Intel's Xeon Sapphire Rapids CPU series has had a bumpy ride so far, with the discovery of bugs resulting in delays pushing proceedings back by more than two years. Units have been shipping out for the past couple of months, but Team Blue ran into more issues in late June—a subset of fourth Generation Intel Xeon Medium Core Count Processors (SPR-MCC) could interrupt normal system operation under certain conditions. Intel confirmed to Tom's Hardware that they were actively investigating the latest bugs, and had paused shipment of affected MCC die-based models (featuring up to 32 cores).

The publication has very recently received an update from their contact at Intel. A company spokesperson stated: "Last week, we informed you (Tom's Hardware) of an issue on a subset of 4th Generation Intel Xeon Medium Core Count Processors (SPR-MCC) that could interrupt system operation under certain conditions. Out of an abundance of caution, we temporarily paused some SPR-MCC shipments while we thoroughly evaluated a firmware mitigation. We are now confident the firmware mitigation addresses the issue. We have resumed shipping all versions of SPR-MCC and are working with customers to deploy the firmware as needed." Specifics about the latest mitigations efforts have not been divulged, but Intel is confident that these fixes will not impact processor performance.

Another next-gen Intel Xeon processor has been leaked by momomo_us via Twitter—the subject of the photograph appears to be a Granite Rapids-SP, alongside a new socket type; LGA 4710. These should not be confused with the recent appearance of a Granite Rapids-AP CPU plus LGA 7529 socket. The latest photo showcases two Intel CPUs with new integrated heat spreader (IHS) designs, both housed in carrier frames labeled "LGA 4710-2." The unit on the left seems to be similar in appearance to current-gen Sapphire Rapids-SP units, but the Xeon sitting on the right is getting most of the attention.

YuuKi_AnS (the leaker of last week's larger GNR-AP) pointed out that the smaller socket type is for a platform codenamed "Beechnut City," that is alleged to support Xeon GNR-SP CPUs. They provided a presentation slide of Intel's Beechnut City Main Validation Vehicle (MVV)—this mainboard appears to sport a dual-socket (2S) setup that can house Granite Rapids-SP Xeon CPUs (compatible with the LGA 4710-2 standard) with a maximum 350 W TDP. The spec sheet indicates that the board can support 8-channel DDR5 memory across 32 DIMM slots (DDR5-6400 1DPC / DDR5-5200 2DPC), as well as 88 PCIe Gen 5.0 lanes. The sixth generation Granite Rapids-SP & AP CPUs (based on "Intel 3" process node) are expected to launch in 2H 2024—following the Sierra Forest lineup.

Intel's Xeon Sapphire Rapids processors have been coated with numerous delays, and today, we learn that the company is stopping shipment of certain SKUs, mostly driven by the discovery of a new bug. After plenty of delays, Sapphire Rapids has been shipping for a few months now. However, SemiAnalysis's Chief Analyst, Dylan Patel, tipped Tom's Hardware that certain SKUs haven't been shipping since June. What this translates into is the additional delays to the 4th generation Xeon Scalable line, which was already in a difficult position. Some estimates claimed that it did 12 steppings, meaning that it took 11 times to perfect the silicon for the mass production run. The impacted CPUs are models with up to 32 cores, based on MCC die. These SKUs represent a huge amount of the total Xeon volume.

Intel's spokesperson published the following statement for Tom's Hardware: "We became aware of an issue on a subset of 4th Generation Intel Xeon Medium Core Count Processors (SPR-MCC) that could interrupt system operation under certain conditions and are actively investigating. This issue was not observed when running commercially available software, and other 4th Generation Intel Xeon processor SKUs (i.e., XCC and HBM) have not exhibited the issue. Out of an abundance of caution, we did temporarily pause some SPR MCC shipments while we gained confidence in the expected firmware mitigation and expect to release remaining shipments shortly."

Today, MLCommons published results of its industry AI performance benchmark, MLPerf Training 3.0, in which both the Habana Gaudi2 deep learning accelerator and the 4th Gen Intel Xeon Scalable processor delivered impressive training results.

