cockpit family is brimming with the latest technology, as the processor core of choice is an Armv9-based design paired with "next-generation" NVIDIA GPU IP, possibly referring to Blackwell, capable of doing ray tracing and DLSS 3, powered by RTX and DLA.

The SoC is supposed to integrate a lot of technology to lower BOM costs of auto manufacturing, and it includes silicon for controlling displays, cameras (advanced HDR ISP), audio streams (multiple audio DSPs), and connectivity (WiFi networking). Interestingly, the SKUs can play movies with AI-enhanced video and support AAA gaming. MediaTek touts the Dimensity Auto Cockpit family with fully local AI processing capabilities, without requiring assistance from outside servers via WiFi, and 3D spatial sensing with driver and occupant monitoring, gaze-aware UI, and natural controls. All of that fits into an SoC fabricated at TSMC's fab on a 3 nm process and runs on the industry-established NVIDIA DRIVE OS.

ScaleFlux, a leader in deploying computational storage at scale, today announced its commitment to integrating the Arm Cortex -R82 processor in its forthcoming line of enterprise Solid State Drive (SSD) controllers. The Cortex-R82, is the highest performance real-time processor from Arm and the first to implement the 64-bit Armv8-R AArch64 architecture, representing a significant advancement in processing power and efficiency for enterprise storage solutions.

ScaleFlux's adoption of the Cortex-R82 is a strategic move to leverage the processor's high performance and energy efficiency. This collaboration underscores ScaleFlux's dedication to delivering cutting-edge technology in its SSD controllers, enhancing data processing capabilities and efficiency for data center and AI infrastructure worldwide.

Samsung and ARM announced a collaborative project last week—the partners are aiming to deliver an "optimized next generation Arm Cortex -X CPU" developed on the latest Gate-All-Around (GAA) process technology. Semiconductor industry watchdogs believe that Samsung Foundry's 3 nm GAA process did not meet sales expectations—reports suggest that many clients decided to pursue advanced three nanometer service options chez TSMC. The South Korean multinational manufacturing conglomerate is setting its sights forward—with an in-progress SF2 GAAFET process in the pipeline—industry insiders reckon that Samsung leadership is hoping to score a major victory within this next-gen market segment.

Lately, important industry figures have been hyping up Backside Power Supply Delivery Network (BSPDN) technology—recent Intel Foundry Services (IFS) press material lays claim to several technological innovations. A prime example being an ambitious five-nodes-in-four-years (5N4Y) process roadmap that: "remains on track and will deliver the industry's first backside power solution." A Chosun Business report proposes that Samsung is working on Backside Power Supply designs—a possible "game changer" when combined with in-house 2 nm SF2 GAAFET. Early experiments, allegedly, involving two unidentified ARM cores have exceeded expectations—according to Chosun's sources, engineers were able to: "reduce the chip area by 10% and 19%, respectively, and succeeded in improving chip performance and frequency efficiency to a single-digit level." Samsung Foundry could be adjusting its mass production timetables, based on freshly reported technological breakthroughs—SF2 GAAFET + BSPDN designs could arrive before the original targeted year of 2027. Prior to the latest developments, Samsung's BSPDN tech was linked to a futuristic 1.7 nm line.

Fibocom, a global leading provider of IoT (Internet of Things) wireless solutions and wireless communication modules, launches a new series of 5G RedCap module integrated with MediaTek's T300 5G modem, which is the world's first 6 nm radio frequency system-on-chip (RFSOC) single die solution for 5G RedCap. By integrating a single-core Arm Cortex-A3 processor in a significantly compact PCB area, the FM330 series are optimal solutions that offer extended coverage, increased network efficiency and device battery life for industry customers.

Compliant with 3GPP R17 standards, the FM330 series supports mainstream 5G frequency bands worldwide and is capable of reaching a maximum bandwidth of 20 MHz, thus ensuring the peak data rate of up to 227 Mbps downlink and 122 Mbps uplink, sufficient to meet the demand for 5G applications with less data throughput while balancing the power efficiency. In hardware design, it adopts the M.2form factor measured at 30x42mm benefiting from the unique RFSOC solution integrated with T300, in addition to the optimized antenna design in 1T2R, which significantly saves the PCB area. Moreover, FM330 series is pin-compatible with Fibocom LTE Cat 6 module FM101, easing the concerns for customers' migration from 4G to 5G. Furthermore, the module provides 64QAM/256QAM (optional) modulation scheme to greatly optimize the cost and size.

