The innovative manufacturer of high-end multi-GPU workstations and professional liquid cooling solutions for individuals and workgroups requiring GPU computation, announces a slim waterblock of top-tier efficiency for GIGABYTE GeForce RTX 4090 GAMING OC 24 GB and AORUS RTX 4090 MASTER 24G GPUs.

Given the fact that the latest 4090 GPUs by Nvidia are extremely power hungry, the Comino team did its best to deliver the highest performance 4090 waterblock design, specifically adding:

Axiomtek - a world-renowned leader relentlessly devoted to the research, development, and manufacture of series of innovative and reliable industrial computer products of high efficiency - is pleased to announce the iNA200, a DIN-rail cybersecurity gateway for operational technology (OT) network security. The iNA200 is powered by the Intel Atom x6212RE or x6414RE processor (Elkhart Lake) and has one DDR4-3200 SO-DIMM for up to 32 GB of system memory. For demanding rugged environments, this fanless IIoT edge gateway comes with a wide operating temperature range of -40°C to 70°C and supports wide power input of 9 to 36 VDC with dual power input. The iNA200 also has two 2.5G LAN ports, sufficient storage, and high expandability for various industrial application needs.

"OT cybersecurity is essential for Industry 4.0. Axiomtek's iNA200 is designed to safeguard your OT assets and avoid network threats for critical infrastructure," said Kevin Hsiao, a product manager of Network Computing Platform Division at Axiomtek. "Additionally, our iNA200 features an M.2 Key B slot to enable 5G connectivity for next-generation industrial use cases. With the Trusted Platform Module 2.0 (TPM 2.0) support, this cybersecurity gateway increases security offering hardware-level protection against malware and sophisticated cyber-attacks."

Alphawave IP (LSE: AWE), a global leader in high-speed connectivity for the world's technology infrastructure, today announced the successful tapeout of its ZeusCORE100 1-112 Gbps NRZ/PAM4 Serialiser-Deserialiser ("SerDes"), Alphawave's first testchip on TSMC's most advanced N3E process. Alphawave IP will be exhibiting this new product alongside its complete portfolio of high-performance IP, chiplet, and custom silicon solutions at the TSMC OIP Forum on October 26 in Santa Clara, CA as the Platinum sponsor.

ZeusCORE100 is Alphawave's most advanced multi-standard-SerDes, supporting extra-long channels over 45dB and the most requested standards such as 800G Ethernet, OIF 112G-CEI, PCIe GEN6, and CXL 3.0. Attendees will be able to visit the Alphawave booth and meet the company's technology experts including members of the recently acquired OpenFive team. OpenFive is a longstanding partner of TSMC through the OIP Value Chain Aggregator (VCA) program. OpenFive is one of a select few companies with an idea-to-silicon methodology in TSMC's latest technologies, and advanced packaging capabilities, enabling access to the most advanced foundry solution available with the best Power-Performance-Area (PPA). With Alphawave's industry-leading IP portfolio and the addition of OpenFive's capabilities, designers can create systems on a chip (SoCs) that pack more compute power into smaller form factors for networking, AI, storage, and high-performance computing (HPC) applications.

IBM Research has published information about the company's latest development of processors for accelerating Artificial Intelligence (AI). The latest IBM processor, called the Artificial Intelligence Unit (AIU), embraces the problem of creating an enterprise solution for AI deployment that fits in a PCIe slot. The IBM AIU is a half-height PCIe card with a processor powered by 23 Billion transistors manufactured on a 5 nm node (assuming TSMC's). While IBM has not provided many details initially, we know that the AIU uses an AI processor found in the Telum chip, a core of the IBM Z16 mainframe. The AIU uses Telum's AI engine and scales it up to 32 cores and achieve high efficiency.

The company has highlighted two main paths for enterprise AI adoption. The first one is to embrace lower precision and use approximate computing to drop from 32-bit formats to some odd-bit structures that hold a quarter as much precision and still deliver similar result. The other one is, as IBM touts, that "AI chip should be laid out to streamline AI workflows. Because most AI calculations involve matrix and vector multiplication, our chip architecture features a simpler layout than a multi-purpose CPU. The IBM AIU has also been designed to send data directly from one compute engine to the next, creating enormous energy savings."