"The latest MLPerf results published by MLCommons validates the TCO value Intel Xeon processors and Intel Gaudi deep learning accelerators provide to customers in the area of AI. Xeon's built-in accelerators make it an ideal solution to run volume AI workloads on general-purpose processors, while Gaudi delivers competitive performance for large language models and generative AI. Intel's scalable systems with optimized, easy-to-program open software lowers the barrier for customers and partners to deploy a broad array of AI-based solutions in the data center from the cloud to the intelligent edge." - Sandra Rivera, Intel executive vice president and general manager of the Data Center and AI Group

Intel's Birch Stream-AP socket will provide an LGA7529 socket with as many as 7529 pins to power the next generation of CPUs. Today, thanks to Yuuki_Ans on Twitter, we have another set of pictures that highlight the massive scale that these processors offer. We got similar pictures in the past; however, these are more representative of how big the next-generation Xeon processors are. In 2024, Intel plans to split its Xeon lineup into E-core and P-core powered models. However, both CPUs will utilize the same platform to reduce the overall ecosystem's complexity. Thanks to the new pictures, we can see the processor with its heatsink present, with labeling indicating an engineering sample based on little info printed on the metal surface.

Below are the pictures of the Granite Rapids-AP and the LGA7529 socket, along with the specification table. The third image shows current generation Xeon Platinum processor in the LGA7529 socket.

Intel Labs, in collaboration with Blockade Labs, has introduced Latent Diffusion Model for 3D (LDM3D), a novel diffusion model that uses generative AI to create realistic 3D visual content. LDM3D is the industry's first model to generate a depth map using the diffusion process to create 3D images with 360-degree views that are vivid and immersive. LDM3D has the potential to revolutionize content creation, metaverse applications and digital experiences, transforming a wide range of industries, from entertainment and gaming to architecture and design.

"Generative AI technology aims to further augment and enhance human creativity and save time. However, most of today's generative AI models are limited to generating 2D images and only very few can generate 3D images from text prompts. Unlike existing latent stable diffusion models, LDM3D allows users to generate an image and a depth map from a given text prompt using almost the same number of parameters. It provides more accurate relative depth for each pixel in an image compared to standard post-processing methods for depth estimation and saves developers significant time to develop scenes," said Vasudev Lal, AI/ML research scientist, Intel Labs.

Tech tipster momomo_us yesterday spotted that ASRock Rack had listed a new and interesting looking motherboard on its product website, albeit in a "preliminary" category—so pricing and availability have "to be determined" status currently. The W790D8UD-1L1N2T/BCM is a new addition to the company's selection of compact workstation boards, but it distinguishes itself by being the first example of a W790 chipset Deep Micro ATX mainboard with platform support for Intel's latest "Sapphire Rapids" Xeon W-2400 and W-3400 processors. The single E-type socket (LGA 4677) looks absolutely huge relative to the overall dimensions of its surroundings (264 × 266 mm). The Deep Micro ATX form factor is exclusive to AsRock Rack so it could be tricky to build with a W790D8UD-1L1N2T/BCM board, given that mainstream PC cases may not provide full compatibility with this proprietary configuration.

ASRock Rack W790D8UD-1L1N2T/BCM is capable of running up to 56 cores (the minimum being 6) and 2 TB of DDR5-4800 modules (eight DIMM slots) with a peak bandwidth of 307.2 GB/s, via the platform's advanced memory subsystem. Sapphire Rapids Xeon W processors can control up to 112 PCIe Gen 5 lanes (W-3400) and 64 PCIe Gen 5 lanes (W-2400). Tom's Hardware has kindly collated the rest of the specifications into sentence form: "As for the physical connectivity, the motherboard is equipped with four PCIe x16 slots, one M.2-2280 slot with a PCIe 4.0 x4 interface attached to the W790 PCH, and two OCuLink connectors for SSDs. Network connectivity includes two 10GbE ports controlled by Broadcom BCM57416, a GbE connector managed by the Intel I226, and another GbE handled by the Intel I210. In addition, it has a dedicated GbE port for remote management with the support of Aspeed AST2600 BMC, that is handled by the Realtek RTL8211F. The board also has an SPI connector for TPM modules, USB 3.2 Gen 1 ports, a COM port, and a D-Sub VGA display connector."

With the launch of 4th Gen Intel Xeon Scalable processors in January 2023, Intel delivered significant advancements in performance with industry-leading Intel accelerator engines and improved performance per watt across key workloads like AI, data analytics, high performance computing (HPC) and others. The industry has taken notice: 4th Gen Xeon has seen a rapid ramp, global customer adoption and leadership performance on a myriad of critical workloads for a broad range of business use cases.

Today, after weeks of rigorous and comprehensive head-to-head testing against the most comparable competitive processors, Intel is sharing compelling results that go far beyond simple industry benchmarks.

