In its latest video presentation dealing with the reference board design and overclocking architecture of the Arc A770 Limited Edition graphics card, Intel revealed that the cards should be "monster overclockers," and that they've been able to get their randomly selected card to run at 2.70 GHz (up from 2.10 GHz reference), without the need for custom-cooling, just by using the overclocking controls on the Arc Control software. The cooler has a noise output of up to 39 dBA, and even with the overclocked GPU, Intel claims, the temperatures never crossed the 80-90 °C range. The GPU power was claimed to be around 228 W.

Intel clarified that the "GPU Clock" advertised with the A770 is the guaranteed clock-speed sustained by the GPU at least 50% of the time, even on the "least performing" silicon. The actual clock will vary around this point. This is represented as a bell-curve on top of the voltage-frequency curve of the GPU. There are two ways to go about increasing the performance of the GPU—increasing the voltage, which would increase the clock residency (sustainability of elevated clock-states); and by increasing the frequency itself. Both of these can be accomplished using Arc Control.

Intel's latest NUC 12 Extreme desktops, codenamed "Serpent Canyon," are up for pre-order. These are the company's first gaming-grade NUCs to pack all-Intel hardware, including the GPU. "Serpent Canyon" combines 12th Gen Core "Alder Lake-H" processors with Arc "Alchemist" discrete GPUs, with options going all the way up to the Arc A770 for graphics, and a Core i7-12700H (6P+8E) for the CPU. In its base configuration with 8 GB (2x 4 GB) DDR4 memory, 256 GB M.2 NVMe storage, i7-12700H processor and Arc A770 graphics; the NUC 12 Extreme can be pre-ordered for £1,499 excluding VAT.

GIGABYTE TECHNOLOGY Co. Ltd, a leading manufacturer of motherboards, graphics cards, and hardware solutions, today announced all Z690, B660, and following motherboards will support EXPO memory. Users can enjoy performance boost with ease on GIGABYTE motherboards of all platforms with either AMD EXPO or Intel XMP supported memories.

AMD recently announced the new EXPO technology for DDR5 memory on the latest AM5 platform, which allows easy DDR5 memory accelerating with built-in overclocking profiles for the performance uplift, just like XMP technology. Along with this new technology, all major memory module brands release EXPO memories correspondingly. GIGABYTE leads to provide both AMD EXPO and Intel XMP DDR5 support on AM5 motherboards, and carry on the innovative design to Intel platform, which enable users to speed up their DDR5 memories on Z690, B660, and following motherboards by simply activate XMP and EXPO in the BIOS setting for the performance boost.

Intel Graphics, in its latest teaser video to the Arc A770 Limited Edition "Alchemist" graphics card, posted detailed renders of the card disassembled. The card features a strictly dual-slot cooling solution that uses an aluminium base-plate and a copper vapor-chamber to pull heat from the various hot components of the PCB. This is conveyed by four flat copper heat pipes through an aluminium fin-stack heatsink, which is ventilated by a pair of 80 mm fans. The cooler and its backplate feature four independent RGB lighting zones—the bores of each of the two fans, a light strip running along the top of the card; and toward the tail-end of the backplate, with a total of 90 LEDs. Intel claims that the maximum noise output of the cooler is 39 dBA.

The PCB is shorter in length than the cooler itself, and is full-height (and no taller). It draws power from a combination of 8-pin and 6-pin PCIe power connectors, which combined with slot-power add up to 300 W. A 6-phase VRM powers the "ACM-G10" GPU, while there are three other VRM phases, which could power the eight GDDR6 memory chips, and other power domains of the card. Display outputs include three standard-size DisplayPort 2.0, and one HDMI 2.1. The card's host interface is PCI-Express 4.0 x16, and although not a system requirement, Intel insists that the card be used on a machine with PCI resizable-BAR enabled.

Today, Intel introduces a new processor for the essential product space: Intel Processor. The new offering will replace the Intel Pentium and Intel Celeron branding in the 2023 notebook product stack.

