Hewlett Packard Enterprise (NYSE: HPE) today announced it is making supercomputing accessible for more enterprises to harness insights, solve problems and innovate faster by delivering its world-leading, energy-efficient supercomputers in a smaller form factor and at a lower price point.

The expanded portfolio includes new HPE Cray EX and HPE Cray XD supercomputers, which are based on HPE's exascale innovation that delivers end-to-end, purpose-built technologies in compute, accelerated compute, interconnect, storage, software, and flexible power and cooling options. The supercomputers provide significant performance and AI-at-scale capabilities to tackle demanding, data-intensive workloads, speed up AI and machine learning initiatives, and accelerate innovation to deliver products and services to market faster.

Intel Corporation today reported third-quarter 2022 financial results. "Despite the worsening economic conditions, we delivered solid results and made significant progress with our product and process execution during the quarter," said Pat Gelsinger, Intel CEO. "To position ourselves for this business cycle, we are aggressively addressing costs and driving efficiencies across the business to accelerate our IDM 2.0 flywheel for the digital future."

"As we usher in the next phase of IDM 2.0, we are focused on embracing an internal foundry model to allow our manufacturing group and business units to be more agile, make better decisions and establish a leadership cost structure," said David Zinsner, Intel CFO. "We remain committed to the strategy and long-term financial model communicated at our Investor Meeting."

ASRock today launched its Arc "Alchemist" A770 and A750 custom-design graphics cards. These include the A770 Phantom Gaming OC, and the A750 Challenger OC. The A770 maxes out the 6 nm ACM-G10 silicon, featuring all 32 Xe Cores (4,096 unified shaders); besides 16 Gbps GDDR6 memory; whereas the A750 gets 28 Xe Cores (3,584 unified shaders), and 16 Gbps GDDR6 memory. Both of ASRock's cards come with 8 GB of memory across a 256-bit wide memory bus, there's no 16 GB version of the A770 Phantom Gaming.

The ASRock A770 Phantom Gaming features a premium, RGB-illuminated cooling solution that's also found in the company's Radeon RX 6000-series Phantom Gaming graphics cards. This card also offers a factory-overclock of 2.20 GHz compared to 2.10 GHz reference. The cooler features a dual fin-stack heatsink with five 6 mm-thick nickel-plated copper heat-pipes that make indirect contact with the GPU over a copper base-plate. The dual ball-bearings fans come with idle fan-stop. There's a switch to manually turn off RGB lighting.

ASUS, a global technology leader renowned for continuously reimagining today's technologies for tomorrow, today announced a new Expert series desktop model, the ExpertCenter D7 SFF (D700SD).

The ExpertCenter D7 SFF is designed for long-term use, giving business users in financial, retail, manufacturing, creative fields, and other industries a durable solution. It's designed to suit growing business needs with tool-free expansion, making this model an investment that can evolve with a business. The case is rotatable and can be fully opened for convenient maintenance and upgrades, with side panels on the chassis that are easily removed without a screwdriver, and a 3.5-inch HDD tool-free tray that enables users to quickly replace or upgrade hard drives.

It's the moment you've been waiting for! (And the moment our teams have been working towards!) The Intel Arc A750 and A770 GPUs will be for sale on October 12th starting at $289 and $329 respectively, with the Arc A770 Limited Edition available for $349. After years of price increases in the massive $200-400 GPU segment, Intel is bringing balance back to the GPU market. Pricing seems to have gone off the deep end and we're working to reel it back in with the Intel Arc A-series GPUs. As we've shown in earlier performance blogs, the Arc A750 and A770 trade blows with the NVIDIA GeForce RTX 3060—a popular mainstream GPU. Intel CEO Pat Gelsinger called out the extreme GPU prices in his Intel Innovation Day 1 keynote, showing that the last four years have seen a nonstop upward trend in prices of mainstream GPUs. By entering the GPU space as a third player, Intel is ready to turn these tides in gamers' favor and disrupt the market.