ASUS today announced ESC N8-E11, its most advanced HGX H100 eight-GPU AI server, along with a comprehensive PCI Express (PCIe) GPU server portfolio—the ESC8000 and ESC4000 series empowered by Intel and AMD platforms to support higher CPU and GPU TDPs to accelerate the development of AI and data science.

ASUS is one of the few HPC solution providers with its own all-dimensional resources that consist of the ASUS server business unit, Taiwan Web Service (TWS) and ASUS Cloud—all part of the ASUS group. This uniquely positions ASUS to deliver in-house AI server design, data-center infrastructure, and AI software-development capabilities, plus a diverse ecosystem of industrial hardware and software partners.

Primate Labs has released the newest update to its cross-platform CPU and GPU benchmark that measures your system's performance, Geekbench 6.1. The latest version brings new features and improvements, including the upgrade to Clang 16, an increased workload gap that should minimize thermal throttling on some devices, as well as introduces support for SVE and AVX 512- FP 16 instructions, and support for fixed-point math. The update also improves multi-core performance.

These changes result in Geekbench 6.1 single-scores to be up to 5 percent higher and multi-core scores up to 10 percent higher, compared to Geekbench 6.0 scores. Due to these differences, Primate Labs recommends that users do not compare scores between Geekbench 6.0 and Geekbench 6.1. Geekbench 6.1 is also a recommended update, according to Primate Labs.

ENERMAX came to the Computex 2023 in full force, showcasing a wide range of new products including new PSUs with ATX 3.0 certification, as well as the new LIQTECH and LIQMAXFLO AIO liquid CPU coolers with new pump design.

ENERMAX definitely had a lot to show at the Computex 2023 event and there were some rather unique and innovative new products on display, including the PLATIMAX GEMINI, a PSU that meets both ATX 3.0 and Intel's new ATX12VO (12 V-only) standards. PLATIMAX GEMINI is an 80 Plus Platinum 1200 W power supply, that surpasses efficiency standards of the ATX12VO standard. ENERMAX also had the who new REVOLUTION D.F. X PSU lineup that is ATX 3.0 and PCIe 5 ready with a native 600 W 12VHPWR cable and an extra dual 8-pin to 12VHPWR 600 W cable, and features new patented Dust-Free Rotation (D.F.R) technology, a new feature that promises to significantly reduce the accumulation of dust around the fan blades. It also features an ARGB side panel with 14 built in lighting modes, and an RGB control button. ENERMAX was showcasing the SPLAVE X REVOLUTION D.F. X PSU, a special edition 1200 W PSU designed in cooperation with a well-known overclocker Splave.

G.Skill a the 2023 Computex showcased its fastest DDR5 memory kits, including some high-performance kits in the non-standard 24 GB DIMM densities. Our visit to the G.Skill booth begins with a handful very boutique custom PC builds. One of them looks like a xenomorph egg, another like a glass pyramid, and another like an Intel semiconductor wafer, and another like sci-fi drilling platform. The Trident Z5 series of DDR5 memory form the bullwark of G.Skill's current-gen lineup. The company showcased a W790 + Xeon W9-3495X workstation build with an 8-channel, 384 GB (8x 48 GB) DDR5-6000 memory setup, with rather tight timings of 30-39-39-96T.

The company also showed us how fast some of its non-standard capacity DIMMs can get, with a DDR5-6800 96 GB (2x 48 GB) build with 34-46-46-108 timings. The star attraction was a build with 48 GB memory (2x 24 GB), and a stellar DDR5-8000, at 40-48-48-128, and G.Skill even performed a live overclocking event, overclocking this to DDR5-8800 speed. Among the memory module models are special gold and silver-chrome variants of the Trident Z5 RGB, and debuting for the very first time, are the Trident Z5 Royal, with its premium aesthetic, and crushed-ice looking LED diffuser.The boutique builds at G.Skill booth follow.

Liquid cooling major Bitspower, which sells both DIY and AIO liquid cooling solutions under its own brand, as well as serves as OEM for other brands, came out with a comprehensive lineup of new products at the 2023 Computex. We begin our stroll of their booth with the Summit lineup of CPU water-blocks and CPU area monoblocks. The company showed us their Summit series LGA4677 block for Intel Xeon W workstations, made of nickel-plated copper and POM acetal tops. These completely dwarf the company's Summit series blocks for AMD sWRX8/sTRX4 Threadripper sockets. The company also showed off a series of CPU area monoblocks. These are motherboard model-specific rather than socket-specific, because they have to be tailored not just for the socket, but also the components in its vicinity, such as CPU VRM.