"Whether for work or play, the importance of the PC has only become more apparent as the torrid pace of technological development continues to shape the world. Intel is committed to driving innovation to benefit users, and our entry-level processor families have been crucial for raising the PC standard across all price points. The new Intel Processor branding will simplify our offerings so users can focus on choosing the right processor for their needs." -Josh Newman, Intel vice president and interim general manager of Mobile Client Platforms

Durabook, the global rugged mobile solutions brand owned by Twinhead International Corporation, today announced the launch of its new Durabook R8, the world's first fanless 8" fully rugged tablet featuring 12th generation Intel Core processors for exceptionally powerful user performance. "Durabook devices are designed to meet the increasing demands of field service workers operating across some of the most demanding sectors, including manufacturing, transportation, logistics, field services and utility industries, as well as law enforcement departments and government agencies," said Twinhead CEO Fred Kao. "These users often require both high performance and the convenience of portability, which are typically conflicting needs. Now, there is R8. The R8 meets all these requirements head-on, allowing workforces to boost efficiency and performance even in the harshest environments."

The only 8" rugged tablet on the market equipped with 12th generation Intel Core processors, the R8 provides an unrivaled combination of power and portability, weighing just 1.9 lbs. Its Pentium Gold CPU offers a performance that's up to 450% faster than competitor devices running on Intel Atom processors and up to 800% for devices using Intel Core processors. In addition, the tablet's Intel Iris Xe Graphics boosts computing power to process large amounts of data, images, and video feeds in real time, providing a reliable mobile solution to support digital and remote operations for diverse professional applications.

Here's the first picture of a custom-design Intel Arc A750 "Alchemist" graphics card, in this case, an ASRock Arc A750 Challenger. ASRock showed the card off at its Tokyo Game Show 2022 booth. The strictly 2-slot thick card appears to have a fairly well-endowed aluminium fin-stack cooling solution featuring a pair of large 100 mm fans. Its cooling solution uses two aluminium fin-stacks skewered by a number of copper heat pipes. The card draws power from two 8-pin PCIe power connectors, and features some illumination in the way of an illuminated Arc logo.

The Arc A750 is based on the same 6 nm "DG2-512" silicon as the A770 Limited Edition—which looks increasingly like an Intel-exclusive that will only be sold in its reference design. While the A770 maxes out the chip with all 32 Xe Cores being enabled (512 EUs, or 4,096 unified shaders), the A750 gets 28 Xe Cores (448 EUs, or 3,584 unified shaders). It also gets 8 GB of 16 Gbps GDDR6 memory across a 256-bit wide memory interface (512 GB/s bandwidth), 448 XMX units (accelerates AI and features like XeSS), and 28 RT units. The reference engine clock of the A750 is set at 2.05 GHz, although it's likely that the ASRock Challenger is a factory-overclocked card.

OneRaichu, who has access to engineering samples of both the AMD "Raphael" Ryzen 7000-series, and Intel 13th Gen Core "Raptor Lake," performed IPC comparisons between the two, by disabling E-cores on the "Raptor Lake," fixing the clock speeds of both chips to 3.60 GHz, and testing them across a variety of DDR5 memory configurations. The IPC testing was done with SPEC, a mostly enterprise-relevant benchmark, but one that could prove useful in tracing where the moderately-clocked enterprise processors such as EPYC "Genoa" and Xeon Scalable "Sapphire Rapids" land in the performance charts. OneRaichu also threw in scores obtained from a 12th Gen Core "Alder Lake" processor for this reason, as its "Golden Cove" P-core powers "Sapphire Rapids" (albeit with more L2 cache).

With DDR5-4800 memory, and testing on SPECCPU2017 Rate 1, at 3.60 GHz, the AMD "Zen 4" core ends up with the highest scores in SPECint, topping even the "Raptor Cove" P-core. It scores 6.66, compared to 6.63 total of the "Raptor Cove," and 6.52 of the "Golden Cove." In the SPECfp tests, however, the "Zen 4" core falls beind "Raptor Cove." Here, scores a 9.99 total compared to 9.91 of the "Golden Cove," and 10.21 of the "Raptor Cove." Things get interesting at DDR5-6000, a frequency AMD considers its "sweetspot," The 13th Gen "Raptor Cove" P-core tops SPECint at 6.81, compared to 6.77 of the "Zen 4," and 6.71 of "Golden Cove." SPECfp sees the "Zen 4" fall behind even the "Golden Cove" at 10.04, compared to 10.20 of the "Golden Cove," and 10.46 of "Raptor Cove."

