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 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

XeSS is arguably the most boasted-about new graphics technology by Intel. A performance enhancement that is functionally similar to AMD FSR or NVIDIA DLSS, XeSS will instrumental in making Arc "Alchemist" GPUs offer high performance with minimal loss to image quality, especially given that Intel's first crack at premium gaming GPUs also happens to include real-time ray tracing support, to meet DirectX 12 Ultimate specs.

Intel announced that XeSS won't be debuting with the Arc 3 series mobile GPUs that launched yesterday (March 30), but instead alongside the Arc 5 and Arc 7 series slated for early-Summer (late-May to early-June). At launch, several AAA titles will be optimized for XeSS, including "Ghostwire: Tokyo," "Death Stranding," "Anvil," "Hitman III," "GRID Legends," etc.

For decades, Intel has been a champion for PC platform innovation. We have delivered generations of CPUs that provide the computing horsepower for billions of people. We advanced connectivity through features like USB, Thunderbolt and Wi-Fi. And in partnership with the PC ecosystem, we developed the ground-breaking PCI architecture and the Intel Evo platform, pushing the boundary for what mobile products can do. Intel is uniquely positioned to deliver PC platform innovations that meet the ever-increasing computing demands of professionals, consumers, gamers and creators around the world. Now, we take the next big step.

Today, we are officially launching our Intel Arc graphics family for laptops, completing the Intel platform. These are the first discrete GPUs from our Intel Arc A-Series graphics portfolio for laptops, with our desktop and workstation products coming later this year. You can visit our Newsroom for our launch video, product details and technical demos, but I will summarize the highlights of how our Intel Arc platform and A-Series mobile GPU family will deliver hardware, software, services and - ultimately - high-performance graphics experiences.

Intel is preparing to debut the Arc "Alchemist" line of graphics processors with a mobile-first approach, where the company leverages its bulletproof relations with notebook manufacturers to use its discrete mobile GPUs to go with their 12th Gen Core "Alder Lake" processors. These will be launch in two tranches, with the first round expected as early as today (March 30), according to a VideoCardz report citing a leaked company slide. The series will debut with the Arc 3 series of entry-level discrete GPUs, before moving onto the mid-range Arc 5 and premium Arc 7 series "early summer" (we read that as May-June, 2022).

The entire lineup of Arc "Alchemist" is based on two ASICs, the smaller one is the ACM-G11, or DG2-128; while the larger one is the ACM-G10, or DG2-512. The former comes with 128 execution units (EU), while the larger one has 512 EU. The Arc 3 series, consisting of the A350M and A370M, come with 96 and 128 EU (768 and 1,024 unified shaders), respectively, The mid-range Arc A550M is based on the lowest trim of the DG2-512, with half its EU count disabled (256 EU, or 2,048 shaders). The Arc A730M has three-fourths of the EU count enabled, while the A770M maxes it out.

SiSoftware put out the mother lode of information on Intel's upcoming Arc "Alchemist" gaming graphics card series, along with OpenCL compute performance of the entry-level Arc A380. The Arc series model numbering is "A" (Alchemist) followed by a number series. The A300 series makes up the entry-mainstream; the A500 series makes up the mid-performance segment; and the A700 series leads the pack with high-end SKUs. The "Alchemist" GPUs are built on the 7 nm silicon fabrication node at TSMC, the N7.

The A300 series is based on the smaller "Alchemist" series dies, with 128 EUs (execution units), which work out to 1,024 programmable shaders. The A500 series and A700 series appear to be carved out from the larger silicon. The A500 series has roughly 384 EU or 3,072 shaders. The top-dog A700 series has all 512 EU or 4,096 shaders enabled. Intel is tapping into industry-standard GDDR6 for dedicated graphics memory. The A300-series SKUs typically have 6 GB of 14 Gbps-rated memory across a 96-bit wide memory bus, for 192 GB/s of bandwidth. The A500 series parts have 12 GB of 16 Gbps-rated memory across a 192-bit bus, for 384 GB/s of bandwidth. The top A700 series maxes out the 256-bit memory bus with 16 GB of memory at 16 Gbps data-rate, for 512 GB/s bandwidth.

Intel plans to ship no less than 4 million discrete GPUs in 2022, the company stated in its Investor Meeting 2022 presentation. The Accelerated Computing Systems and Graphics Group (AXG), headed by Raja Koduri, announced this bold target. The company announced a Q1-2022 debut of its ambitious new Arc "Alchemist" discrete GPU for notebooks (before April). This is to be followed by a desktop debut in Q2-2022 (before July), before a professional-visualization (workstation-class) debut in Q3 (before October). All put together, the company plans to ship over 4 million discrete GPUs over the year.

