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.

Marvell Technology, a leader in data infrastructure semiconductor solutions, is enabling networking equipment and firewall manufacturers achieve breakthrough levels of performance and efficiency with two new OCTEON 10 data processing units (DPUs), the OCTEON 10 CN102 and OCTEON 10 CN103. The 5 nm OCTEON CN102 and CN103, broadly available to OEMs for product design and pilot production, are optimized for data and control plane applications in routers, firewalls, 5G small cells, SD-WAN appliances, and control plane applications in top-of-rack switches and line card controllers. Several of the world's largest networking equipment manufacturers have already incorporated the OCTEON 10 CN102 into a number of product designs.

Containing up to eight Arm Neoverse N2 cores, OCTEON 10 CN102 and CN103 deliver 3x the performance of Marvell current DPU solutions for devices while reducing power consumption by 50% to 25 W. Achieving SPEC CPU (2017) integer rate (SPECint) scores of 36.5, OCTEON 10 CN102 and CN103 are able to deliver nearly 1.5 SPECint points per Watt. The chips can serve as an offload DPU for host processors or as the primary processor in devices; advanced performance per watt also enables OEMs to design fanless systems to simplify systems and further reduce cost, maintenance and power consumption.

Today, at VMware Explore 2023 Las Vegas, AMD continued to showcase its proven performance and growing adoption of AMD EPYC CPUs, AMD Pensando data processing units (DPUs) and adaptive computing products as ideal solutions for the most efficient and innovative virtualized environments. For instance, a system powered by a 4th Gen AMD EPYC 9654 CPUs and a Pensando DPU, delivers approximately 3.3x the Redis application performance and 1.75x the aggregate network throughput when compared to a 4th Gen EPYC system with standard NICs. Additionally, servers with 2P 4th Gen EPYC 9654 CPUs alone can enable using up to 35% fewer servers in an environment running 2000 virtual machines (VMs) compared to 2P Intel Xeon 8490H based servers.

"AMD is helping enterprise customers fully realize the benefits of their virtualized data centers with the latest generation EPYC CPUs and Pensando DPUs," said Forrest Norrod, executive vice president and general manager, Data Center Solutions Business Group, AMD. "Consolidation and modernization enable businesses to increase server utilization and efficiency while delivering impressive performance for critical enterprise workloads. Our ongoing collaboration with VMware enables customers to get more efficient and agile to reach their digital transformation goals."

A watershed moment on Nov. 22, 2022, was mostly virtual, yet it shook the foundations of nearly every industry on the planet. On that day, OpenAI released ChatGPT, the most advanced artificial intelligence chatbot ever developed. This set off demand for generative AI applications that help businesses become more efficient, from providing consumers with answers to their questions to accelerating the work of researchers as they seek scientific breakthroughs, and much, much more.

Businesses that previously dabbled in AI are now rushing to adopt and deploy the latest applications. Generative AI—the ability of algorithms to create new text, images, sounds, animations, 3D models and even computer code—is moving at warp speed, transforming the way people work and play. By employing large language models (LLMs) to handle queries, the technology can dramatically reduce the time people devote to manual tasks like searching for and compiling information.

GIGABYTE Technology, an industry leader in high-performance servers and workstations, today announced participation in the global AI conference, NVIDIA GTC, and will share an AI session and other resources to educate attendees. Additionally, with the release of the NVIDIA L4 Tensor Core GPU, GIGABYTE has already begun qualifying its G-series servers to support it with validation. Last, as the NVIDIA OVX architecture has reached a new milestone, GIGABYTE has begun production of purpose-built GIGABYTE servers based on the OVX 3.0 architecture to handle the performance and scale needed for real-time, physically accurate simulations, expansive 3D worlds, and complex digital twins.

NVIDIA Session (S52463) "Protect and Optimize AI Models on Development Platform"
GTC is a great opportunity for researchers and industries to share what they have learned in AI to help further discoveries. This time around, GIGABYTE has a talk by one of MyelinTek's senior engineers that is responsible for the research and development of MLOps technologies. The session demonstrates an AI solution using a pipeline function to quickly retrain new AI models and encrypt them.