Arm, Intel and NVIDIA have jointly authored a paper describing an 8-bit floating point (FP8) specification and its two variants E5M2 and E4M3 to provide a common interchangeable format that works for both artificial intelligence (AI) training and inference. This cross-industry specification alignment will allow AI models to operate and perform consistently across hardware platforms, accelerating AI software development.

Computational requirements for AI have been growing at an exponential rate. New innovation is required across hardware and software to deliver computational throughput needed to advance AI. One of the promising areas of research to address this growing compute gap is to reduce the numeric precision requirements for deep learning to improve memory and computational efficiencies. Reduced-precision methods exploit the inherent noise-resilient properties of deep neural networks to improve compute efficiency.

Andreas Schilling with Hardwareluxx.de, as part of the Intel Tech Tour Israel, got to hold a 12-inch wafer full of "Raptor Lake-S" dies. These are dies in their full 8P+16E configuration. The die is estimated to measure 257 mm² in area. We count 231 full dies on this wafer. Intel is building "Raptor Lake" on the same 10 nm Enhanced SuperFin (aka Intel 7) node as "Alder Lake." The die is about 23% larger than "Alder Lake" on account of two additional E-core clusters, possibly larger P-cores, and larger L2 caches for both the P-core and E-core clusters. "Raptor Lake" gains significance as it will be the last client processor from Intel to be built on a monolithic die of a uniform silicon fabrication node. Future generations are expected to take the chiplets route, realizing the company's IDM 2.0 product development strategy.

Intel's Xeon Scalable "Sapphire Rapids" processor may have a tough time getting to market, as leaked benchmarks suggest that even its premium HPC models with on-package HBM2E memory are outperformed by AMD's older-generation "Zen 3" EPYC processors. The 64-core/128-thread EPYC "Milan-X" processor based on older "Zen 3" microarchitecture with 3D Vertical Cache (3DV cache) chiplets, allegedly outperforms 52-core/104-thread Xeon Platinum 8472C and 60-core/120-thread Xeon Platinum 8490H "Sapphire Rapids" engineering samples in CPU-Z Bench and V-ray tests that scale across cores. These benchmark scores were compared with those of the EPYC "Milan-X" by Tom's Hardware, in which they well woefully short of the AMD chips.

The recent 80 Gbps USB4 Version 2.0 standard looks set to get company from Thunderbolt at 80 Gbps in the not too distant future, as Intel has demoed its next generation Thunderbolt hardware to the media during its Technology Tour 2022 in Israel. It doesn't appear that Intel showed too much of the upcoming technology, but the company did apparently show it running at 80 Gbps, or if you want to be picky, two times 40 Gbps in dual link mode, much in the same way USB4 Version 2.0 will operate.

According to Tom's Hardware, Intel hasn't set the marketing name in stone quite yet, so it's not clear what Intel will be calling its next generation of Thunderbolt. What is clear is that Intel will continue to deliver on its own Thunderbolt products, despite USB4 having almost feature parity with Thunderbolt, apart from some Intel platform specific features. What is also unknown, is a potential availability date for Intel's next generation of Thunderbolt, but an educated guess will be before USB4 Version 2.0 launches.

Super Micro Computer, Inc. (SMCI), a global leader in enterprise computing, storage, networking solutions, and green computing technology, is announcing its most advanced GPU server, incorporating eight NVIDIA H100 Tensor Core GPUs. Due to its advanced airflow design, the new high-end GPU system will allow increased inlet temperatures, reducing a data center's overall Power Usage Effectiveness (PUE) while maintaining the absolute highest performance profile. In addition, Supermicro is expanding its GPU server lineup with this new Universal GPU server, which is already the largest in the industry. Supermicro now offers three distinct Universal GPU systems: the 4U,5U, and new 8U 8GPU server. The Universal GPU platforms support both current and future Intel and AMD CPUs -- up to 400 W, 350 W, and higher.