Apple's M-series chips frighten Intel, AMD, and Microsoft like nothing else can, as they have the potential to power MacBooks to grab a sizable share of the notebook market share. This is based squarely on the phenomenal performance/Watt on offer with Apple's chips. A user installed Windows 11 Arm on a virtual machine running on an M2-powered MacBook, opened up CPU-Z (which of course doesn't detect the chip since it's on a VM). They then ran a CPU-Z Bench session for a surprising result—a single-threaded score of 749.5 points, with a multithreaded score of 3822.3 points.

The single-thread score in particular is comparable to Intel's 12th Gen Core "Alder Lake" chips (their "Golden Cove" P-cores); maybe not on the fastest Core i9-12900K, but of the mid-range Core i5 chips, such as the i5-12600. It's able to do this at a fraction of the power and heat output. It is on the backs of this kind of IPC that Apple is building bigger chips such as the M3 Pro and M3 Max, which are able to provide HEDT or workstation-class performance, again, at a fraction of the power.

Qualcomm Snapdragon 8cx Gen 3 is a high performance Arm SoC designed to compete with Apple M3, with Windows 11 thin and light notebooks and Chromebooks being its main target devices. Microsoft pins a lot of hope in chips such as the Snapdragon 8cx series as they offer comparable performance and battery life to the current crop of M3 MacBooks. A lot of water has flown under the bridge since Windows RT, and the latest crop of Windows 11 for Arm has a much wider PC application support base thanks to official translation layers by Microsoft. CPUID has an Arm64 version of the popular CPU-Z utility, which correctly detects all the specs of the Snapdragon 8cx, but more importantly, has a Bench tab that can test the single- and multithreaded performance of the CPU.

A Chinese tech enthusiast wasted no time in putting the Snapdragon 8cx through this CPU-Z internal benchmark, and found surprisingly good performance numbers. The single-threaded bench, which loads one of chip's four Arm Cortex-X1C P-cores, registers a score of 543.7 points. This is roughly comparable to that of the AMD "Zen 2" or Intel "Comet Lake" x86-64 core. The multithreaded test, which saturates all four P-cores, and all four Cortex-A78C E-cores, springs up 3479.7 points, which again compares to entry/mainstream x86-64 processors from AMD or Intel. Not impressed? How about the fact that the Snapdragon 8cx Gen 3 is a 7 W chip that idles under 2 W for the most part, and can make do with passive cooling, posting scores comparable to 35 W x86 chips that need active cooling?

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.

ARM's in-progress fifth generation "Blackhawk" Cortex design is allegedly going through a troubled phase of development, according to Chinese insider sources. A Revegnus (@Tech_Reve) social media post highlights ongoing issues: "It's reported that the Cortex X5 architecture is underperforming compared to expectations. It's speculated that the high-frequency power consumption has surged explosively. Therefore, if performance is reduced for lower power consumption, the Geekbench 6 multi-core score of Dimensity 9400 may not achieve a score of 9,400 points." A recent Moor Insights & Strategy analysis piece proposed that "Blackhawk" would become "the most powerful option available at launch" later this year—mobile chipsets leveraging ARM's Cortex-X5 design are touted to face tough next-gen competition from Qualcomm and Apple corners.

Revegnus pulled in a rival SoC: "While Snapdragon 8 Gen 4 is seen to have minor issues, there is no evidence to support this claim. There might be a problem with low-frequency power consumption not showing clear superiority over ARM's middle cores." Qualcomm's next flagship model is performing admirably according to insiders—an engineering sample managed to score 10,628 points in alleged Geekbench 6 multi-core gauntlets. Late last month prototype clocks were leaked—Digital Chat Station claimed that a Snapdragon 8 Gen 4 High-Performance "Big" core was capable of reaching 4.0 GHz. Prior to the latest news, MediaTek's Dimensity 9400 SoC was observed achieving ~10,000 multi-core Geekbench 6 scores—leaked CPU cluster details present a single "Big" Cortex-X5 unit operating alongside three Cortex-X4 cores.

Samsung Electronics Co., Ltd., a world leader in advanced semiconductor technology, today announced a collaboration to deliver optimized next generation Arm Cortex -X CPU developed on Samsung Foundry's latest Gate-All-Around (GAA) process technology. This initiative is built on years of partnership with millions of devices shipped with Arm CPU intellectual property (IP) on various process nodes offered by Samsung Foundry.

