Intel has confirmed that its Arc A750 graphics card has reached end-of-life, as outlined in Product Change Notification #856777‑00 published yesterday. This announcement marks the beginning of the end for a model that arrived just two and a half years ago, and it offers partners a clear timetable for winding down orders and shipments. Customers should mark June 27, 2025, as their final opportunity to submit discontinuance orders for the Arc A750. After that date, no new orders will be accepted. All remaining units are slated for delivery by September 26, 2025. Intel recommends that system builders, integrators, and distributors assess their inventory and projected needs now and then place any last orders before the cutoff. Should questions arise, field sales representatives stand ready to assist. Do note that end of life here means end of manufacturing, not end of support. Intel will continue to provide driver and quality of life updates to these Arc Alchemist GPUs.

When it launched in October 2022, the Arc A750 staked its claim in the performance segment of Intel's market-entry discrete GPU lineup. Based on the DG2‑512 processor in its ACM‑G10 form, the card leveraged TSMC's 6 nm to pack 21.7 billion transistors into a 406 square millimeter die. With 3,584 shading units, 224 texture units, and 112 ROPs, it delivered strong raster throughput. Its 28 ray‑tracing cores and 448 tensor cores brought hardware‑accelerated lighting and machine-learning inference within reach of mainstream gamers and creators alike. At the board level, the A750 features 8 GB of GDDR6 memory, running at an effective 16 Gbps across a 256-bit bus, which yields 512 GB/s of bandwidth. A base clock of 2,050 MHz could be boosted to 2,400 MHz, while a dual-slot design drew up to 225 W via one 6-pin and one 8-pin connector. Video outputs included HDMI 2.1 and three DisplayPort 2.0 ports, all bridged to the host system over PCI‑Express 4.0 x16.

Intel is officially stepping back from its Deep Link suite of technologies. The confirmation came through a company representative on GitHub, confirming that active development has ceased. This follows a period when Intel quietly stopped highlighting Deep Link in newer offerings, such as its "Battlemage" GPUs. While the features might still work for those currently using Deep Link, don't expect any future updates or official assistance from Intel's support channels. If you cast your mind back to late 2020, you might recall Intel launching Deep Link. The core idea was to get Intel CPUs and their dedicated Arc GPUs working more effectively in tandem. To tap into this, you needed a specific setup: an 11th, 12th, or 13th Generation Intel CPU alongside an Arc Alchemist GPU. The package featured key tools: Dynamic Power Share for optimizing power between the CPU and GPU, Stream Assist to offload streaming to integrated graphics, Hyper Encode for faster video encoding, and Hyper Compute to accelerate AI tasks using OpenVINO.

These were designed to give a leg up to applications like OBS, DaVinci Resolve, and Handbrake. However, the writing may have been on the wall for Deep Link. Intel's "Meteor Lake" chips, which arrived in late 2023, weren't on the compatibility list, hinting that development had already wound down. Getting these features to perform reliably wasn't always straightforward, with users, like the one on GitHub who raised the initial question, reporting difficulties even with supported hardware. A user tried running Core Ultra 200S with Battlemage in OBS, facing issues not by the software, but by Intel's drivers. The general thinking is that Intel might have viewed Deep Link as a bit of a niche feature, possibly concluding that the continued effort and investment, especially with the need for validation with each software vendor, wasn't paying off. As for what's next, Intel hasn't announced a direct successor to these specific integrated features.

Earlier in the week, reports indicated the potential introduction of an Intel Xe2 "Battlemage" B770 gaming graphics card at Computex 2025. Last night, a Team Blue tweet confirmed forthcoming product unveilings: "new Intel Arc Pro GPUs are on the way. See you in Taipei!" In the months leading up to this important trade event, industry watchdogs have drummed up speculation about "Battlemage's" future (or fate). Whispers of 24 GB VRAM-equipped variants emerged late last year—around late January, these theories were connected to an official leak: "3 new PCI IDs for BMG."