"Supermicro is leading the industry with an extremely flexible and high-performance GPU server, which features the powerful NVIDIA A100 and H100 GPU," said Charles Liang, president, and CEO, of Supermicro. "This new server will support the next generation of CPUs and GPUs and is designed with maximum cooling capacity using the same chassis. We constantly look for innovative ways to deliver total IT Solutions to our growing customer base."

Here are the first pictures of a low-profile Intel Arc A380 graphics card by MSI. The half-height card is 2 slots thick, and is probably the first A380 card we've come across that appears to lack a power connector. The card surfaced on Japanese IT news portals, when a DAIV-built commercial desktop was disassembled revealing this low-profile card. The desktop combines a Core i7-12700 with this A380 card. The card appears to feature a complex aluminium fin-stack heatsink instead of a cheap aluminium monoblock one. The typical board power of A380 running at stock frequencies is exactly 75 W, and so MSI could build this card without any power connectors. Other board partners have been known to include at least a 6-pin connector to minimize power draw from the slot.

In an article explaining how to choose the right desktop processor with examples, Intel Canada accidentally leaked the Core i9-13900K, i7-13700K, and i5-13600K processors. The article has since been corrected with their 12th Gen predecessors, but not before screenshots made it to social media. The screenshots confirm the core-count of the i5-13600K to be 14-core/20-thread (6P+8E), the i7-13700K to be 16-core/24-thread (8P+8E), and the flagship i9-13900K to be 20-core/32-thread (8P+16E). It also mentions their clock speeds to be 5.10 GHz P-core boost for the i5-13600K, 5.30 GHz for the i7-13700K, and 5.40 GHz for the i9-13900K; however leaked press-deck slides list these as maximum Turbo Boost 2.0 frequencies. The Boost Max 3.0 and Thermal Velocity Boost frequencies are much higher. In case of the i9-13900K, it can be as high as 5.80 GHz. Intel is expected to launch its 13th Gen Core desktop processor series on September 27.

As with every generation before it, Intel is preparing a line of 13th Gen Core processors with 35 W processor base power under the "T" brand extension. The Core i7-13700T retains the core-configuration of the i7-13700K (8P+8E), but with a much more aggressive power-management for commercial-desktop applications. Geekbench 5.4.5 scores of the processor were leaked to the web, where the processor was shown matching or beating the Core i5-12600K, a previous-generation 6P+4E core processor with much higher boost frequencies, and power limits.

The Core i7-13700T comes with nominal clock speeds of just 1.40 GHz, compared to 3.40 GHz of the i7-13700K, while its P-core maximum boost is probably 4.90 GHz, compared to 5.40 GHz of its enthusiastic sibling. The maximum boost frequency difference between the two SKUs may not seem like much, but the tighter power limits mean that the i7-13700T will hold on to boost frequencies in much smaller bursts. The chip is shown scoring 1939 points in the single-threaded test, and 11564 points in the multi-threaded one. In the ST test, the chip has sufficient power budget to boost one P-core to its maximum frequency, and so it's beating the i5-12600K with its 1856 ST score. In the multi-threaded test, it's slightly worse than the 11608 points of the i5-12600K. While it has more cores, there simply isn't enough power budget to run them at high frequencies. The Core i7-13700T likely won't be part of the first wave of 13th Gen Core SKUs, and will probably launch by late-2022 or early-2023.

With Intel's 13th Gen Core "Raptor Lake" facing stiff competition from AMD's Ryzen 7000 series, and the "Zen 4" series being augmented with 7000X3D series in early-2023, it's becoming a foregone conclusion that Intel will launch a possible "Core i9-13900KS" SKU, which is on its way to being the world's first desktop processor that can boost up to the 6.00 GHz mark. The processor should be able to boost its 8 "Raptor Cove" P-cores to the 6.00 GHz mark, given that the maximum boost frequency of the stock i9-13900K is already rumored to be at 5.70 GHz.