According to the latest TrendForce research, pandemic-induced materials shortages abated in the second half of this year and the supply and delivery of short-term materials has recovered significantly. However, assuming materials supply is secure and demand can be met, the annual growth rate of server shipments in 2023 is estimated to be only 3.7%, which is lower than 5.1% in 2022.

TrendForce indicates that this growth slowdown is due to three factors. First, once material mismatch issues had eased, buyers began adjusting previously placed purchase order overruns. Thus, ODM orders also decreased but this will not affect the 2022 shipment volume of whole servers for the time being. Second, due to the impact of rising inflation and weakness in the overall economy, corporate capital investment may trend more conservative and IT-related investment will emphasize flexibility, such as the replacement of certain server terminals with cloud services. Third, geopolitical changes will drive the continuing emergence of demand for small-scale data centers and previous construction of hyperscale data centers will slow. The recent ban on military/HPC servers issued by the U.S. Department of Commerce on October 7 has a very low market share in terms of its application category, so the impact on the overall server market is limited at present. However, if the scope of the ban is expanded further in the future, it will herald a more significant slowdown risk for China's server shipment momentum in 2023.

Solidigm has introduced the P44 Pro solid-state storage drive (SSD), a high-performance client SSD for today's most demanding workloads. With blazing-fast speed and excellent power efficiency, the P44 Pro is the world's premier SSD for enthusiasts. The P44 Pro delivers spectacular PCIe Generation 4.0 performance, with up to 7,000 MB/s sequential read speeds. It provides a superb combination of speed and efficiency in Solidigm testing, meeting or exceeding published performance specifications while drawing just 5.3 W. The P44 Pro is available in 512 GB, 1 TB, and 2 TB capacities.

"Our flagship client SSD, the P44 Pro, is built with our cutting-edge NAND technology. Combined with our powerful software, it delivers the high performance users require in demanding applications. The P44 Pro is the most powerful client SSD Solidigm has launched to date and the premier enthusiast SSD on the market," said Sanjay Talreja, General Manager, Client Storage Group. "This drive delivers quick launch and load, and the fast save desired by gaming enthusiasts and content creators. With excellent power efficiency, the P44 Pro minimizes throttling that can come from excessive power and heat - resulting in consistent peak performance."[Editor's note: Our in-depth review of the Solidigm Introduces the P44 Pro is now live]

Affected by tight wafer supply, lead time for SSD controller IC and PMIC components was prolonged to 32 weeks in 2021. All controller IC suppliers generally give priority to supplying NAND Flash manufacturers, so production at module factories could not meet SSD demand in the retail market during that time. In 2H21, the supply of SSD-related components improved quarter by quarter and various module manufacturers boosted their SSD shipments in order to upsurge their annual performance. According to TrendForce research, SSD shipments through global distribution channels reached 127 million units in 2021, with an annual growth rate of 11%.

This global SSD ranking is based on the shipment volume of module houses' own in-house brands in the distribution channel market as a standard for calculation and NAND Flash manufacturers are not included. NAND Flash manufacturer supply accounts for approximately 42% of the overall distribution channel market while module factory shipments account for approximately 58%. When SSD-related components were hard to come by, NAND manufacturers' supply chain management occupied a superior position compared to module houses, so NAND manufacturers' market share in the overall distribution channel market increased compared with 2020.

In December of 2021, we covered the appearance of Russia's home-grown Baikal-S processor, which has 48 cores based on Arm Cortex-A75 cores. Today, thanks to the famous chip photographer Fritzchens Fritz, we have the first die shows that show us exactly how Baikal-S SoC is structured internally and what it is made up of. Manufactured on TSMC's 16 nm process, the Baikal-S BE-S1000 design features 48 Arm Cortex-A75 cores running at a 2.0 GHz base and a 2.5 GHz boost frequency. With a TDP of 120 Watts, the design seems efficient, and the Russian company promises performance comparable to Intel Skylake Xeons or Zen1-based AMD EPYC processors. It also uses a home-grown RISC-V core for management and controlling secure boot sequences.