Unsurprisingly, VideoCardz has weighed in with some new inside track info—they propose that one of Intel's upcoming professional options will be an "Arc Pro B60 24 GB" model, aka "Developer Edition" (an alleged in-house reference). Despite Sparkle HQ downplaying recent "rogue claims," a company rep (in China) alluded to a possible May/June release of their own custom 24 GB "Battlemage" productivity-oriented card. VideoCardz has picked up on rumors, regarding the "Arc Pro B60's" internal setup. They propose Team Blue's selection of the familiar "BMG-G21" GPU; as used by their Arc Xe2 B580 12 GB and B570 10 GB designs. According to an unnamed inside source, this professional/workstation variant will stick with the usual 192-bit memory interface. Intel's Computex 2025 new product teaser provided a big clue about the speculated "B60" model's cooling solution.

Die shots of Intel's "Arrow Lake" desktop processors have appeared online, confirming the chiplet design we have known about since the launch. The images annotated by the YouTube channel HighYield show a four‑tile arrangement mounted on a base die made with Intel's 22 nm FinFET process. The compute tile sits at the top left, built on TSMC's N3B node and covering 117.24 mm². To its right are the SoC tile on TSMC's N6 node measuring 86.65 mm², and the GPU tile, which houses four Xe cores alongside an Arc Alchemist render slice. The I/O tile, at 24.48 mm² on the same N6 node, completes the group at the bottom left. Intel has redesigned its hybrid core layout for Arrow Lake, moving away from separate P‑core and E‑core clusters. Four of the eight high‑performance P‑cores line the die's outer edges, with the remaining four in the center. In between these lie the four efficiency E‑core clusters, each sharing 3 MB of L2 cache. A unified 36 MB L3 cache ring bus connects to every core, allowing E‑cores to tap into that larger cache pool for the first time. Intel aims to spread heat more evenly and boost background task performance.

The I/O tile integrates Thunderbolt 4 controllers, PCIe buffers and PHYs. The SoC tile carries display engines, media accelerators and DDR5 memory controllers. All tiles are bonded to the base die via Intel's Foveros Omni stacking technology. Arrow Lake also reflects a shift in Intel's manufacturing strategy. Plans to use Intel's 20A node were dropped in favor of TSMC processes, making this the first desktop CPU from Intel that relies almost entirely on external foundries. On the software side, Intel has begun offering its IPO profiles in select prebuilt systems. These presets optimize CPU and memory settings for a hassle‑free performance boost that remains within warranty limits. Meanwhile, the native 200S Boost overclocking option is rolling out via BIOS updates. Early tests suggest that 200S Boost alone yields modest gains unless paired with very high-speed DDR5 modules, while IPO profiles deliver more consistent improvements with mainstream memory configurations.

Intel along the sidelines of the 2025 GDC announced the release of the XeSS 2 SDK on the company's GitHub page. This makes it possible for any game developer to understand XeSS 2 and integrate it with their current and upcoming games, covering features such as XeSS 2 upscaling, XeSS 2 frame generation, and XeSS 2 Low Latency. Intel released the XeSS 2 feature-set with its Arc B-series "Battlemage" graphics cards, it is backwards compatible with Arc A-series "Alchemist" discrete GPUs that support XMX matrix math acceleration. XeSS 2 uses an AI DNN to reconstruct details in upscaled images, making it technologically closer to DLSS than to AMD FSR. Next up, Intel also announced that it has updated its first-party programming guides, its Unreal Engine plugin, and its XeSS Inspector software development tool, to each support XeSS 2, including its upscaling, frame-generation, and low-latency components.

Perhaps the more important development in the Intel Graphics team right now is that the company announced that it has laid the groundwork to implement Neural Rendering, or at least the parts that are standardized under the latest updates to DirectX 12, bringing the benefits of DirectX Cooperative Vectors to game developers. It will soon be possible for 3D applications to directly address the XMX engines on Arc A-series and B-series GPUs for an up to 10x gain in inference performance for neural texture compression.