On average, a new GeForce RTX 3060 will set you back $418. (This number was calculated on Newegg.com, targeting in stock, sold by Newegg, new RTX 3060 cards as of Sept 22, 2022.) Picking up an Intel Arc A750 on October 12th for $289 gets you 53% more performance per dollar on average, or an 8 GB Arc A770 for $329 provides 42% more perf/dollar. Why is that? The Arc A700-series performance beats the 3060 in most modern titles using DirectX 12 or Vulkan APIs and our GPUs aren't far behind in most DX11 games—all for much less cash.

Intel expanded its Arc "Alchemist" desktop graphics card series with the entry-level Arc A310. This GPU has specs that enable Intel's AIB partners to build low-profile graphics cards that are possibly even single-slot, or conventional sized with fanless cooling. The A310 is being pushed as a slight upgrade over the iGPU, and an alternative to cards such as the AMD Radeon RX 6400. Its target user would want to build a 4K or 8K HTPC, or even be a workstation/HEDT user with a processor that lacks integrated graphics, and wants to use a couple of high-resolution monitors. There is no reference board design, but we expect it to look similar to the Arc Pro A40 in dimensions (pictured below), except with full-size DP and HDMI in place of those mDP connectors, and a full-height bracket out of the box.

The A310 is carved out of the 6 nm "ACM-G11" silicon by enabling 6 out of 8 Xe Cores (that's 96 out of 128 EUs, or 768 out of 1,024 unified shaders). You also get 96 XMX units that accelerate AI; and 6 ray tracing units. The GPU runs at 2.00 GHz, compared to 2.10 GHz on the A380. The memory sub-system has been narrowed by a third—you get 4 GB of 15.5 Gbps GDDR6 memory across a 64-bit wide memory interface. In comparison, the A380 has 6 GB of memory across a 96-bit memory bus. The card features a PCI-Express 4.0 x8 host interface, and with its typical power expected to be well under the 75 W-mark, most custom cards could lack any power connectors.

Intel's ambitious XeSS (Xe Super Sampling) performance enhancement formally launched, with the latest "Shadow of the Tomb Raider" patch dated September 27. The patch release notes describes this feature addition as "Added XeSS graphics support for DX12-compatible systems." This means that XeSS not only works in its native XMX code-path for Arc "Alchemist" GPUs, but also the agnostic DP4a code. CapFrameX confirmed that XeSS works with Radeon RX 6000 RDNA2 GPUs, which means the DP4a fallback has been implemented. The XeSS feature-addition to SoTR comes just in time as reviews of the Arc A770 are expected to go live early next month, with availability slated for October 12. You can learn more about XeSS in our older article.

Intel today announced the pricing for the Arc A770 Limited Edition desktop graphics card, and it is set at USD $329, offering a class of performance comparable to NVIDIA and AMD graphics cards around the $400-range. The A770 is a full-feature DirectX 12 Ultimate-capable graphics cards. The Arc A770 Limited Edition maxes out the 6 nm ACM-G10 silicon, features 32 Xe Cores, 512 XMX matrix processors, and 512 EUs, which work out to 4,096 unified shaders. The card comes with 8 GB or 16 GB of 17.5 Gbps GDDR6 memory across a 256-bit wide memory bus. $329 could be the starting price of the A770 for its 8 GB model. Available from October 12.

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.

AAEON's new GENE-ADP6 unlocks the door to elite edge computing, digital signage, and machine vision applications with enhanced features across the board. The GENE-ADP6 provides a 15% improvement in CPU performance through the Intel 12th Generation Core /Celeron CPU (formerly Alder Lake-P), featuring hybrid platform processor architectures with up to 12 cores and 16 threads. Along with an improvement in CPU power, the GENE-ADP6 shows greater AI-readiness, with Intel's Deep Learning Boost AI accelerator providing enhanced inferencing capabilities to make the GENE-ADP6 perfect for 5G and AI edge computing.

