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.

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.

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.

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.

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 officially launched the Arc A380 "Alchemist" entry-mainstream desktop graphics card in China, priced at RMB ¥1,030, including VAT, which roughly converts to USD $153. The Arc A380 "Alchemist" is based on the Xe-HPG graphics architecture, and the smaller DG2-128 (ACM-G11) silicon, which is built on the TSMC N6 (6 nm) silicon fabrication process.

The A380 desktop GPU is endowed with 8 Xe Cores, or 128 EU (execution units), which work out to 1,024 unified shaders. The chip features a 96-bit wide GDDR6 memory interface, running 6 GB of memory. Despite these hardware specs, you get full DirectX 12 Ultimate capability, including ray tracing, and the XeSS performance enhancement. There are also several content-creation accelerators, including Intel XMX, and AV1 hardware-encode capabilities.

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.

CPU-Z is one of the most widespread tools for profiling and monitoring, gathering information from the system, and presenting it in a user-readable UI. Today, the application has reached another milestone with the release of the CPU-Z 2.01 version, which brings support for additional upcoming processors from AMD and Intel. One of the software highlights is the inclusion of AMD's forthcoming processor designs, codenamed Rembrandt and Raphael. These processors are what AMD is bringing to the market now and in the near future, meaning that the software ecosystem has to prepare. Additionally, CPU-Z has been updated with preliminary support for Intel's upcoming 13th Generation Raptor Lake processors, alongside Intel ARC 3/5/7 DG2 designs. CPU-Z developers also improved validation process for high-frequency overclocking submissions of over 6 GHz. The full changelog is listed below.

Download CPU-Z 2.01 here.

HotHardware did a video interview with Intel Fellow Tom Petersen, who briefly teased a prototype Intel Arc "Alchemist" graphics card with three 8-pin PCIe power connectors, for a total power input capability of 450 W. This does not necessarily mean that a finished product will ship with three connectors; as prototype motherboards and graphics cards are known to feature various redundant connectivity and power-input options for product developers to test capabilities. The three connectors are spaced far apart from each other, so it's likely that the board tests various combinations of power inputs. One of the three could even be a 224 W EPS instead of a 150 W PCIe. The Arc "Alchemist" 7-series desktop board that maxes out the DG2-512 silicon, has been grinding through the rumor mill for quite some time now, including PCB pictures, showing two 8-pin PCIe 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.

Some interesting technical specifications of the elusive two GPUs behind the Intel Arc "Alchemist" series surfaced. The larger DG2-512 silicon in particular, which forms the base for the Arc 5 and Arc 7 series, is interesting, in that it is larger in every way than the performance-segment ASICs from both NVIDIA and AMD. The table below compares the physical specs of the DG2-512, with the NVIDIA GA104, and the AMD Navi 22. This segment of GPUs has fairly powerful use-cases, including native 1440p gameplay, or playing at 4K with a performance enhancement—something Intel has, in the form of the XeSS.

The DG2-512 is built on the 6 nm TSMC N6 foundry node, the most advanced node among the three GPUs in this class. It has the highest transistor density of 53.4 mTr/mm², and the largest die-area of 406 mm², and the highest transistor-count of 21.7 billion. The Xe-HPG graphics architecture is designed for full DirectX 12 Ultimate feature support, and the DG2-512 dedicated hardware for ray tracing, as well as AI acceleration. The Arc A770M is the fastest product based on this silicon, however, it is a mobile GPU with aggressive power-management characteristic to the form-factor it serves. Here, the DG2-512 has an FP32 throughput of 13.5 TFLOPs, compared to 13.2 TFLOPs of the Navi 22 on the Radeon RX 6700 XT desktop graphics card, and the 21.7 TFLOPs of the GA104 that's maxed out on the GeForce RTX 3070 Ti desktop graphics card.

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.

The Intel Arc A370M was put through the "Ashes of the Singularity" benchmark. In two separate runs, the GPU ended up with a score of 3500 and 3600 points in the "Min_1080p" configuration, with an average framerate of 67 FPS in the normal batch. The notebook test-platform this chip ran on consisted of a Core i7-12700H processor, and 32 GB of memory.

3500 points is a rather vague score for this benchmark, given that GPUs from a wide range of market segments attained the similar scores (albeit on very different CPU and memory configurations). The A370M is expected to be SKU that maxes out the smaller DG2 ASIC that physically features 128 execution units (1,024 unified shaders), and a 64-bit wide GDDR6 memory bus holding 4 GB of memory. This A370M should offer roughly twice the performance as the Iris Xe iGPU with 96 EUs found in quad-core "Tiger Lake" mobile processors.