Last December, Intel revealed that its next-generation "Celestial" GPU architecture was "complete." At the time, Team Blue's Tom "TAP" Petersen revealed: "our IP that's kind of called Xe3, which is the one after Xe2, that's pretty much baked... And so the software teams have a lot of work to do on Xe3. The hardware teams are off on the next thing (aka Xe4/Druid), right." Noted Intel inside info leaker—Raichu—believes that "Celestial" will be: "different from Panther Lake, Celestial dGPU looks like will maybe be based on Xe3P instead of Xe3. I estimate it will (be) based on INTC's process instead of outside." Their Friday evening (February 14) social media declaration suggests that Team Blue is bringing things in-house for the manufacturing of discrete "Celestial" graphics cards; utilizing an Intel Foundry node process, rather than rely on TSMC once more. The latter's foundry produced the Arc "Alchemist" and "Battlemage" dGPU generations.

Intel's rumored "Xe3P" architecture is not a fully known quantity, but reports from last November pointed to the existence of multiple "Xe3" variants; courtesy of information gleaned from an employee's LinkedIn profile. Over the past two weeks, we have witnessed plenty of leaks alluding to future Intel CPU families, but the flow of Arc graphic solutions-related leaks seemingly slowed down around the launch of Intel's budget-friendly "Battlemage" B570 card. Recent-ish insider disclosures have uncovered a possible expansion of the current-gen Arc series, with more SKUs rumored to be on the way. A certain group of industry watchdogs reckon that the unannounced "BGM-G31" GPU will be the basis for higher-end "Battlemage" B-series models, but others believe that options above B580 and B570 are canceled—potentially paving the way for "Xe3P-based" C-series designs later this year, or in 2026.

FunkyIT scored an ASRock Arc B580 Steel Legend 12 GB "Battlemage" graphics card that they previewed on their channel. The card appears fairly large, considering that Intel is positioning the B580 to be an upper-mid range GPU, if we go by the naming convention of the previous "Alchemist" generation, and the A580. The ASRock Steel Legend product features a large, aluminium dual fin-stack cooler featuring a trio of fans, and what looks like a metallic, dual-tone cooler shroud and backplate combo. The PCB underneath is a little over half the length of the card, which means nearly half the heatsink's airflow passes through the card and out large cutouts in the backplate.

The card draws power from a pair of 8-pin PCIe power connectors, a combination rated for up to 375 W power delivery. Previous leaks suggest that the ASRock B580 Steel Legend features RGB lighting in the form of a large Steel Legend ornament on top of the card, and the three fans each feature RGB LED lighting. FunkyIT also showed off the retail box of the card. There's no change in the Intel Arc main branding, but attention is given to the Intel XeSS technology logo, which mentions "AI Upscaling." The XMX cores, which are the main AI acceleration hardware on discrete Arc GPUs, get their own separate branding on the box. Intel isn't just going after gamers, but also creators, and AI acceleration markets. "Play, Create, Generate," reads the box.

Sparkle introduced an interesting new graphics card meant for those with four high-resolution displays tied to a workstation, or a digital-signage setup. The new Arc A310 OmniView is based on an underclocked version of the Intel Arc A310 "Alchemist," with the idea being to cap the card at 50 W typical power. The card comes with a 1.00 GHz GPU clock and 15.5 Gbps memory speed, compared to the reference A310, which ticks at 1.75 GHz, but at 75 W typical board power. The card comes with 6 Xe cores, and a 64-bit wide memory interface, pulling 4 GB of GDDR6 memory. The A310 OmniView features a single-slot, full-height design, with no additional power connectors. It uses a simple fan-heatsink to keep cool. Perhaps the most striking aspect of the card is its display I/O, featuring four HDMI 2.0b ports, each of which can drive a 4K display at 60 Hz. The card is 14.5 cm long, and 10.5 cm tall. The company didn't reveal pricing.