This collaboration sets the stage for a series of announcements and planned innovation between Samsung and Arm. The companies have bold plans to reinvent 2-nanometer (nm) GAA for next-generation data center and infrastructure custom silicon, and a groundbreaking AI chiplet solution that will revolutionize the future generative artificial intelligence (AI) mobile computing market.

NVIDIA today announced that Australia's Pawsey Supercomputing Research Centre will add the NVIDIA CUDA Quantum platform accelerated by NVIDIA Grace Hopper Superchips to its National Supercomputing and Quantum Computing Innovation Hub, furthering its work driving breakthroughs in quantum computing.

Researchers at the Perth-based center will leverage CUDA Quantum - an open-source hybrid quantum computing platform that features powerful simulation tools, and capabilities to program hybrid CPU, GPU and QPU systems - as well as, the NVIDIA cuQuantum software development kit of optimized libraries and tools for accelerating quantum computing workflows. The NVIDIA Grace Hopper Superchip - which combines the NVIDIA Grace CPU and Hopper GPU architectures - provides extreme performance to run high-fidelity and scalable quantum simulations on accelerators and seamlessly interface with future quantum hardware infrastructure.

Japanese tech billionaire and founder of the SoftBank Group, Masayoshi Son, is embarking on a hugely ambitious new project to build an AI chip company that aims to rival NVIDIA, the current leader in AI semiconductor solutions. Codenamed "Izanagi" after the Japanese god of creation, Son aims to raise up to $100 billion in funding for the new venture. With his company SoftBank having recently scaled back investments in startups, Son is now setting his sights on the red-hot AI chip sector. Izanagi would leverage SoftBank's existing chip design firm, Arm, to develop advanced semiconductors tailored for artificial intelligence computing. The startup would use Arm's instruction set for the chip's processing elements. This could pit Izanagi directly against NVIDIA's leadership position in AI chips. Son has a chest of $41 billion in cash at SoftBank that he can deploy for Izanagi.

Additionally, he is courting sovereign wealth funds in the Middle East to contribute up to $70 billion in additional capital. In total, Son may be seeking up to $100 billion to bankroll Izanagi into a chip powerhouse. AI chips are seeing surging demand as machine learning and neural networks require specialized semiconductors that can process massive datasets. NVIDIA and other names like Intel, AMD, and select startups have capitalized on this trend. However, Son believes the market has room for another major player. Izanagi would focus squarely on developing bleeding-edge AI chip architectures to power the next generation of artificial intelligence applications. It is still unclear if this would be an AI training or AI inference project, but given that the training market is currently bigger as we are in the early buildout phase of AI infrastructure, the consensus might settle on training. With his track record of bold bets, Son is aiming very high with Izanagi. It's a hugely ambitious goal, but Son has defied expectations before. Project Izanagi will test the limits of even his vision and financial firepower.

Faraday Technology Corporation, a Taiwanese silicon IP designer, has announced plans to develop a new 64-core system-on-chip (SoC) utilizing Intel's most advanced 18A process technology. The Arm-based SoC will integrate Arm Neoverse compute subsystems (CSS) to deliver high performance and efficiency for data centers, infrastructure edge, and 5G networks. This collaboration brings together Faraday, Arm, and Intel Foundry Services. Faraday will leverage its ASIC design and IP solutions expertise to build the SoC. Arm will provide the Neoverse compute subsystem IP to enable scalable computing. Intel Foundry Services will manufacture the chip using its cutting-edge 18A process, which delivers one of the best-in-class transistor performance.

The new 64-core SoC will be a key component of Faraday's upcoming SoC evaluation platform. This platform aims to accelerate customer development of data center servers, high-performance computing ASICs, and custom SoCs. The platform will also incorporate interface IPs from the Arm Total Design ecosystem for complete implementation and verification. Both Arm and Intel Foundry Services expressed excitement about working with Faraday on this advanced Arm-based custom silicon project. "We're thrilled to see industry leaders like Faraday and Intel on the cutting edge of Arm-based custom silicon development," said an Arm spokesperson. Intel SVP Stuart Pann said, "We are pleased to work with Faraday in the development of the SoC based on Arm Neoverse CSS utilizing our most competitive Intel 18A process technology." The collaboration represents Faraday's strategic focus on leading-edge technologies to meet evolving application requirements. With its extensive silicon IP portfolio and design capabilities, Faraday wants to deliver innovative solutions and break into next-generation computing design.