ASUS today announced its participation in NVIDIA GTC, a developer conference for the era of AI and the metaverse. ASUS will offer comprehensive NVIDIA-certified server solutions that support the latest NVIDIA L4 Tensor Core GPU—which accelerates real-time video AI and generative AI—as well as the NVIDIA BlueField -3 DPU, igniting unprecedented innovation for supercomputing infrastructure. ASUS will also launch the new ProArt Studiobook Pro 16 OLED laptop with the NVIDIA RTX 3000 Ada Generation Laptop GPU for mobile creative professionals.

Purpose-built GPU servers for generative AI
Generative AI applications enable businesses to develop better products and services, and deliver original content tailored to the unique needs of customers and audiences. ASUS ESC8000 and ESC4000 are fully certified NVIDIA servers that support up to eight NVIDIA L4 Tensor Core GPUs, which deliver universal acceleration and energy efficiency for AI with up to 2.7X more generative AI performance than the previous GPU generation. ASUS ESC and RS series servers are engineered for HPC workloads, with support for the NVIDIA Bluefield-3 DPU to transform data center infrastructure, as well as NVIDIA AI Enterprise applications for streamlined AI workflows and deployment.

Today, Microsoft is announcing the acquisition of Fungible Inc., a provider of composable infrastructure aimed at accelerating networking and storage performance in datacenters with high-efficiency, low-power data processing units (DPUs). Fungible's technologies help enable high-performance, scalable, disaggregated, scaled-out datacenter infrastructure with reliability and security.

The Fungible team will join Microsoft's datacenter infrastructure engineering teams and will focus on delivering multiple DPU solutions, network innovation and hardware systems advancements.

BBT.live, the Tel Aviv-based startup that has developed an all-in-one, tech-agnostic, software-defined connectivity solution, has announced a new technology innovation powered by NVIDIA. As a result, BBT.live, the software-defined connectivity platform, will run on NVIDIA BlueField data processing units (DPUs) to unlock the benefits of cloud-based connectivity solutions to businesses at every scale.

Modern workloads are experiencing an ever-growing need for network efficiency, privacy, and security. Businesses and enterprises that depend on solutions require additional hardware and integration, which introduces additional complexity and points of failure. BBT.live's proprietary technology, recognized by the Israel Innovation Authority, is device agnostic. It integrates with a variety of different hardware platforms (uCPE) without the need for time-consuming customization.

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, at the 2022 Super Computing Conference is unveiling the most extensive portfolio of servers and storage systems in the industry based on the upcoming 4th Gen Intel Xeon Scalable processor, formerly codenamed Sapphire Rapids. Supermicro continues to use its Building Block Solutions approach to deliver state-of-the-art and secure systems for the most demanding AI, Cloud, and 5G Edge requirements. The systems support high-performance CPUs and DDR5 memory with up to 2X the performance and capacities up to 512 GB DIMMs and PCIe 5.0, which doubles I/O bandwidth. Intel Xeon CPU Max Series CPUs (formerly codenamed Sapphire Rapids HBM High Bandwidth Memory (HBM)) is also available on a range of Supermicro X13 systems. In addition, support for high ambient temperature environments at up to 40° C (104° F), with servers designed for air and liquid cooling for optimal efficiency, are rack-scale optimized with open industry standard designs and improved security and manageability.

"Supermicro is once again at the forefront of delivering the broadest portfolio of systems based on the latest technology from Intel," stated Charles Liang, president and CEO of Supermicro. "Our Total IT Solutions strategy enables us to deliver a complete solution to our customers, which includes hardware, software, rack-scale testing, and liquid cooling. Our innovative platform design and architecture bring the best from the 4th Gen Intel Xeon Scalable processors, delivering maximum performance, configurability, and power savings to tackle the growing demand for performance and energy efficiency. The systems are rack-scale optimized with Supermicro's significant growth of rack-scale manufacturing of up to 3X rack capacity."

AMD announced that the AMD Pensando Distributed Services Card, powered by the industry's most advanced data processing unit (DPU)1, will be one of the first DPU solutions to support VMware vSphere 8 available from leading server vendors including Dell Technologies, HPE and Lenovo.

As data center applications grow in scale and sophistication, the resulting workloads increase the demand on infrastructure services as well as crucial CPU resources. VMware vSphere 8 aims to reimagine IT infrastructure as a composable architecture with a goal of offloading infrastructure workloads such as networking, storage, and security from the CPU by leveraging the new vSphere Distributed Services Engine, freeing up valuable CPU cycles to be used for business functions and revenue generating applications.