Intel on Monday rolled out the first public release of AI Playground, an AI productivity suite the company showcased in its 2024 Computex booth. AI Playground is a well-packaged suite of generative AI applications and a chatbot, which are designed to leverage Intel Arc discrete GPUs with at least 8 GB of video memory. All utilities in the suite are designed under the OpenVINO framework, and take advantage of the XMX cores of Arc A-series discrete GPUs. Currently, only three GPU models from the lineup come with 8 GB or higher amounts of video memory, the A770, A750, and A580; and their mobile variants. The company is working on a variant of the suite that can work on Intel Core Ultra-H series processors, where it uses a combination of the NPU and the iGPU for acceleration. AI Playground is open source. Intel put in effort to make the suite as client-friendly as possible, by giving it a packaged installer that looks after installation of all software dependencies.

Intel AI Playground tools include an image generative AI that can turn prompts into standard or HD images, which is based on Stable Diffusion backed by DreamShaper 8 and Juggernaut XL models. It also supports Phi3, LCM LoRA, and LCM LoRA SDXL. All of these have been optimized for acceleration on Arc "Alchemist" GPUs. The utility also includes an AI image enhancement utility that can be used for upscaling along with detail reconstruction, styling, inpainting and outpainting, and certain kinds of image manipulation. The third most important tool is the text AI chatbot with all popular LLMs.

DOWNLOAD: Intel AI Playground

Welcome to another slow-ish week of new games, but from next week it looks like things will start to pick up again after about a month of lesser releases. At least this week there are a few more interesting titles and this week's major release is a post-apocalyptic open-world survival game from China. As for the other new releases, we have sheeps, an alien invasion of sorts, a game about an intergalactic freelance adventurer, a lot of shoes and finally some alchemy.

Once Human / This week's major release / Tuesday 9 July
The apocalypse changed everything. Human, animal, plant… all are infested by an alien creature—Stardust. As a Meta-Human, you can survive the contamination and use the power of Stardust. Play alone or join others to fight, build and explore. When the world is in chaos, you are our last hope. You wake up in the middle of nowhere. You'll have to brace yourself for the cruelty of nature (from monsters to lack of food); however, Stardust's influence does not restrict to living things, it also affects the soil and water. Eating polluted food and drinking dirty water will reduce your Sanity. When your Sanity drops, your max HP would drop accordingly. To eat or not to eat, it's a question. Steam link

Intel has reportedly chosen the TSMC 4 nm EUV foundry node for its next generation Arc Xe2 discrete GPUs based on the "Battlemage" graphics architecture. This would mark a generational upgrade from the Arc "Alchemist" family, which Intel built on the TSMC 6 nm DUV process. The TSMC N4 node offers significant increases in transistor densities, performance, and power efficiency over the N6, which is allowing Intel to nearly double the Xe cores on its largest "Battlemage" variant in numerical terms. This, coupled with increased IPC, clock speeds, and other features, should make the "Battlemage" contemporary against today's AMD RDNA 3 and NVIDIA Ada gaming GPUs. Interestingly, TSMC N4 isn't the most advanced foundry node that the Xe2 "Battlemage" is being built on. The iGPU powering Intel's Core Ultra 200V "Lunar Lake" processor is part of its Compute tile, which Intel is building on the more advanced TSMC N3 (3 nm) node.

Intel very much does intend to make discrete gaming GPUs based on its Xe2 "Battlemage" graphics architecture, which made its debut with the Core Ultra 200V "Lunar Lake-MX" processor as an iGPU. With its next generation, Intel plans to capture an even bigger share of the gaming graphics market, both on the notebook and desktop platforms. "Battlemage" will be crucial for Intel, as it will be able to make its case with Microsoft and Sony for semi-custom chips, for their next-generation consoles. Intel has all pieces of the console SoC puzzle that AMD does. A Xe2 "Battlemage" discrete GPU sample, codenamed "Churchill Falls," has been spotted making its transit in and out of locations known for Intel SoC development, such as Bangalore in India, and Shanghai in China.