The innovative new Summit M Silent is designed to reduce noise caused due to coolant flow (by bubbles and vortexes). This is essentially a nickel-plated copper plate that guides coolant through the micro-fin lattice. While the block material is copper with acrylic top, these blocks have additional brushed aluminium top-plates. The Summit M Pure lacks this feature, and is a typical copper+acetal block. Both the Summit M Pure and Summit M Silent come in Socket LGA1700 and Socket AM5 variants. The AMD variants have design-level optimization for the MCM layout of "Raphael," "Vermeer," and "Matisse." Bitspower also showed us a plethora of new fittings, including 45° extenders, 90° extenders, rotary fittings, and static ones. These come in four color options—black, brass, white, and chrome. All four are made of brass. The company also showed us their CR series flat-type and cuboidal reservoirs with provision for integrated pumps.

GIGABYTE is exhibiting cutting-edge technologies and solutions at COMPUTEX 2023, presenting the theme "Future of COMPUTING". From May 30th to June 2nd, GIGABYTE is showcasing over 110 products that are driving future industry transformation, demonstrating the emerging trends of AI technology and sustainability, on the 1st floor, Taipei Nangang Exhibition Center, Hall 1.

GIGABYTE and its subsidiary, Giga Computing, are introducing unparalleled AI/HPC server lineups, leading the era of exascale supercomputing. One of the stars is the industry's first NVIDIA-certified HGX H100 8-GPU SXM5 server, G593-SD0. Equipped with the 4th Gen Intel Xeon Scalable Processors and GIGABYTE's industry-leading thermal design, G593-SD0 can perform extremely intensive workloads from generative AI and deep learning model training within a density-optimized 5U server chassis, making it a top choice for data centers aimed for AI breakthroughs. In addition, GIGABYTE is debuting AI computing servers supporting NVIDIA Grace CPU and Grace Hopper Superchips. The high-density servers are accelerated with NVLink-C2C technology under the ARM Neoverse V2 platform, setting a new standard for AI/HPC computing efficiency and bandwidth.

Intel's Programmable Solutions Group today announced that the Intel Agilex 7 with the R-Tile chiplet is shipping production-qualified devices in volume - bringing customers the first FPGA with PCIe 5.0 and CXL capabilities and the only FPGA with hard intellectual property (IP) supporting these interfaces. "Customers are demanding cutting-edge technology that offers the scalability and customization needed to not only efficiently manage current workloads, but also pivot capabilities and functions as their needs evolve. Our Agilex products offer the programmable innovation with the speed, power and capabilities our customers need while providing flexibility and resilience for the future. For example, customers are leveraging R-Tile, with PCIe Gen 5 and CXL, to accelerate software and data analytics, cutting the processing time from hours to minutes," said Shannon Poulin, Intel corporate vice president and general manager of the Programmable Solutions Group.

Faced with time, budget and power constraints, organizations across industries including data center, telecommunications and financial services, turn to FPGAs as flexible, programmable and efficient solutions. Using Agilex 7 with R-Tile, customers can seamlessly connect their FPGAs with processors, such as 4th Gen Intel Xeon Scalable processors, with the highest bandwidth processor interfaces to accelerate targeted data center and high performance computing (HPC) workloads. Agilex 7's configurable and scalable architecture enables customers to quickly deploy customized technology - at scale with hardware speeds based on their specific needs - to reduce overall design costs and development processes and to expedite execution to achieve optimal data center performance.

ASUS today announced a showcase of the latest HPC solutions to empower innovation and push the boundaries of supercomputing, at ISC High Performance 2023 in Hamburg, Germany on May 21-25, 2023. The ASUS exhibition, at booth H813, will reveal the latest supercomputing advances, including liquid-cooling and AI solutions, as well as outlining a slew of sustainability breakthroughs - plus a whole lot more besides.

Comprehensive Liquid-Cooling Solutions
ASUS is working with Submer, the industry-leading liquid-cooling provider to demonstrate immersion-cooling solutions at ISC High Performance 2023, focused on ASUS RS720-E11-IM - the Intel -based 2U4N server that leverages our trusted legacy server architecture and popular features to create a compact new design. This fresh outlook improves the accessibility on I/O ports, storage and cable routing, and strengthens the structure to allow the server to be placed vertically in the tank, with durability assured.