For faster, more advanced storage speeds, the GENE-ADP6 introduces 64GB system memory via two dual-channel DDR5 SODIMMs, being AAEON's first 3.5" SubCompact Board to do so. This improvement from DDR4 to DDR5 offers up to 50% faster data transfer speeds and a new, more efficient power management structure. The GENE-ADP6 supports M.2 3052/3042 and M.2 2230 modules, enabling 5G and Wi-Fi for enhanced application connectivity. Additionally, the board's FPC expansion slot provides sophisticated, high-performance PCIe x4 (Gen 4) speed. This also gives users the flexibility to expand the board's additional PCIe x4 slot for machine vision, smart retail and industrial automation applications.

Intel's upcoming Meteor Lake (MTL) processor is set to deliver a wide range of exciting solutions, with the first being the Intel 4 manufacturing node. However, today we have some interesting Linux kernel patches that indicate that Meteor Lake will have a dedicated "Standalone Media" Graphics Technology (GT) block to process video/audio. Moving encoding and decoding off GPU to a dedicated media engine will allow MTL to play back video without the GPU, and the GPU can be used as a parallel processing powerhouse. Features like Intel QuickSync will be built into this unit. What is interesting is that this unit will be made on a separate tile, which will be fused with the rest using tile-based manufacturing found in Ponte Vecchio (which has 47 tiles).

Intel Linux PatchesStarting with [Meteor Lake], media functionality has moved into a new, second GT at the hardware level. This new GT, referred to as "standalone media" in the spec, has its own GuC, power management/forcewake, etc. The general non-engine GT registers for standalone media start at 0x380000, but otherwise use the same MMIO offsets as the primary GT.

Standalone media has a lot of similarity to the remote tiles present on platforms like [Xe HP Software Development Vehicle] and [Ponte Vecchio], and our i915 [kernel graphics driver] implementation can share much of the general "multi GT" infrastructure between the two types of platforms.

Intel Graphics today posted a technological deep-dive video presentation into how XeSS (Xe Super Sampling), the company's rival to NVIDIA DLSS and AMD FSR, works. XeSS is a gaming performance enhancement technology where your game is rendered by the GPU at a lower resolution than what your display is capable of; while a high-quality upscaling algorithm scales it up to your native resolution while minimizing quality losses associated with classical upscaling methods.

The video details mostly what we gathered from our older articles on how XeSS works. A game's raster and lighting is rendered at a lower-resolution, frame-data along with motion vectors are fed to the XeSS upscaling algorithm, and is then passed on to the renderer's post-processing and the native-resolution HUD is applied. The XeSS upscaler takes not just motion vector and the all important frame inputs, but also temporal data from processed (upscaled) frames, so a pre-trained AI could better reconstruct details.

EK Fluid Works, a high-performance workstation manufacturer, is expanding its Compute Series with a rackmount liquid-cooled GPU server, the X7000-RM. The EK Fluid Works Compute Series X7000-RM is tailor-made for high-compute density applications such as machine learning, artificial intelligence, rendering farms, and scientific compute simulations.

What separates the X7000-RM from similar GPU server solutions is EK's renowned liquid cooling and high compute density. It offers 175% more GPU computational power than air-cooled servers of similar size while maintaining 100% of its performance output no matter the intensity or duration of the task. The standard X7000-RM 5U chassis can be equipped with an AMD EPYC Milan-X 64 Core CPU, up to 2 TB of DDR4 RAM, and up to seven NVIDIA A100 80 GB GPUs for the ultimate heavy-duty GPU computational power. Intel Xeon Scalable single and dual socket solutions are also possible, but such configurations are limited to a maximum of five GPUs.

Intel Arc Alchemist graphics cards span both gamer and creator/professional user market sector, where we witnessed Intel announce gamer and pro-vis GPU SKUs. Today, we are seeing the usage of the flagship Arc Alchemist SKU called A770 in Blender rendering with ray tracing enabled. The GPU is designed to have a DG2-512 GPU with 512 EUs, 4096 Shading Units, 16 GB of GDDR6 memory, and 32 Xe cores for ray tracing, be a powerhouse for games, and handle some professional software as well. At SIGGRAPH 2022, Bob Duffy, Intel's Director of Graphics Community Engagement, showcased a system with Arc A770 GPU running Blender Cycles with ray tracing and denoising.