Such shipping manifests tend to be incredibly descriptive, and speak of an Arc "Battlemage" X3 and Arc "Battlemage" X4 SKUs, each with 448 execution units (EU), across 56 Xe cores. Assuming an Xe core continues to have 128 unified shaders in the "Battlemage" architecture, you're looking at 7,168 unified shaders for this GPU, a staggering 75% increase in just the numerical count of the shaders, and not accounting for IPC increase and other architecture-level features. The descriptions also speak of a 256-bit wide memory bus, although they don't specify memory type or speed. Given that at launch, the Arc A770 "Alchemist" was a 1440p-class GPU, we predict Intel might take a crack at a 4K-class GPU. Besides raster 3D performance, Intel is expected to significantly improve the ray tracing and AI performance of its Xe2 discrete GPUs, making them powerful options for creative professionals.

According to the report from Phoronix, the upcoming Linux 6.11 kernel will introduce initial display support for the highly anticipated Intel Battlemage graphics processors. Battlemage, built on Intel's Xe2 architecture, represents the company's latest effort to challenge established players in the graphics arena. This new line of GPUs is designed to succeed the current DG2/Alchemist hardware, promising enhanced performance and improved power efficiency. The Linux 6.11 kernel will provide the fundamental capability to drive displays connected to Battlemage GPUs. While this initial support is a crucial first step, it lays the groundwork for more comprehensive functionality in future updates. Linux users and developers can look forward to testing and providing feedback on these new graphics solutions.

Intel's focus on power efficiency is evident in the features accompanying Battlemage support. The kernel will introduce Panel Replay functionality, a technology aimed at reducing display power consumption. This aligns with the growing demand for energy-efficient computing solutions, particularly in mobile and laptop segments. However, the work is far from complete. Intel's Linux graphics driver team continues to refine and optimize Battlemage support, with the goal of delivering a seamless experience by the time these GPUs hit the market later this year. The introduction of Battlemage support not only expands options for Linux users but also intensifies competition in the GPU market, potentially driving innovation across the industry. With promises of up to 1.5x over the previous generation Arc GPUs, we are in for a decent upgrade this year.

According to the latest report from ComputerBase, Intel had a strong presence at the recently concluded Embedded World 2024 conference. The company officially showcased its Arc series of GPUs for the embedded market, based on the existing Alchemist chips rebranded as the "E series." However, industry whispers hint at a more significant development—the impending launch of Intel's second-generation Arc Xe² GPUs, codenamed "Battlemage," potentially before the lucrative Black Friday shopping season. While Alchemist serves as Intel's current offering for embedded applications, many companies in attendance expressed keen interest in Battlemage, the successor to Alchemist. These firms often cover a broad spectrum, from servers and desktops to notebooks and embedded systems, necessitating a hardware platform that caters to this diverse range of applications.

Officially, Intel had previously stated that Battlemage would "hopefully" arrive before CES 2025, implying a 2024 launch. However, rumors from the trade show floor suggest a more ambitious target—a release before Black Friday, which falls on November 29th this year. This timeline aligns with Intel's historical launch patterns, as the original Arc A380 and notebook GPUs debuted in early October 2022, albeit with a staggered and limited rollout. Intel's struggles with the Alchemist launch serve as a learning experience for the company. Early promises and performance claims for the first-generation Arc GPUs failed to materialize, leading to a stuttering market introduction. This time, Intel has adopted a more reserved approach, avoiding premature and grandiose proclamations about Battlemage's capabilities.

Intel on Wednesday released the XeSS 1.3 performance enhancement, which works with Intel Arc "Alchemist" discrete GPUs, and Intel Arc iGPUs powering the Core Ultra "Meteor Lake" processors. The new super sampling technology brings several under-the-hood improvements to the upscaler, which improves image quality at a given resolution. Intel leveraged this improved upscaler to rework the resolution-scale of each performance preset, thereby improving performance per preset; while also introducing new presets at both ends of the resolution scale. The company released the XeSS 1.3 SDK on GitHub, so developers can begin exploring the tech and implementing it on their games.

The XeSS 1.3 update is predicated on an improved upscaler. Intel says that it has updated the AI models with new optimizations, and additional pre-training, particularly with difficult to upscale elements (such as meshes, as in textures with a lot of alpha pixels). The updated upscaler offers better reconstruction of detail, better AA, less ghosting, and improved temporal stability. Intel then used this up change the resolution scale across all its presets as detailed in the table below. It introduced the new Ultra Performance preset that does a 3.0x resolution scale, something that didn't exist in the previous versions of XeSS. On the other end of the spectrum is Native AA, a mode that has zero upscaling, but just the full application of the upscaler as a varnish—this is essentially Intel's take on DLAA.