At its Tech Tour event in Israel, Intel confirmed that "Raptor Lake" brings a 15% single-threaded, and 41% multi-threaded performance gain over "Alder Lake." The single-threaded gain is from the higher IPC of the "Raptor Cove" P-core, coupled with its frequency set as high as 5.70 GHz; whereas the multi-threaded performance gain is a combination of increased IPC of the P-cores, and increased frequencies for both the P-cores and E-cores. The E-core clusters get more shared L2 cache, which should improve their performance, too.

Intel's accelerated computing group head Raja Koduri, who heads the team behind the Arc "Alchemist" graphics, on late-Sunday, refuted rumors about the company shutting down the Arc graphics product line. Responding to a question to that effect on Twitter, Koduri tweeted "we are shrugging about these rumors as well. They don't help the team working hard to bring these to market, they don't help the PC graphics community..one must wonder, who do they help?..we are still in first gen and yes we had more obstacles than planned to overcome, but we persisted."

Rumors about Intel dropping the axe on Arc have been around for some time now, after repeated delays in getting the products to market, limited regional launches; and gathered steam as Intel closed down the Optane Memory business last quarter. Last week, after Intel presented a less-than-perfect outlook for its processor business hinted that it could exit "other" unprofitable businesses.

Today, President Joe Biden joins Intel, Ohio Gov. Mike DeWine and other federal, state and local officials to celebrate breaking ground in the Silicon Heartland on two of the world's most advanced chipmaking facilities. As part of Intel's commitment to develop a skilled talent pipeline for its two new leading-edge chip fabs, Intel also announced the first phase of funding for its Ohio Semiconductor Education and Research Program. During this first phase, Intel is providing $17.7 million for eight proposals from leading institutions and collaborators in Ohio to develop semiconductor-focused education and workforce programs.

"Today marks a pivotal moment in the journey to build a more geographically balanced and resilient semiconductor supply chain. The establishment of the Silicon Heartland is testament to the power of government incentives to unlock private investment, create thousands of high-paying jobs, and benefit U.S. economic and national security. We would not be here today without the support of leaders in the administration, Congress and the state of Ohio, who share a vision to help restore the United States to its rightful place as a leader in advanced chipmaking," said Pat Gelsinger, Intel CEO.

During Evercore ISI TMT conference, Intel announced that the company would continue to lose market share, with a possible bounce back in the coming years. According to the latest report, Intel's CEO Pat Gelsinger announced that he expects the company to continue to lose its market share to AMD as the competition has "too much momentum" going for it. AMD's Ryzen and EPYC processors continue to deliver power and efficiency performance figures, which drives customers towards the company. On the other hand, Intel expects a competing product, especially in the data center business with Sapphire Rapids Xeon processors, set to arrive in 2023. Pat Gelsinger noted, "Competition just has too much momentum, and we haven't executed well enough. So we expect that bottoming. The business will be growing, but we do expect that there continues to be some share losses. We're not keeping up with the overall TAM growth until we get later into '25 and '26 when we start regaining share, material share gains."

The only down years that are supposed to show a toll of solid competition are 2022 and 2023. As far as creating a bounceback, Intel targets 2025 and 2026. "Now, obviously, in 2024, we think we're competitive. 2025, we think we're back to unquestioned leadership with our transistors and process technology," noted CEO Gelsinger. Additionally, he had a say about the emerging Arm CPUs competing for the same server market share as Intel and AMD do so, stating that "Well, when we deliver the Forest product line, we deliver power performance leadership versus all Arm alternatives, as well. So now you go to a cloud service provider, and you say, 'Well, why would I go through that butt ugly, heavy software lift to an ARM architecture versus continuing on the x86 family?"