While we don't have any comparable data to showcase, the system managed to produce a decent rendering in Blender 3.3 LTS release, using Intel's oneAPI. The demo scene had 4,369,466 vertices, 8,702,031 edges, 4,349,606 faces, and 8,682,950 triangles, backed by ray tracing and live denoising. We are yet to see more detailed benchmarks and how the GPU fares against the competition.

Intel Graphics, with its latest Graphics Drivers 31.0.101.3222, changed the coverage of its latest driver updates. The company would be providing game optimizations and regular driver updates only for its Gen12 (Iris Xe), and Arc "Alchemist" graphics products. Support for Gen9, Gen9.5, and Gen11 iGPUs integrated with 6th, 7th, 8th, 9th, and 10th generations of Intel processors, namely "Skylake," "Kaby Lake," "Coffee Lake," "Ice Lake," and "Cascade Lake," will be relegated to a separate, quarterly driver update cycle, which only covers critical updates and security vulnerabilities, but not game optimizations.

Intel's regular Graphics Driver cycle that includes Day-0 optimizations timed with new game releases, will only cover the Gen12 Xe iGPUs found in 11th Gen "Tiger Lake," "Rocket Lake," and 12th Gen "Alder Lake" processors; besides the DG1 Iris Xe graphics card; and Arc "Alchemist" discrete GPUs. Version 31.0.101.3222 appears to be a transitioning point, and so it has drivers from both branches included within a 1.1 GB package (the main branch supporting game optimizations for new GPUs, and the legacy branch for the older iGPUs). You can grab this driver from here.

Remember that Limited Edition card that Intel was teasing at the end of March? Well, it turns out that it could very well be the Arc A750 card, at least based on a quick appearance of a card in Gamer Nexus' review of the Gunnir Arc A380 card. For a few seconds in the review video, Gamers Nexus was showing off a card that looked nigh on identical to the renders Intel showed back in March. There was no mention of any specs or anything else related, except that Gamer Nexus has tested the card and that it will presumably be getting its own video in the near future based on what was said in the video.

Based on leaked information, the Arc A750 GPU should feature 24 Xe cores, 3072 FP32 cores and it's expected to be paired with 12 GB of GDDR6 memory on a 192-bit bus. For reference, the Arc A380 features eight Xe cores, 1024 FP32 cores and the cards ship with 6 GB of GDDR6 memory on a 96-bit bus. In related news, Intel is said to be touring some gaming events in the US promoting its yet unavailable Arc graphics cards. LANFest Colorado is said to be the first stop, so if you're planning on attending, this could be your first chance to get some hands-on time with an Arc graphics card.

Intel's upcoming family of Arc Alchemist mobile graphics cards is just around the corner, and we are already starting to spot the company's reference systems utilizing the latest dedicated graphics. Thanks to the findings of @momomo_us, we have information that Intel is readying the NUC X15 laptop reference system codenamed "Alder Country." There are two SKUs, LAPAC71G and LAPAC71H, each with similar CPU and GPU configurations. Carrying an Intel Core i7-12700H processor with 14 cores and 20 threads, the CPU is paired with either Arc A550M on the LAPAC71G SKU or Arc A730M on LAPAC71H SKU.

As a reminder, Intel already made such NUC X15 reference laptop designs with Tiger Lake processors. However, they came with NVIDIA GeForce RTX 30 graphics instead of Intel Arc Alchemist. Implementations of NUC X15 appeared with partners such as ADATA XPG Xenia laptop. We could expect to see more OEMs adapt Alder Country if the performance of Arc Alchemist graphics proves good.

With the new VIA 15 Pro, SCHENKER has put together a unique overall package: The 1.45 kg ultrabook integrates AMD's efficient eight-core Ryzen 7 5700U, a 15.6 inch WQHD IPS display and two freely accessible and upgradeable M.2 SSD and RAM slots - a combination that is usually only found in significantly heavier gaming laptops with dedicated graphics cards. Unlike these, however, the VIA 15 Pro features AMD's energy-efficient, integrated Radeon graphics unit. With this outfit, the ultrabook is aimed at developers, programmers, and creative professionals, among others. The all-round office laptops SCHENKER WORK 15 and WORK 17 are also being updated with Intel's Alder Lake-P processors.