Phoronix has taken a short break away from monitoring the latest goings-on at AMD's software department—the site's editor-in-chief, Michael Larabel, took a moment to investigate patch notes relating to Intel's Xe and i915 Linux kernel graphics drivers. Earlier today, he noticed that "two additional PCI IDs" have been added to Team Blue's DG2/Alchemist family. This discovery prompted further sleuthing—after: "some searching and turning up hits within the Intel Compute Runtime code, 0x56BE is for an Intel Arc Graphics A750E variant and 0x56BF is for an Intel Arc Graphics A580E."

The aforementioned GPU identification codes seem to exist in gray area—the patch notes do not reveal whether these new variants are destined for desktop or mobile platforms. VideoCardz cited a remark made by "Bionic_Squash"—the reputable leaker reckons that the: "IDs are linked to Intel's Arc Embedded series. This family is tailored for industrial, business, and commercial applications, ranging from edge systems to powering large interactive screens." It is highly likely that Intel is paving the way for embedded/low-power variants of its existing Arc A750 and A580 GPUs. Tom's Hardware proposes that Team Blue is clearing out its inventory of remaining Alchemist silicon ahead of a successive generation's rollout—Battlemage is a major priority in 2024.

SPARKLE unveiled its low-profile series around mid-January—this lineup included an Intel Arc A380 GENIE dual-fan/dual-slot model and an Arc A310 ECO (single-slot, single-fan config) card. Compact device expert/YouTuber, ETA Prime, has uploaded a fascinating video that covers a modification project that involved a hybridization of SPARKLE's latest low-profile graphics cards and a Minisforum MS-01 test system. SPARKLE has released various models based on Intel's "Alchemist" Arc A380 6 GB GPU, but their PCB design is shared across a range of cooling options. ETA Prime could not source an aftermarket lower-profile cooler for his SPARKLE A380 GENIE, so he resorted to cannibalizing the A310 ECO model for relevant parts.

The ECO's single-slot cooling solution was not well proportioned enough to make contact with the SPARKLE A380 GENIE's VRM, so ETA Prime had to "add an aftermarket heatsink." He sold the remaining unneeded pieces—A310 board and GENIE cooler—to a friend for $60. The resultant hybrid—the "world's first-ever single-slot Intel Arc A380"—was bunged into the SFF Minisforum MS-01 test system. Notable specs included the Intel Core i9-13900H CPU and 32 GB of DDR5-5200 RAM. ETA Prime utilized Acer's Predator BiFrost graphics card utility to "trick" in a stable 54 W power limit. 60-ish FPS performance results—with low-to-medium settings at 1080p across a selection of games—were promising, especially for a restrictive small form factor build. ETA Prime hopes that SPARKLE will launch a smaller A380 model in the future—alternatively a specialist firm could produce a nice aftermarket copper part.

Tulpar, an emerging PC gaming hardware company, has been doing the rounds across several European tech events—they demoed Meteor Lake-powered handheld devices at last month's Intel Extreme Masters tour stop in Katowice, Poland. A Hardwareluxx Germany report presented evidence of the Turkish company expanding into graphics card market sectors—Tulpar exhibited their "customized" Intel Arc A770 16 GB model at a recent trade show in Berlin. Andreas Schilling, resident editor at Hardwareluxx, realized that Tulpar had simply rebadged and color adjusted ASRock's Arc A770 Phantom D OC card design.