Increasing its HPL score from 1.02 Eflop/s in November 2022 to an impressive 1.194 Eflop/s on this list, Frontier was able to improve upon its score after a stagnation between June 2022 and November 2022. Considering exascale was only a goal to aspire to just a few years ago, a roughly 17% increase here is an enormous success. Additionally, Frontier earned a score of 9.95 Eflop/s on the HLP-MxP benchmark, which measures performance for mixed-precision calculation. This is also an increase over the 7.94 EFlop/s that the system achieved on the previous list and nearly 10 times more powerful than the machine's HPL score. Frontier is based on the HPE Cray EX235a architecture and utilizes AMD EPYC 64C 2 GHz processors. It also has 8,699,904 cores and an incredible energy efficiency rating of 52.59 Gflops/watt. It also relies on gigabit ethernet for data transfer.

Supermicro, Inc., a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, continues to expand its data center offerings with liquid cooled NVIDIA HGX H100 rack scale solutions. Advanced liquid cooling technologies entirely from Supermicro reduce the lead time for a complete installation, increase performance, and result in lower operating expenses while significantly reducing the PUE of data centers. Savings for a data center are estimated to be 40% for power when using Supermicro liquid cooling solutions compared to an air-cooled data center. In addition, up to 86% reduction in direct cooling costs compared to existing data centers may be realized.

"Supermicro continues to lead the industry supporting the demanding needs of AI workloads and modern data centers worldwide," said Charles Liang, president, and CEO of Supermicro. "Our innovative GPU servers that use our liquid cooling technology significantly lower the power requirements of data centers. With the amount of power required to enable today's rapidly evolving large scale AI models, optimizing TCO and the Total Cost to Environment (TCE) is crucial to data center operators. We have proven expertise in designing and building entire racks of high-performance servers. These GPU systems are designed from the ground up for rack scale integration with liquid cooling to provide superior performance, efficiency, and ease of deployments, allowing us to meet our customers' requirements with a short lead time."

Implementing state-of-the-art artificial intelligence (AI) and machine learning (ML) models requires large amounts of computation, both to train the underlying models, and to serve those models once they're trained. Given the demands of these workloads, a one-size-fits-all approach is not enough - you need infrastructure that's purpose-built for AI.

Together with our partners, we offer a wide range of compute options for ML use cases such as large language models (LLMs), generative AI, and diffusion models. Recently, we announced G2 VMs, becoming the first cloud to offer the new NVIDIA L4 Tensor Core GPUs for serving generative AI workloads. Today, we're expanding that portfolio with the private preview launch of the next-generation A3 GPU supercomputer. Google Cloud now offers a complete range of GPU options for training and inference of ML models.

Supermicro, Inc. (NASDAQ: SMCI), a Total IT Solution Provider for Cloud, AI/ML, Storage, and 5G/Edge, is introducing the most powerful server in its lineup for large-scale database and enterprise applications. The Multi-Processor product line includes the 8-socket server, ideal for in-memory databases requiring up to 480 cores and 32 TB of DDR5 memory for maximum performance. In addition, the product line includes a 4-socket server, which is ideal for applications that require a single system image of up to 240 cores and 16 TB of high-speed memory.

These powerful systems all use 4th Gen Intel Xeon Scalable processors. Compared with the previous generation of 8-socket and 4-socket servers, the systems have 2X the core count, 1.33X the memory capacity, and 2X the memory bandwidth. Also, these systems deliver up to 4X the I/O bandwidth compared to previous generations of systems for connectivity to peripherals. The Supermicro 8-socket system has attained the highest performance ratings ever for a single system based on the SPECcpu2017 FP Rate benchmarks, for both the base and peak results. In addition, the Supermicro 8-socket and 4-socket servers demonstrate performance leadership on a wide range of SPEC benchmarks.

Nfina announces the addition of two new server systems to its lineup, customized for small to medium businesses and virtualized environments. Featuring 3rd Gen Intel Xeon Scalable Processors, these scalable server systems fill a void in the marketplace, bringing exceptional multi-socket processing performance, easy setup, operability, and Nfina's five-year warranty.

"We are excited to add two new 3rd generation Intel systems to Nfina's lineup. Performance, scalability, and flexibility are key deciding factors when expanding our offerings," says Warren Nicholson, President and CEO of Nfina. "Both servers are optimized for high- performance computing, virtualized environments, and growing data needs." He continues by saying, "The two servers can also be leased through our managed services division. We provide customers with choices that fit the size of their application and budget - not a one size fits all approach."