Intel on Thursday confirmed that there will be only four Arc "Alchemist" desktop graphics card SKUs in the retail channel, and that it will be led by the A770 Limited Edition, which maxes out the DG2-512 silicon, and features 17.5 Gbps memory across its 256-bit wide memory bus, putting 560 GB/s of memory bandwidth at its disposal. The A750 uses 16 Gbps memory data-rates, and has 512 GB/s of bandwidth. It turns out, that the mid-range A580 features a 256-bit wide memory bus, and not the previously-reported 192-bit, which means it has the same 512 GB/s bandwidth as the A750. The A580 and A750 come with 8 GB of memory, while the A770 tops out with 16 GB.

Today, Intel Corporation and Broadcom Inc. showcased the industry's first cross-vendor Wi-Fi 7 demonstration, with over-the-air speeds greater than 5 gigabits per second. The trial used an Intel Core processor-based laptop with a Wi-Fi 7 solution connected to a Broadcom Wi-Fi 7 access point.

"We are proud to highlight how next-generation Wi-Fi 7 can make new mobile PC experiences possible. Industry collaboration is essential to ensure we deliver on the promises of this new wireless technology. We would like to thank our colleagues at Broadcom for their great technical cooperation, which helped enable this unprecedented, first-of-its-kind demonstration of ultra-high speed and ultra-low latency Wi-Fi 7," said Carlos Cordeiro, Intel Fellow and Wireless CTO, Client Computing Group, Intel.

Vijay Nagarajan, vice president, Wireless Connectivity Division, Broadcom, said, "Today's milestone sends a clear message: the ecosystem is ready and Wi-Fi 7 is here to deliver extraordinary capacity and blazing fast speeds to extend gigabit broadband. The reliable, low latency communication provided by Wi-Fi 7 is a key element of Broadcom's vision for connecting everything as the Internet evolves to its next iteration replete with immersive experiences. Industry collaboration is key to making this unprecedented connectivity a reality and we were delighted to work with Intel to achieve another industry first."

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 x 16, 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.

The upcoming Intel 13th Gen Core "Raptor Lake" promises to be an overclocker's delight, with an extreme overclocking feat surfacing of an astounding 8 GHz overclock of the chip. There are several riders to this feat. The most obvious being that an engineering sample (and not a retail chip), was used. Extreme cooling, such as liquid-nitrogen was used to keep the feisty chip cool. All 16 of its E-cores were disabled, and the 8 P-cores had HyperThreading disabled.

A stunning 1.792 V core voltage was used, to get the clock speed up to 8000 MHz, with an 80.0 multiplier and 100 MHz base clock. This would be the first Intel processor in around a decade to hit the 8 GHz-mark, with the last one being the i7-5775C "Broadwell." The clock-speed leaderboard is dominated by the AMD FX-8350 and FX-8150, with the unbeaten record being The Stilt's 8772 MHz.

The most juicy bits of the Intel 13th Gen Core "Raptor Lake" launch press-deck just leaked, courtesy of Igor's Lab. They reveal the six SKUs Intel will debut the 13th Gen Core desktop processor series with, highlight key differences with the previous-gen "Alder Lake," and also detail what the new Intel Z790 chipset brings to the table. To begin with, the first-wave of 13th Gen Core processors will include six SKUs—the Core i9-13900K, i9-13900KF, i7-13700K, i7-13700KF, i5-13600K, and the i5-13600KF. The -K and -KF parts are identical to each other, spare for the lack of integrated graphics with the -KF ones.

Many of the key specs of these six SKUs were already leaked to the web along with those of several SKUs from future waves of 13th Gen SKUs, but this slide confirms a handful interesting specs related to power. The slide confirms 125 W as the Processor Base Power value for all six SKUs, 253 W as the Maximum Turbo Power value for the Core i9 and Core i7 K/KF SKUs; and 181 W as the Maximum Turbo Power for the Core i5 K/KF SKUs. This is a definite step up from the 241 W MTP for the previous-gen Core i9, 190 W MTP for the Core i7, and 150 W MTP for the Core i5. Of course, these limits are like a hedge blocking your path, you can relax them in the motherboard BIOS.