Tulpar's product placard boasted about their own "3X Cooling System"—a thin renaming of the already well-known ASRock Phantom Gaming triple-fan cooling solution. Their reliance on OEM designs is not a major revelation—the Tulpar 7-inch handheld gaming PC appears to be based on an existing platform—somewhat similar to Emdoor's EM-GP080MTL. Company representatives estimate that their "first dedicated gaming GPU" will be hitting retail within the third quarter of this year. News outlets have questioned this curious launch window—first generation Intel Arc "Alchemist" graphics cards (released in late 2022) are a tough sell, even with a much improved driver ecosystem delivering significant improvements throughout 2023/2024. Tulpar could be targeting a super budget price point, since Team Blue has signalled that their next-gen "Battlemage" GPUs are due later on in the year.

Intel just announced optimizations for PyTorch (IPEX) to take advantage of the AI acceleration features of its Arc "Alchemist" GPUs.PyTorch is a popular machine learning library that is often associated with NVIDIA GPUs, but it is actually platform-agnostic. It can be run on a variety of hardware, including CPUs and GPUs. However, performance may not be optimal without specific optimizations. Intel offers such optimizations through the Intel Extension for PyTorch (IPEX), which extends PyTorch with optimizations specifically designed for Intel's compute hardware.

Intel released a blog post detailing how to run Meta AI's Llama 2 large language model on its Arc "Alchemist" A770 graphics card. The model requires 14 GB of GPU RAM, so a 16 GB version of the A770 is recommended. This development could be seen as a direct response to NVIDIA's Chat with RTX tool, which allows GeForce users with >8 GB RTX 30-series "Ampere" and RTX 40-series "Ada" GPUs to run PyTorch-LLM models on their graphics cards. NVIDIA achieves lower VRAM usage by distributing INT4-quantized versions of the models, while Intel uses a higher-precision FP16 version. In theory, this should not have a significant impact on the results. This blog post by Intel provides instructions on how to set up Llama 2 inference with PyTorch (IPEX) on the A770.

Intel today launched the Arc A580 "Alchemist" desktop graphics card, with general availability across both the prebuilt and DIY retail channels. The card starts at a price of USD $179.99. The A580 targets the lower-end of the mid-range, and is targeted at AAA gaming at 1080p with medium-thru-high settings. The card fully meets DirectX 12 Ultimate feature-requirements, and is based on the Xe HPG "Alchemist" graphics architecture that powers the current Arc A750 and A770.

The new A580 has a lot in common with the Arc 7-series, as it is based on the same 6 nm ACM-G10 (aka DGX-512) silicon that powers them. Intel carved out this SKU by enabling 24 out of 32 Xe Cores, across 6 out of 8 Render Slices. This results in 384 execution units, or 3,072 unified shaders, 384 XMX AI acceleration cores, 24 Ray Tracing engines, 192 TMUs, and 96 ROPs. Perhaps the best aspect of the A580 is its memory sub-system that's been carried over from the A750—you get 8 GB of 16 Gbps GDDR6 memory across a 256-bit memory bus, yielding a segment-best 512 GB/s memory bandwidth. Intel claims that the Arc A580 should provide performance highly competitive to the GeForce RTX 3050, but there's more to this, do check out our reviews.

ASRock Arc A580 Challenger OC | Sparkle Arc A580 Orc

Schenker Technologies GmbH's e-commerce platform, bestware.com, is now offering Intel's NUC X15 Laptop Kit with Core i7-12700H and dedicated Arc A730M graphics card, in addition to the laptops of the two own brands XMG and SCHENKER. The base configuration of the 2 kg light and well-equipped 15.6-inch notebook is available at a reduced price of €899 (~$963) for a limited time at launch.

Intel NUC X15 Arc combines Core i7-12700H with Arc A730M
Measuring 358.26 x 235 x 22.2 mm and weighing just 2 kg, the 15.6-inch Intel NUC X15 Arc positions itself among the light and slim laptops in its performance class. The display lid and top shell of the black chassis are aluminium; only the bottom shell and the display frame use plastic. Despite its compactness, the NUC 15 Arc offers high performance. Intel pairs a Core i7-12700H with 14 cores (6 performance, 8 efficiency cores) and 20 threads with a dedicated graphics card from its own Arc portfolio: The Arc A730M offers a generous 12 GB of GDDR6 memory and operates at a TGP of 75 watts.