Below, you can see the die shots taken by Fritzchens Fritz and annotated details by Twitter user Locuza that marked the entire SoC. Besides the core clusters, we see that a slum of cache connects everything, with six 72-bit DDR4-3200 PHYs and memory controllers surrounding everything. This model features a pretty good selection of I/O for a server CPU, as there are five PCIe 4.0 x16 (4x4) interfaces, with three supporting CCIX 1.0. You can check out more pictures below and see the annotations for yourself.

GIGABYTE Technology, (TWSE: 2376), an industry leader in high-performance servers and workstations, today announced supporting products for the new AMD AM5 platform starting with two GIGABYTE motherboards, MC13-LE0 & MC13-LE1, that pair a consumer CPU with IPMI management functionalities via BMC. Additionally, a new desktop workstation, W332-Z00, was released using the same motherboard series platform that supports remote management, but the W332 does so with a Realtek NIC that enables DASH.

The new GIGABYTE products designed to support host systems are deceivingly powerful with a small micro-ATX form factor motherboard and enterprise rich out-of-band management features on top of PCIe Gen 5 and DDR5 technologies. These new client friendly products will be found in office settings under a desk rather than a rack in a data center, as they be managed from anywhere, provided there is a network connection. Furthermore, these new products are purpose built for the mainstream AMD B650E chipset with AMD Zen 4 architecture for AMD Ryzen 7000 Series desktop processors.

NVIDIA's high-performance computing hardware stack is now equipped with the top-of-the-line Hopper H100 GPU. It features 16896 or 14592 CUDA cores, developing if it comes in SXM5 of PCIe variant, with the former being more powerful. Both variants come with a 5120-bit interface, with the SXM5 version using HBM3 memory running at 3.0 Gbps speed and the PCIe version using HBM2E memory running at 2.0 Gbps. Both versions use the same capacity capped at 80 GBs. However, that could soon change with the latest rumor suggesting that NVIDIA could be preparing a PCIe version of Hopper H100 GPU with 120 GBs of an unknown type of memory installed.

According to the Chinese website "s-ss.cc" the 120 GB variant of the H100 PCIe card will feature an entire GH100 chip with everything unlocked. As the site suggests, this version will improve memory capacity and performance over the regular H100 PCIe SKU. With HPC workloads increasing in size and complexity, more significant memory allocation is needed for better performance. With the recent advances in Large Language Models (LLMs), AI workloads use trillions of parameters for tranining, most of which is done on GPUs like NVIDIA H100.

Last year Cooler Master unveiled a milestone in the history of contemporary technology: the very first small form factor power supply in the market with 850 W, V SFX Gold series. Today, Cooler Master takes the successor and pushes the limit to the maximum. Introducing V SFX Platinum, a series of small form factor power supply focused on high density and maximum power. While increasing the efficiency rate from Gold to Platinum, we also added ATX 3.0 and PCI-e Gen 5 connector so even with the Mini-ITX build; this will be your last stop when choosing the right power supply.

High Density / Performance-Focused
The V SFX Platinum comes with 2 different wattages: 1100 W and 1300 W targeting Mini-ITX system builders who wants to go bold with their setup, but doesn't have enough juice from the power supply. It also comes with a free SFX-ATX bracket that unlocks the limitations between each form factors, giving end-users more freedom and potential builds in the future. The V SFX Platinum are built with Full Bridge LLC design, quiet 92 mm silent fan and 100% Japanese capacitors. By adding PCIe Gen 5 connector, V SFX Platinum can unlock it's true potential and power up all Nvidia RTX 40 series GPU in the future.

The demand for data is insatiable, from 5G to the cloud to smart cities. As a society we want more autonomy, information to fuel our decisions and habits, and connection - to people, stories, and experiences.