One of the most striking features of the SCHENKER VIA 15 Pro is a performance-enhanced AMD Ryzen 7 5700U with eight cores and 16 threads: instead of running the CPU with a TDP of 15 watts, which is common in the ultrabook sector, it can operate permanently at 35 watts in the highest performance profile ("enthusiast") - this way, it outperforms the majority of ULV processors and achieves a multi-score of 3937 points in Cinebench R20. The laptop's dual-fan cooling system was adopted from the 2020 predecessor model of the VIA 15 Pro, so it is designed for less efficient CPUs from the 54 watt TDP class and therefore guarantees superior and quiet cooling. Those who require somewhat less performance may select the medium performance profile ("balanced") for particularly quiet operation. Switching is possible in real time at the touch of a button via a keyboard shortcut.

One of the biggest dividends of the Arc discrete graphics lineup for Intel is getting to use its own GPUs in its NUC desktops. The next-generation NUC 12 "Serpent Canyon" desktop sees the 11th Gen Core "Tiger Lake" quad-core + RTX 2060 "Turing" combination replaced by advanced 12th Gen Core "Alder Lake" 6P+8E processor, and the Arc "Alchemist" A770M discrete GPU. Intel's choice of mobile versions of "Alchemist" and "Alder Lake" may have to do with not just lower TDP, but possibly also an implementation of the Intel Deep Link feature.

The A770M maxes out the 6 nm ACM-G11 silicon, packing 32 Xe Cores (512 execution units, or 4,096 unified shaders), and has 16 GB of 256-bit GDDR6 memory. When paired with the 14-core "Alder Lake-H" processor, the duo could make for a formidable performance-gaming and creator machine. "Serpent Canyon" also sees the integration of Thunderbolt 4, SDXC UHS-II, Wi-Fi 6E, and 2.5 GbE interfaces, along with a number of USB 3.2 ports. Although its marketing images are leaked to the web on Chinese social media, there's no release date for the thing yet, but it could be just around the corner.

AAEON continues to innovate and improve with the introduction of their UP Squared 6000 Edge Computing Kit, which offers customers elite, exclusive features in a plug-and-play industrial turnkey solution powered by the Intel Atom x6425RE SoC (formerly Elkhart Lake).

An upgrade from the UP Squared 6000 Edge, the UP Squared 6000 Edge Computing Kit provides a wealth of additional features while only outgrowing its predecessor's form factor by 1 centimeter in height. This centimeter houses an integrated carrier board containing a HAT2-compatible 40-pin PSE header, doubling the expansion options available compared to previous iterations of the UP Board series. This is in addition to an already impressive I/O, which features four Gigabit Ethernet ports, two COM ports, three USB 3.2 ports, along with three M.2 sockets to incorporate AI, SSD, 5G, and Wi-Fi5/6 modules.

During the International Supercomputing Conference on May 31, 2022, in Hamburg, Germany, Jeff McVeigh, vice president and general manager of the Super Compute Group at Intel Corporation, announced Rialto Bridge, Intel's data center graphics processing unit (GPU). Using the same architecture as the Intel data center GPU Ponte Vecchio and combining enhanced tiles with Intel's next process node, Rialto Bridge will offer up to 160 Xe cores, more FLOPs, more I/O bandwidth and higher TDP limits for significantly increased density, performance and efficiency.

"As we embark on the exascale era and sprint towards zettascale, the technology industry's contribution to global carbon emissions is also growing. It has been estimated that by 2030, between 3% and 7% of global energy production will be consumed by data centers, with computing infrastructure being a top driver of new electricity use," said Jeff McVeigh, vice president and general manager of the Super Compute Group at Intel Corporation.