The Asian Games 2022 athletic event was originally set to take place last September—officials have rescheduled proceedings to later this month (opening September 23, closing October 8). Gunnir has prepared new versions of its existing Arc A770 & A750 Photon OC graphics cards in celebration of e-sports competitions being added to the roster at XIX Asian Games, Hangzhou. The Chinese hardware manufacturer has produced an extensive portfolio of Intel Alchemist-based discrete solutions, so it is not surprising to see slightly revised designs being issued to tie-in with a significant multi-sport tournament.

Gunnir's Photon OC White Edition shroud has been updated with the official Asian Games emblem as well as wavy graphic patterns—their retail packaging shares similar revisions, giving off some very calming vibes. According to product listings on JD.com, the A750 8 GB model currently sells for 1699 RMB (~$232), while the range-topping A770 16 GB variant is available to pre-order at 2399 RMB (~$328). The latest Intel and Gunnir collaboration is not likely to reach Western shores—Team Blue's Chinese operation announced (last month) that it was the official graphics processor supplier for this month's Hangzhou Asian Games. We expect only the most hardcore of GPU collectors to import these curiosities from Joybuy/Jingdong (JD).

Intel recently updated its website to highlight interposers used for testing upcoming chips before their actual product integration. A specific webpage now showcases components used by various tools, notably the "Gen5 VR," which stands for CPU Voltage Regulator in this context. The highlight of the update reveals at least four yet-to-be-announced products: Battlemage (BMG), Arrow Lake (ARL), and Lunar Lake (LNL), slated for launch in 2024. Particularly interesting are the two Battlemage interposers: BGA2362-BMG-X2 and BGA2727-BMG-X3. This hints that a Battlemage GPU could have more pins than Intel's current top-tier GPU from the Alchemist series, known as DG2, which features 2660 pins (BGA2660-DG2-512EU).

This unveiling could indicate Intel's plans to introduce two GPUs in its new series or potentially two different package sizes. Manufacturers often use consistent package sizes for multiple GPUs, granting flexibility to interchange processors with similar specifications and presenting a feasible production strategy. Another notable mention is the Arrow Lake-HX, intended for premium desktop/laptop hybrids.. While there was some buzz about the ARL-HX series before, this update provides clear confirmation from Intel. Lastly, the reveal includes an interposer for the Lunar Lake-M series (LNL-M), which is expected to be Intel's most energy-efficient line. Drawing parallels from the Alder Lake series, such chips were designed for tablets with power consumption between 5 to 7 watts.

Intel Graphics late Wednesday released the Arc GPU Graphics Software 101.4578 beta. These drivers come with Game On (day-zero) optimization for the hottest game release of this Summer, "Baldur's Gate 3." Intel beat both AMD and NVIDIA to be the first with optimized drivers for the game. The fantasy RPG releases later today. Given that the game is very easy on system requirements, you can expect the entire span of Intel Arc "Alchemist" graphics card to be perfectly suited to the game. The Arc A380 should be able to max out the game at resolutions of 1080p, while the A750 and A770 should max it out at 1440p and 4K Ultra HD.

DOWNLOAD: Intel Arc GPU Graphics Drivers 101.4578 beta

A Newegg product page popped up last week, giving us a first glimpse at ASRock's Phantom Gaming Arc A770 16 GB graphics card. The e-tailer had no stock available on July 20, but the listing included an asking price of $329.99 (MSRP is $349). The Taiwanese manufacturer was radio silent at the time—no press material was released, and their own website was not updated with a product page for the 16 GB variant of its existing custom Alchemist design.

The ASRock Arc A770 Phantom Gaming 16 GB OC model's page is now live and fully accessible, and Newegg appears to have units in stock. TPU has not received any fresh PR material, so ASRock is seemingly taking a quiet approach to their new product's launch. The spec sheet shows that the card's memory clock comes in at 17.5 Gbps, which makes it a good alternative to Intel's recently discontinued A770 Limited Edition. It joins Acer's competing Predator BiFrost model in an exclusive club—these are the only 16 GB A770 custom design graphics cards available in the West.