MaxLinear Inc. today announced the availability of Panther III, the latest in the company's Panther series of storage accelerators. The company is showcasing this product at the Flash Memory Summit in Santa Clara, CA, August 2 - 4. Booth 111. Businesses need immediate access to larger and larger amounts of data and, at the same time, are faced with security and CAPEX costs challenges. With its 16 nanometer (nm) DPU architecture, Panther III provides breakthrough data reduction, encryption, deduplication, and data protection and sets a new standard in storage acceleration with a high throughput of 200 Gbps and ultra-low single-pass transformation latency.

Panther III opens new opportunities within the storage market, including all-flash-array and non-volatile memory express (NVMe) systems. As with previous generations of Panther products, Panther III offers powerful data reduction technology that intelligently offloads the CPU to open all tiers of storage to their full bandwidth potential with no CPU or software limitations. These capabilities enable intelligent and faster dataset delivery, high-performance analytics, and improved workload accuracy in fast-growing Edge to disaggregated computing of the public cloud.

L7 Defense Ltd., a pioneering developer of AI-based cybersecurity solutions, announced today that it has successfully completed the integration of its API security solution Ammune with the NVIDIA BlueField-2 SmartNIC. The integration elevates the Kubernetes nodes' security posture with maximum "zero trust" in-and-out traffic protection. Furthermore, it does not interfere with the day-to-day efficiency of serving applications. Installed on BlueField-2, the Ammune real-time AI workload is offloaded to the BlueField-2 DPU, reducing nodes' CPU usage for security to the essential minimum.

"Thanks to the successful integration, the server CPU utilization with the BlueField DPU was reduced by almost a factor of 8 in cases of high traffic analysis, in comparison to CPU utilization without the DPU," said Dr. Doron Chema, L7 Defense's CEO. "Ammune is a pure AI product. The real-time AI security agent is going to be further accelerated by more BlueField functionality. The Ammune analytical near-real-time AI unit will gain more acceleration with the NVIDIA Morpheus cybersecurity AI application framework in the near future."

Fungible, Inc., the composable infrastructure company, today announced a new product offering, Fungible GPU-Connect (FGC ), an innovative solution engineered to revolutionize how data processing power is accessed in enterprise and service provider infrastructures. Fungible GPU-Connect solves the challenges caused by the growing demand for AI/ML, especially in Edge Data Centers with stranded and underutilized GPUs. FGC leverages the Fungible DPU to dynamically compose GPU and CPU resources across an Ethernet network. This provides significant economic benefits and agility to organizations that provision, allocate, and manage expensive GPU resources. For the first time, organizations can create a GPU-powered infrastructure free from the physical limitations of PCIe.

FGC allows data centers to centralize their existing GPU assets into a single resource pool to be attached to servers on demand. Instead of dedicated GPUs sitting idle most of the time, data centers can provide new users with access to the GPU pool, making greater use of existing assets. This disaggregated solution also removes the constraints of having GPUs and CPUs physically co-located. They can be located anywhere within the same data center, eliminating the stranding of expensive GPU resources. The Fungible DPU creates a secure, virtual PCIe connection between the GPU and the server that is transparent to the server and to applications - no special software or drivers are needed. This connection is managed in hardware by the DPU, ensuring a high-performance and low latency connection. This transparency means FGC can be easily retrofitted into existing environments, and can scale with growing demand, ensuring GPUs are always available when they are needed.

Excelero, a Tel Aviv-based provider of high-performance software-defined storage, is now a part of NVIDIA. The company's team of engineers—including its seasoned co-founders with decades of experience in HPC, storage and networking—bring deep expertise in the block storage that large businesses use in storage-area networks.

Now their mission is to help expand support for block storage in our enterprise software stack such as clusters for high performance computing. Block storage also has an important role to play inside the DOCA software framework that runs on our DPUs.

The Federal Trade Commission today sued to block U.S. chip supplier Nvidia Corp.'s $40 billion acquisition of U.K. chip design provider Arm Ltd. Semiconductor chips power the computers and technologies that are essential to our modern economy and society. The proposed vertical deal would give one of the largest chip companies control over the computing technology and designs that rival firms rely on to develop their own competing chips. The FTC's complaint alleges that the combined firm would have the means and incentive to stifle innovative next-generation technologies, including those used to run datacenters and driver-assistance systems in cars.