Finding itself embattled with AMD's EPYC "Genoa" processors, Intel is giving its 4th Gen Xeon Scalable "Sapphire Rapids" processor a rather quick succession in the form of the Xeon Scalable "Emerald Rapids," bound for Q4-2023 (about 8-10 months in). The new processor shares the same LGA4677 platform and infrastructure, and much of the same I/O, but brings about two key design changes that should help Intel shore up per-core performance, making it competitive to EPYC "Zen 4" processors with higher core-counts. SemiAnalysis compiled a nice overview of the changes, the two broadest points of it being—1. Intel is peddling back on the chiplet approach to high core-count CPUs, and 2., that it wants to give the memory sub-system and inter-core performance a massive performance boost using larger on-die caches.

The "Emerald Rapids" processor has just two large dies in its extreme core-count (XCC) avatar, compared to "Sapphire Rapids," which can have up to four of these. There are just three EMIB dies interconnecting these two, compared to "Sapphire Rapids," which needs as many as 10 of these to ensure direct paths among the four dies. The CPU core count itself doesn't see a notable increase. Each of the two dies on "Emerald Rapids" physically features 33 CPU cores, so a total of 66 are physically present, although one core per die is left unused for harvesting, the SemiAnalysis article notes. So the maximum core-count possible commercially is 32 cores per die, or 64 cores per socket. "Emerald Rapids" continues to be based on the Intel 7 process (10 nm Enhanced SuperFin), probably with a few architectural improvements for higher clock-speeds.

According to Ming-Chi Kuo, an industry analyst known for making accurate predictions about Apple, we have some new information regarding Intel's Sapphire Rapids Xeon processors. As Kuo notes, Intel's major Cloud Service Provider (CSP) client, Microsoft, has notified the supply chain that the company is cutting orders of Sapphire Rapids Xeons by 50-70% in the second half of 2023. Interestingly, Intel's supply chain has notified the company to cut chip orders by around 50% amidst weak server demand. This comes straight after Intel's plans to start shipping Sapphire Rapids processors in the second quarter of 2023 and deliver the highly anticipated lineup to customers.

Additionally, Kuo has stated that Intel isn't only competing for clients with AMD but also with Arm-based CPUs. Microsoft also plans to start buying Arm-based server processors made by Ampere Computing in the first half of 2024. This will reduce Microsoft's dependence on x86 architecture and induce higher competition in the market, especially if other CSPs follow.

Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, server motherboards, and workstations, today announced a lineup of powerful GPU-centric servers with the latest AMD and Intel CPUs, including NVIDIA HGX H100 servers with both 4-GPU and 8-GPU modules. With growing interest in HPC and AI applications, specifically generative AI (GAI), this breed of server relies heavily on GPU resources to tackle compute-heavy workloads that handle large amounts of data. With the advent of OpenAI's ChatGPT and other AI chatbots, large GPU clusters are being deployed with system-level optimization to train large language models (LLMs). These LLMs can be processed by GIGABYTE's new design-optimized systems that offer a high level of customization based on users' workloads and requirements.

The GIGABYTE G-series servers are built first and foremost to support dense GPU compute and the latest PCIe technology. Starting with the 2U servers, the new G293 servers can support up to 8 dual-slot GPUs or 16 single-slot GPUs, depending on the server model. For the ultimate in CPU and GPU performance, the 4U G493 servers offer plenty of networking options and storage configurations to go alongside support for eight (Gen 5 x16) GPUs. And for the highest level of GPU compute for HPC and AI, the G393 & G593 series support NVIDIA H100 Tensor Core GPUs. All these new two CPU socket servers are designed for either 4th Gen AMD EPYC processors or 4th Gen Intel Xeon Scalable processors.

Noctua has showcased its NH-U14S DX-4677 air cooler in action, cooling down Intel's 56-core Xeon W9-3495X at full load and drawing 700 W of power. While all-in-one (AiO) liquid coolers are popular these days, Noctua aim to show that air coolers are more than capable on handling even the most high-end CPUs, even at continuous load and without throttling.

While the video does not show the full details of the CPU settings, it is still an impressive feat, especially considering the high power draw, which suggest that the CPU was pushed way beyond its default settings for demonstration. The setup includes the aforementioned Intel's 56-core Xeon W9-3495X CPU, running on ASUS Pro WS W790E-SAGE SE motherboard with SK Hynix DDR5 EC8 RDIMM, and powered by Seasonic's PX-1600 PSU.