To address these demands, the cloud infrastructure of tomorrow will need to handle the coming data explosion and the effective processing of evermore complex workloads … all while increasing power efficiency and minimizing carbon footprint. It's why the industry is increasingly looking to the performance, power efficiency, specialized processing and workload acceleration enabled by Arm Neoverse to redefine and transform the world's computing infrastructure.

Marvell today unveiled its LiquidSecurity 2 (LS2) hardware security module (HSM) adapter, the industry's most advanced solution for enabling encryption, key management, authentication and other HSM services in the cloud. LS2 is a converged security platform for payment, privacy compliance, and general purpose applications, and is powered by a cloud-optimized Marvell OCTEON data processing unit (DPU), proven at scale across the world's largest hyperscale clouds. The new Marvell HSM adapter offers the industry's highest performing cryptographic acceleration and processing, including hardware-secured storage of up to one million keys for AES, RSA and ECC encryption algorithms, and 45 partitions for robust multi-tenant use cases.

As enterprises migrate from on-premises to private- or multi-cloud environments, the industry-leading Marvell LiquidSecurity platform empowers cloud service providers and large enterprises to create HSM-as-a-service clouds. Marvell's HSM adapters have the latest FIPS-certified security boundary, designed for the most demanding applications deployed at cloud-scale while offering best-in-class cost, performance and energy efficiency for both public and private clouds.

Lian Li unveiled the SP850, the first SFX form-factor power supply featuring ATX 3.0 specs readiness, and PCIe Gen 5 compliance, including a 12+4 pin ATX12HPWR connector for next-generation graphics cards. Available in black and white body-color variants, the it offers 850 W continuous output, including tolerance for +100% excursions for at least 100 µs intervals. and meets 80 Plus Gold efficiency. It features a single +12 V rail design, with most common electrical protections. The 92 mm fluid dynamic bearing fan keeping it cool offers fanless (zero RPM) cooling up to 340 W load (excluding excursions). The Lian Li SP850 offers full modular cabling. Besides the 12+4 pin ATXHPWR, you get two 8-pin EPS, and three 6+2 pin PCIe power connectors. Peripheral connectivity includes eight SATA power connectors. Lian Li is backing the SP850 with a 5-year warranty. Available now, it is priced at USD $150-170.

Here are some of the first pictures of the Seasonic PS Vertex series of high-Wattage PSUs that meet ATX 3.0 standards, and feature a PCIe Gen 5-compliant ATX12HPWR 12+4 pin connector capable of delivering 600 W, with +100% excursions lasting 100 µs. There are four models in the series, the PS Vertex 1000G, PS Vertex 1000P, PS Vertex 1200G, and PS Vertex 1200P. The 1000G/1200G meet 80 Plus Gold efficiency, while the 1000P/1200P meet 80 Plus Platinum. Both offer fully modular cabling, including a 12+4 pin ATXHPWR connector, a multitude of conventional 6+2 pin PCIe power connectors, SATA power connectors, at least two 8-pin EPS, and more. Early listing see the PS Vertex 1200P at USD $319, the PS Vertex 1200G at $281, the PS Vertex 1000P at $271, and the PS Vertex 1000G at $243.

Tech manufacturer JSAUX announces that its upcoming generation of Steam Deck Docking Stations is available and ready to order. The HB0604 Docking Station features an M.2 SSD slot that will allow players to upgrade the Deck's storage by attaching an external storage unit (not included with the dock). This way, players can expand their library when playing games on a big screen, especially AAA titles that tend to grab a significant chunk of the Deck's storage. This new Docking Station will be on sale on September 7 at 7am PST for a special $99 early bird price for the first 100 orders. After that, next orders will be priced at $129. JSAUX is also offering two bundled M.2 Docks with a 1 TB SSD and a 2 TB SSD storage card. The Dock + 1 TB SSD storage card will have an early bird price of $169 for the first 50 units (after that, it will be sold at $199), the Dock + 2 TB SSD storage card will have an early bird price of $239 for the first 50 units (after that, it will be priced at $269). All customers will get a complimentary portable stand for the Deck (while supplies last), a skin and a keycap with their orders.