"The FTC is suing to block the largest semiconductor chip merger in history to prevent a chip conglomerate from stifling the innovation pipeline for next-generation technologies," said FTC Bureau of Competition Director Holly Vedova. "Tomorrow's technologies depend on preserving today's competitive, cutting-edge chip markets. This proposed deal would distort Arm's incentives in chip markets and allow the combined firm to unfairly undermine Nvidia's rivals. The FTC's lawsuit should send a strong signal that we will act aggressively to protect our critical infrastructure markets from illegal vertical mergers that have far-reaching and damaging effects on future innovations."

NVIDIA today reported record revenue for the third quarter ended October 31, 2021, of $7.10 billion, up 50 percent from a year earlier and up 9 percent from the previous quarter, with record revenue from the company's Gaming, Data Center and Professional Visualization market platforms. GAAP earnings per diluted share for the quarter were $0.97, up 83 percent from a year ago and up 3 percent from the previous quarter. Non-GAAP earnings per diluted share were $1.17, up 60 percent from a year ago and up 13 percent from the previous quarter.

"The third quarter was outstanding, with record revenue," said Jensen Huang, founder and CEO of NVIDIA. "Demand for NVIDIA AI is surging, driven by hyperscale and cloud scale-out, and broadening adoption by more than 25,000 companies. NVIDIA RTX has reinvented computer graphics with ray tracing and AI, and is the ideal upgrade for the large, growing market of gamers and creators, as well as designers and professionals building home workstations.

NVIDIA today announced NVIDIA Quantum-2, the next generation of its InfiniBand networking platform, which offers the extreme performance, broad accessibility and strong security needed by cloud computing providers and supercomputing centers.

The most advanced end-to-end networking platform ever built, NVIDIA Quantum-2 is a 400 Gbps InfiniBand networking platform that consists of the NVIDIA Quantum-2 switch, the ConnectX-7 network adapter, the BlueField-3 data processing unit (DPU) and all the software that supports the new architecture.

Marvell today announced the expansion of its industry-leading 5 nm data infrastructure platform with the launch of the industry's first 5 nm 50G PAM4 device for the carrier market, the Prestera DX 7321 Ethernet switch. The new switch builds on the success of the Prestera carrier-optimized portfolio and is ideal for 5G fronthaul and edge connectivity. In concert with this, Marvell's 5 nm OCTEON 10 DPU family, incorporating industry-leading hardware accelerators, is now sampling. By utilizing the industry's leading advanced process geometry, the Marvell Prestera switch and OCTEON DPU deliver 50% lower power than existing offerings, enabling new infrastructure solutions for next-generation carrier edge networks and RAN deployment models.

With the addition of the 5 nm Prestera device, the expanded carrier-optimized switch portfolio now comprises four cutting-edge Ethernet switches that scale port speeds from 1 Gbps to 400 Gbps with aggregate bandwidths ranging from 200 Gbps to 1.6 Tbps. The newest offering enhances Marvell's 5G solutions for Open RAN, vRAN and traditional RAN architectures, with Class D precision time protocol (PTP), which provides more timing headroom to enable larger cell coverage radius. The switch device incorporates integrated MACsec security and advanced telemetry to facilitate network visibility and automation.

NVIDIA (NASDAQ: NVDA) today reported record revenue for the second quarter ended August 1, 2021, of $6.51 billion, up 68 percent from a year earlier and up 15 percent from the previous quarter, with record revenue from the company's Gaming, Data Center and Professional Visualization platforms. GAAP earnings per diluted share for the quarter were $0.94, up 276 percent from a year ago and up 24 percent from the previous quarter. Non-GAAP earnings per diluted share were $1.04, up 89 percent from a year ago and up 14 percent from the previous quarter.

"NVIDIA's pioneering work in accelerated computing continues to advance graphics, scientific computing and AI," said Jensen Huang, founder and CEO of NVIDIA. "Enabled by the NVIDIA platform, developers are creating the most impactful technologies of our time - from natural language understanding and recommender systems, to autonomous vehicles and logistic centers, to digital biology and climate science, to metaverse worlds that obey the laws of physics.

NVIDIA today announced the NVIDIA BlueField -3 DPU, its next-generation data processing unit, to deliver the most powerful software-defined networking, storage and cybersecurity acceleration capabilities available for data centers.

The first DPU built for AI and accelerated computing, BlueField-3 lets every enterprise deliver applications at any scale with industry-leading performance and data center security. It is optimized for multi-tenant, cloud-native environments, offering software-defined, hardware-accelerated networking, storage, security and management services at data-center scale.