Intel announced over 50 design wins for OEMs and "AICs." This is big, as it denotes that Arc "Alchemist" graphics cards won't just be sold in the OEM/SI channel, but also the DIY retail channel. Among the familiar brands in the DIY space from the Intel slide are ASUS, MSI, and GIGABYTE. The company is working with over 100 software-ecosystem partners or ISVs, to optimize their current and upcoming applications and games, for the Xe HPG graphics architecture. This includes support for the XeSS performance enhancement (analogous to AMD FSR and NVIDIA DLSS), and DeepLink, a graphics processing resource virtualization tech. Intel plans to launch a new generation of Arc almost every year for the next 3 years, starting with "Alchemist" in 2022, "Battlemage" somewhere around 2023-2024, and "Celestial" after 2024.

It's happening, Intel is taking a very pointy stab at the AAA gaming graphics market, taking the fight to NVIDIA GeForce and AMD Radeon. The Arc "Alchemist" discrete GPU implements the Xe HPG (high performance gaming) graphics architecture, and offers full DirectX 12 Ultimate compatibility. It also offers contemporary features gamers want, such as XeSS, an AI-supersampling feature rivaling DLSS and FSR. There's a lot more to the Xe HPG architecture than being a simple a scale-up from the Xe LP-based iGPUs found in today's "Tiger Lake" processors.

Just like Compute Units on AMD GPUs, and Streaming Multiprocessors on NVIDIA, Intel designed a scalable hierarchical compute hardware structure for Xe HPG. It begins with the Xe-core, an indivisible compute building block that contains 16 each of 256-bit vector engines and 1024-bit matrix engines. combined with basic load/store hardware and an L1 cache. The vector unit here is interchangeable with the execution unit, and the Xe-core contains 16 of these. The Render Slice is a collective of four Xe-cores, four Raytracing Units; and other common fixed-function hardware that include the geometry pipeline, rasterization pipeline, samplers, and pixel-backends. The Raytracing Units contain fixed-function hardware for bounding-box intersection, ray traversal, and triangle intersection.

On the sidelines of its 2021 International Supercomputing Conference announcements that mostly covered the HPC-relevant portions of the company's Xe scalar compute architecture, the company also put out a couple of nuggets on Xe HPG, the gaming-grade consumer graphics architecture by Intel, which is expected to power graphics cards capable of AAA gaming at high resolutions. Without mentioning dates, the company announced that Xe HPG will see the light of the day soon.

It's a long march for Intel to break into the gaming graphics card business, and Intel is calling this project "Odyssey." A select few (Intel employees, ISVs, hardware partners, etc.,), have access to greater information and merchandise, as they hold the "Odyssey Card." The company called for them to "redeem" this card for the goodies. "We are soon heading toward a milestone moment, the pending release of the Xe HPG microarchitecture from Intel. Some of you received an Odyssey card and were the first to engage with Intel on this journey. Now is the time to redeem this card, which is one in many steps we hope to formally take forward with you. We have a few required fields here to confirm you have received a card from us," stated Intel.

Intel's foray into the discrete GPU market is inching ever closer, and with that diminishing time to market, leaks are getting more common. Renowned leaker TUM_APISAK has shared some performance numbers for Intel's upcoming DG2 graphics card, part of the company's Xe HPG (High Performance Gaming) architecture. In the leak, he also confirmed that Intel is working on a cut-down version of their top offering (which features 4,096 shading units spread across 512 EUs) in the form of a new SKU that offers 448 EUs and 3584 shading units running at 1.8 GHz. That is the actual chip whose relative performance was shared.

According to TUM_APISAK, users should expect the Intel DG2 448 EU graphics card to offer performance that's around the NVIDIA RTX 3070 (5% lower performance for the Intel part) and AMD's RX 6700 XT (8% lower performance for the Intel part). As for the performance of the full-fat 512 EU chip, another leaker, Moore's Law is Dead, expects its performance to fall very slightly lower than the performance offered by NVIDIA's RTX 3080 and AMD's RX 6800/6800 XT. The 512-EU DG2 should also feature higher Boost clocks up to 2.2 GHz. Intel's launch of their Xe HPG graphics architecture is expected to occur before the end of the year, likely starting with the highest performance/highest margin parts, trickling down the product stack through the beginning of 2022. Intel's launch should help in alleviating the lack of available graphics cards, whilst simultaneously breaking a duopoly market.

A senior game developer relations engineer at Intel, Pete Brubaker, Tweeted late Wednesday that the company's DG2 discrete graphics card is "right around the corner," and that "it's about to get exciting." Brubaker's Tweet comes as the company is looking to recruit more engineers to work with its developer relations, the team that interfaces with game devs to optimize their engines and games for Intel's graphics architectures.

While the DG1, which was productized as the Iris Xe MAX graphics card, was essentially an iGPU-on-a-stick, the DG2 should spark a lot more interest. Based on a third-party foundry process, the DG2 is the first client graphics product based on the Xe HPG (high performance gaming) graphics architecture, and allegedly crams up to 512 execution units or 4,096 unified shaders—a 4.3x gain over the Iris Xe MAX. It's also rumored to ship with up to 16 GB of GDDR6 memory across a 256-bit wide memory bus. Whether it features DirectX 12 Ultimate features or not, remains to be seen, but it's becoming clear that Intel wants a crack at the high-volume e-sports market, with a product that's fast enough for competitive e-sports gaming, and capable of AAA.