MediaTek revealed its (now current generation) flagship Dimensity 9300 flagship mobile processor last November, but we are already hearing about its successor's foundation. Digital Chat Station published some early insights on their Weibo micro-blog—the tipster appears to have an inside track at MediaTek's system-on-chip R&D department. The imaginatively named "Dimensity 9400" chipset is reportedly earmarked for mass production chez TSMC, with the foundry's second generation 3 Nm process being the favored node—this information aligns with official announcements as well as industry rumors from last autumn. MediaTek's Dimensity 9300 sports a "one-of-a-kind All Big Core design," with no provision for puny efficiency units—built on TSMC's third generation 4 nm process with four ARM Cortex-X4 cores (going up to 3.25 GHz) and four Cortex-A720 cores (maximum 2.0 GHz).

Digital Chat Station reckons that the 9300's All Big Core configuration will carryover to its next generation sibling, albeit with some major upgrades. MediaTek hardware engineers are alleged to have selected ARM's latest and greatest CPU and Mali GPU designs—the Cortex-X5 core could be a prime candidate in the first category. The rumor mill has the next batch of flagship Exynos SoCs utilizing ARM's fifth generation design. Digital Chat Station proposes that more smartphone manufacturers could adopt a top-flight Dimensity 2024 chip, if its performance can match the closest rivals. Industry experts posit both MediaTek and Qualcomm choosing TSMC's N3E process for their upcoming flagship chipsets—this node apparently "offers improved cost-effectiveness and superior yields" when compared to the first generation N3B process (as ordered by Apple for its latest M and B-series SoCs). Dimensity 9400 is expected to take on Snapdragon 8 Gen 4—this could be a tough fight, given that Qualcomm's offering is set to debut with custom Oryon cores.

Last week Patrick Moorhead, CEO and founder of Moor Insights & Strategy, shared his insider sourced thoughts about ARM's next generation Cortex-X processor: "Blackhawk is planned to enable in smartphones shipping at the end of 2024. I think phones could be on the shelf a year from now at CES or maybe MWC." Moorhead believes that Cortex-X4's successor will be the most powerful option available at launch, which forms part of (ARM CEO) Rene Haas's strategy to "eliminate the performance gap between ARM-designed processors and custom ARM implementations." He believes that "this is a big and bold claim," since Apple is widely considered to rule the roost here with its cutting edge ARM-based Bionic designs. Moorhead's inside information has "Blackhawk" demonstrating the "largest year-over-year IPC performance increase in 5 years" citing undisclosed Geekbench 6 results.

He also presented evidence that the artificial intelligence processing is a key focus: "I am hopeful these performance goals translate to app performance as well. ARM also believes that Blackhawk will provide "great" LLM performance. I will assume that this has to do with big CPU IPC performance improvements as ARM says that its Cortex CPU is the #1 AI target for developers...The NPU and GPU can be an efficient way to run AI, but a CPU is the easiest and most pervasive way, which is why developers target it. A higher-performing CPU obviously helps here, but as the world moves increasingly to smaller language models, Arm's platform with higher-performing CPU and GPU combined with its tightly integrated ML libraries and frameworks will likely result in a more efficient experience on devices."

New York-based security firm Trail of Bits has identified a security vulnerability with various GPU models, which include AMD, Qualcomm, and Apple. This vulnerability, named LeftoverLocals, could potentially allow attackers to steal large amounts of data from a GPU's memory. Mainstream client-GPUs form a sizable chunk of the hardware accelerating AI and LLMs, as they cost a fraction of purpose-built data-center GPUs, and are available in the retail market. Unlike CPUs, which have undergone extensive hardening against data leaks, GPUs were primarily designed for graphics acceleration and lack similar data privacy architecture. To our knowledge, none of the client GPUs use virtualization with their graphics memory. Graphics acceleration in general is a very memory sensitive application, and requires SIMD units to have bare-metal access to memory, with as little latency as possible.

First the good news—for this vulnerability to be exploited, it requires the attacker to have access to the target device with the vulnerable GPU (i.e. cut through OS-level security). The attack could break down data silos on modern computers and servers, allowing unauthorized access to GPU memory. The potential data breach could include queries, responses generated by LLMs, and the weights driving the response. The researchers tested 11 chips from seven GPU makers and found the vulnerability in GPUs from Apple, AMD, and Qualcomm. While NVIDIA, Intel, and Arm first-party GPUs did not show evidence of the vulnerability, Apple, Qualcomm, and AMD confirmed to wired that their GPUs are affected, and that they're working on a security response. Apple has released fixes for its latest M3 and A17 processors, but older devices with previous generations of Apple silicon remain vulnerable. Qualcomm is providing security updates, and AMD plans to offer mitigations through driver updates in March 2024.