Besides the M.2 SSD slot, that supports NVMe and SATA with a 900 MB/s data transfer, the docking Station features a 4K@60 Hz / 2K@120 Hz HDMI 2.0 port, 2 USB-A 3.1 ports, 1 Gigabit Ethernet port as well as a USB-C port for power input that allows charging at 100 W, letting the Steam Deck fully recharge while plugged in. The units bundled with SSD storage will feature M.2 2280 units, featuring PCIe Gen 3 8GT/s interface, up to 4 lanes. The SSDs are compliant with NVMe Express Revision 1.4 and support host memory buffer. Both the 1 TB and the 2 TB units offer up to 3300 MB/s read speeds and up to 2600 MB/s write speeds.

ASUS Republic of Gamers (ROG) today announced the availability of the ROG Loki—the high-performance, high-wattage PSU series in a striking SFX-L form. Packed with large ROG heatsinks for rapid cooling, integrated ARGB lighting to project personal style and axial-tech fans for whisper-quiet operation, the Loki series is pumped and primed to power small-form-factor (SFF) builds.

Large showcase rigs will always be the lifeblood of the PC-building community, but SFF builds have become increasingly popular in recent years. It's easy to see why: for those that want a build that can comfortably fit on a smaller desk, or in an entertainment center for TV gaming, a Mini-ITX machine is the perfect choice. But cramming next-gen power into a tiny case can be a challenge, especially with the added heat those components can produce. ROG's new Loki power supplies were designed to keep efficiency up and footprint down, empowering avid PC DIYers to build no-compromise, console-crushing clones.

AMD's upcoming launch of Ryzen 7000 series processors will bring an entirely new AM5 platform that will enable newer technologies and protocols. We have DDR5 memory and PCIe 5.0 connection with everything at level five. However, the upcoming chipsets AMD has designed to work alongside the new processors will be available in several variants. There will be regular X670 and B650 versions that support either a PCIe 5.0 GPU or a PCIe 5.0 M.2 NVIMe SSD. Today, we got a confirmation that not only the big X670 chipset has an "E" or "Extreme" version, but its smaller brother B650 as well. With X670E and B650E, users get both PCIe 5.0 connectivity for their GPU and M.2 NVIMe SSD. For more information, we have to wait for AMD's official launch information later today.

According to TrendForce research, material supply improvement and spiking demand for enterprise SSDs from North American hyperscale data center and enterprise clients in 2Q22 coupled with the Kioxia contamination incident in 1Q22 prompted customers to ramp up procurement to avoid future supply shortages. Manufacturers also give priority to meeting the needs of server customers due to the high pricing of enterprise SSD. In the second quarter, overall revenue of the enterprise SSD market increased by 31.3% to US$7.32 billion.

As the market leader, Samsung has grown its enterprise SSD revenue to US$3.26 billion with the recovery of enterprise SSD procurement. Especially in the second quarter, when orders for other consumer products continued to decline, enterprise SSD became the company's outlet for reducing production capacity. At present, Samsung has been continuously investing in the development of next-generation transmission specification products such as the CXL 2.0 product released at the Flash Summit in early August, in order to maintain a leading position in the market.

DFI, the global leading provider of high-performance computing technology across multiple embedded industries, unveils a server-grade ATX motherboard, designed for Intel Ice Lake platform, powered by the 3rd Generation Intel Xeon Scalable processors, and equipped with ultra-high speed computing that can support up to 205 W. ICX610-C621A also comes with built-in Intel Speed Select Technology (Intel SST), which provides an excellent load balancing between CPUs and multiple accelerator cards to effectively distribute CPU resource, stabilize computation loads and maximize computing power. As a result, it improves the performance by 1.46 times compared to previous generation.

Featuring powerful performance, the offers three PCIe x16, two PCIe x8 slots and one M.2 Key and enables ultra-performance computing, AI workload and deep learning, specifically for high-end inspection equipment, such as AOI, CT, and MRI application. The ICX610 also supports ECC RDIMM up to 512 GB 3200 MHz, enhances high end performance for advanced inspection equipment and improves efficiency.