Intel Graphics tweeted a marketing splash screen of its upcoming Xe HPG gaming discrete graphics architecture. There's not much to the video, except announcing the Xe HPG logo. It starts off with a depiction of the Xe LP architecture, on which the company's Gen12 iGPUs and Iris Xe MAX entry-level discrete GPUs are based; and swells into a larger silicon that grows in all directions. The animation could be a hint that Xe HPG chips will be an order of magnitude faster than the Iris Xe MAX, target serious gaming, and take the fight to both NVIDIA and AMD.

Intel is designing the Xe HPG graphics architecture for third-party silicon fabrication nodes, such as TSMC and Samsung, and could leverage a sub-10 nm node to significantly scale up from the Xe LP. A recent report pointed to the likelihood of 512 execution units on a certain Xe HPG variant (4,096 unified shaders) and contemporary GDDR6 memory, while Intel has the necessary IP to pull off DirectX 12 Ultimate logo readiness, including raytracing. Intel is likely eyeing a slice of the e-sports hardware segment, although a high-end GPU cannot be completely ruled out. Watch the video from the source link below.

Intel started shipping their first Xe DG1 graphics card to OEMs earlier this year which features 4 GB of LPDDR4X and 80 execution units. While these initial cards aren't high performance and only compete with entry-level products like the NVIDIA MX350 they demonstrated Intel's ability to produce a discrete GPU. We have recently received some more potential performance information about Intel's next card the DG2 from chief GPU architect, Raja Koduri. Koduri posted an image of him with the team at Intel's Folsom lab working on the Intel Iris Pro 5200 iGPU back in 2012 and noted that now 9 years later their new GPU is over 20 times faster. The Intel Iris Pro 5200 scores 1015 on Videocard Benchmarks and ~1,400 points on 3DMark Fire Strike, if we assume these scores will be 20x more we get values of ~20,300 in Videocard Benchmarks and 28,000 points in Fire Strike. While these values don't extrapolate perfectly they provide a good indication of potential performance placing the GPU in the same realm of the NVIDIA RTX 3070 and AMD RX 6800.

Intel's head for architecture, software, and graphics divisions, Raja Koduri, on Wednesday (10/02) teased a Xe HPG discrete GPU prototype running the upcoming 3DMark DirectX 12 Mesh Shaders feature test. Mesh Shaders are one of the four key features for graphics solutions to achieve the DirectX 12 Ultimate logo readiness, the other three being Real-time raytracing, Variable Rate Shading, and Sampler Feedback. Intel has already been supporting VRS tier-1 since Gen11, and the new Gen12 Xe LP carries forward VRS support.

The Xe HPG architecture is being pushed by Intel as the company's first high-performance gaming discrete graphics architecture. The company earlier released entry-level dGPUs based on the same Xe LP architecture as the Gen12 iGPU found in its "Tiger Lake" processors. The presence of VRS and Mesh Shader support, along with foundational work Intel has done in the area of real-time raytracing, hints at the likelihood of Intel gunning for DirectX 12 Ultimate readiness for the Xe HPG.

Intel's Xe HPG discrete GPU made its debut in a game's system requirements list. Frictional Games, developers of "Amnesia Rebirth," put out system requirements lists for the game. Easy on graphics hardware, the first-person survival horror can make do with Intel UHD 630 integrated graphics, which features in the minimum system requirements list next to the HD 5750 from AMD and GTX 460 from NVIDIA. Things get interesting, however, with the recommended system requirements list, where we see what is possibly the first mention by a game dev of the Intel Xe HPG discrete GPU. What's even more interesting is that the Xe HPG is pitted next to the AMD Radeon RX 580 and NVIDIA GeForce GTX 680 (which compare to the RX 5500 XT and GTX 1660 Super from the current-gen). We don't know if game devs have access to Xe HPG engineering samples, but this listing gives us a peek at what the devs expect out of the Xe HPG.

Intel on Thursday at its 2020 Architecture Day event announced a high performance gaming variant of its Xe graphics architecture, which it calls Xe HPG. The Xe architecture is designed to scale between tiny iGPUs and mobile discrete GPUs as Xe LP, up to scalar compute processors under Xe HP, and beyond to HPCs and supercomputers, under Xe HPC. The combination of the client graphics feature-set of Xe LP, with the scale of Xe HP, results in Xe HPG. Intel is designing Xe HPG for a third-party semiconductor foundry, and hopes to debut it in 2021.

In our older graphics detailing the Xe LP, we tried to explain just how easy it is for Intel scale up the iGPU to a discrete GPU SoC. This is done by simply dialing up the Xe slices, and dropping in dGPU ancillaries such as a PCI-Express host interface and memory controllers for the prevalent client-segment discrete graphics, namely GDDR6. There will be additional components, such as ray-tracing hardware. Intel is gunning for DirectX 12 Ultimate logo compliance, and ray-tracing forms a big part of that.