Hot Chips 34, the upcoming semiconductor conference from Sunday, August 21 to Tuesday, August 23, 2022, will feature many significant contributions from folks like Intel, AMD, Tesla, and NVIDIA. Today, thanks to Intel's registration at the event, we discovered that the company would present its work on Meteor Lake and Arrow Lake processors with the novel Foveros 3D packaging. The all-virtual presentation from Intel will include talks about Ponte Vecchio GPU and its architecture, system, and software; Meteorlake and Arrowlake 3D Client Architecture Platform with Foveros; and some Xeon D and FPGA presentations. You can see the official website here for a complete list of upcoming talks.

As a little reminder, Meteor Lake is supposed to arrive next year, replacing the upcoming Raptor Lake design, and it has already ahs been pictured, which you can see below. The presentation will be recorded and all content posted on Hot Chips's website for non-attendees to catch up on.

GIGABYTE Technology, an industry leader in high-performance servers and workstations, today announced a new supercharged, scalable server, G492-PD0, that supports an Ampere Altra Max or Altra processor with NVIDIA HGX A100 Tensor Core GPUs for the highest performance in cloud infrastructure, HPC, AI, and more. Leveraging Ampere's Altra Max CPU with a high core count, up to 128 Armv8.2 cores per socket with Arm's M1 core, the G492-PD0 delivers high performance efficiently and with minimized total cost of ownership.

GIGABYTE developed the G492-PD0 in response to a demand for high-performing platform choices beyond x86, namely the Arm-based processor from Ampere. This new G492 server was tailored to handle the performance of NVIDIA's baseboard accelerator without compromising or throttling CPU or GPU performance. This server joins the existing line of GIGABYTE G492 servers that support the NVIDIA HGX A100 8-GPU baseboard on the AMD EPYC platform (G492-ZL2, G492-ZD2, G492-ZD0) and Intel Xeon Scalable (G492-ID0).

With its desktop graphics card lineup still elusive, the company is planning a new entry-level SKU positioned below the Arc A380 and A350M. Called A310, this chip will be based on a heavily cut-down version of the DG2-128 (ACM-G11) silicon, and offer performance levels somewhere between the Iris Xe MAX (DG1) desktop discrete GPU, and the A350M, with the design goal being to compete with AMD's Radeon RX 6400 and NVIDIA's GTX 1650 in the entry-level space.

At this point the core configuration of the A310 is not known. It is speculated to feature 64 to 96 execution units (EU) out of the 128 present on the ACM-G11 silicon. 4 GB of GDDR6 memory across a 64-bit wide memory bus, could remain standard fare for this card. All of the media-acceleration features of "Alchemist" could be featured, including AV1 decode and encode. The A310 could make for a good combo with future Intel workstation or HEDT platforms with non-gaming visual requirements. The ACM-G11 is built on the 6 nm silicon fabrication process, and so the A310 could come with a low power footprint that doesn't need additional power connectors.

Intel's recently announced Arc "Alchemist" line of discrete gaming graphics processors consists of at least five mobile SKUs across the Arc 3, Arc 5, and Arc 7 lines; with desktop SKUs expected later this year. These are based on one of two ASICs—the DG2-128 (ACM-G11) and the DG2-512 (ACM-G10), both built on the TSMC N6 (6 nm) silicon fabrication process. Coelacanth's Dream discovered a third ASIC when digging through Intel Graphics Compiler code on GitHub, referred to as the "ACM-G12."

This silicon has exactly half the amount of number-crunching machinery as the DG2-512, and features 256 execution units (EU), or 16 Xe cores, working out to 2,048 unified shaders—double that of the DG2-128, but half that of the DG2-512. Interestingly, the Arc 5 A550M mobile GPU announced last week has specifications corresponding to this silicon, even though it was announced to be a heavily cut-down DG2-512. Intel probably figures that at some point making A550M GPUs using DG2-512 could mean cutting down perfectly functional silicon, and so it makes sense to manufacture physically smaller dies (more dies per wafer). There are no other known specs of the ACM-G12. It's quite likely given the rest of its alignment with the A550M's specs that it could feature a 128-bit wide GDDR6 memory interface.