Intel's next-generation "Meteor Lake" processor is the first mass-production client processor to embody the company's IDM 2.0 manufacturing strategy—one of building processors with multiple logic tiles interconnected with Foveros and a base-tile (essentially an interposer). Each tile is built on a silicon fabrication process most suitable to it, so that the most advanced node could be reserved for the component that benefits from it the most. For example, while you need the SIMD components of the iGPU to be built on an advanced low-power node, you don't need its display controller and media engine to, and these could be relegated to a tile built on a less advanced node. This way Intel is able to maximize its use of wafers for the most advanced nodes in a graded fashion.

Japanese tech publication PC Watch has annotated the "Meteor Lake" SoC, and points out that the vast majority of the chip's tiles and logic die-area is manufactured on TSMC nodes. The MCM consists of four logic tiles—the CPU tile, the Graphics tile, the SoC tile, and the I/O tile. The four sit on a base tile that facilitates extreme-density microscopic wiring interconnecting the logic tiles. The base tile is built on the 22 nm HKMG silicon fabrication node. This tile lacks any logic, and only serves to interconnect the tiles. Intel has an active 22 nm node, and decided it has the right density for the job.

MSI welcomes the MEG Ai1300P PCIE5 power supply unit, the world's first power supply unit to be fully ready for ATX 3.0 and PCIe 5.0. With graphics cards becoming all the more important, users must know what components to buy for their system if they are looking to upgrade. To understand why the MEG Ai1300P PCIE5 is the ultimate future-proof power supply unit, let's begin with understanding ATX 3.0.

ATX 3.0 is Intel's new specification standard for existing PSUs. In short, ATX 3.0's main purpose is to help provide more reliability, and better power efficiency and provide graphics cards up to 600 watts of power. ATX 3.0 is created in response to graphics cards' increase in performance and the ever-increasing need for power. ATX 3.0 puts heavy emphasis on power excursions to make sure high-performance graphics cards can be sustained and your system can remain stable. Thanks to ATX 3.0 there is now an increase in efficiency while idling and a new power connector is added to help achieve all the above. ATX 3.0 added a new PCIe 5.0 12VHPWR connector that features 12+4 pins instead of the traditional 6 or 8. With the new PCIe 5.0 connector, the power supply and cable can supply up to 600 watts of power.

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.

ASRock has signed up as one of Intel's board partners for its Arc "Alchemist" graphics cards, and is ready with its custom-design Arc A380 Challenger card, pictured below. The company joins the likes of China's Gunnir, in bringing to market some of the first graphics cards from the yet-elusive GPUs from Intel. The ASRock-branded custom A380 card surfaced on Chinese social-media site Bilibili, revealing a cost-effective design, with a simple aluminium mono-block fan-heatsink. The board draws power from a single 8-pin PCIe power connector, and like Gunnir's A380 card, has a spartan-looking PCB. There's still no word on global availability, and ASRock could stick to the China-first rollout of Arc.

For those with older systems, or for those just in need of additional M.2 slots in their system, SilverStone has launched the SST-ECM28 riser card. The SST-ECM28 is a low-profile solution that can house one M-key NVMe drive and one B-key SATA drive, as it allows a drive to be mounted on each side of the riser card. The SATA drive requires a SATA cable to be connected to the rear of the riser card and then to a SATA slot on the motherboard to function.

This isn't the first time we've seen a product that can handle two drives, but it's the first time we've seen one that is as compact as this. The downside is that there's no retention bracket and it appears that the only way to hold the SST-ECM28 is by fitting it into a physical x16 slot that has a locking mechanism for graphics cards, as the PCB has a retention hook, just as you get on most x16 cards. The SST-ECM28 uses a standard x4 PCIe interface, so it will fit in x4 slots as well, with the risk of it popping out of the slot if the system is moved around. Drives of all sizes from 2230 up to 2280 are supported for both SATA and NVMe drives.