We recently reported on the unnamed discrete Intel Arc Alchemist GPU found in the upcoming Samsung Galaxy Book2 Pro. That listing has now been removed but Finnish retailer Proshop has posted two models of the upcoming Acer Swift X laptop featuring Intel Arc A370M graphics cards. The listings include a Core i5-1240P and Core i7-1260P model each featuring 16 GB of LPDDR5 memory and an Intel Arc A370M GPU available to pre-order for 1299 EUR and 1549 EUR respectively.

The Intel Arc A370M is based on the DG2-128EU GPU and is expected to feature 4 GB of VRAM on a 64-bit memory bus. The Intel Arc Alchemist discrete mobile graphics cards will be officially unveiled by Intel on March 30th with claims of a 2x performance improvement from the integrated 96EU Iris-XE GPU found in the Core i7-12700H. The Acer Swift X laptops are listed by Proshop as not being available until May 25th almost 2 months after the official announcement.

According to Igor's Lab, Intel has listed a new product on its non-public ARK site that lists what appears to be a motherboard product with an Intel Arc GPU. The product listing is very peculiar, as it's listed as a graphics card, but the "family name" is DG2MB. It's also said to have a clock speed of 4 GHz, 16 MB of cache and a TDP of 200 W. None of this seems to add up in any sensible way and additional information provided by Igor, doesn't improve things, as the chip is using an FC-BGA16E packaging with a pin-count of 2660.

For those not familiar with Intel ARK, it's Intel's product specification website and there's a public version, as well as a version that only select Intel customers have access to and it's from the latter this information has been sourced. As to what this product could be, is anyone's guess at this point, but the MB in the model name suggests it might be some kind of embedded motherboard with an Intel CPU and GPU, possibly for some kind of NUC product.

At Intel's 2022 investor meeting, the company has presented a technology roadmap update to give its clients an insight into what is to come. Today, team blue announced one of the first discrete data-centric graphics cards in the lineup, codenamed Arctic Sound-M GPU. Based on the DG2 Xe-HPG variation of Intel Xe GPUs, Arctic Sound-M is the company's first design to enter the data center space. The DG2 GPU features 512 Execution Units (EUs), which get passive cooling from the single-slot design of Arctic Sound's heatsink, envisioned for data center enclosures with external airflow.

One of the most significant selling points that Intel advertises is support for hardware-based AV1 encoding standard. This feature allows the card to achieve a 30% greater bandwidth, and it is the main differentiator between consumer-oriented Arc Alchemist GPUs and itself. The card is powered by PCIe power and an 8-pin EPS power connector. Arctic Sound-M is already sampling to select customers and it will become available in the middle of 2022.Below is Intel's teaser video.

Mesh shader is a relatively new concept of a programmable geometric shading pipeline, which promises to simplify the whole graphics rendering pipeline organization. NVIDIA introduced this concept with Turing back in 2018, and AMD joined with RDNA2. Today, thanks to the finds of Phoronix, we have gathered information that Intel's DG2 GPU will carry support for mesh shaders and bring it under Vulkan API. For starters, the difference between mesh/task and traditional graphics rendering pipeline is that the mesh edition is much simpler and offers higher scalability, bandwidth reduction, and greater flexibility in the design of mesh topology and graphics work. In Vulkan, the current mesh shader state is NVIDIA's contribution called the VK_NV_mesh_shader extension. The below docs explain it in greater detail:

Vulkan API documentationThis extension provides a new mechanism allowing applications to generate collections of geometric primitives via programmable mesh shading. It is an alternative to the existing programmable primitive shading pipeline, which relied on generating input primitives by a fixed function assembler as well as fixed function vertex fetch.

There are new programmable shader types—the task and mesh shader—to generate these collections to be processed by fixed-function primitive assembly and rasterization logic. When task and mesh shaders are dispatched, they replace the core pre-rasterization stages, including vertex array attribute fetching, vertex shader processing, tessellation, and geometry shader processing.

Intel's upcoming Arc Alchemist lineup of discrete graphics cards generates a lot of attention from consumers. Leaks of these cards' performance and detailed specifications appear more and more as we enter the countdown to the launch day, which is sometime in Q1 of this year. Today, we managed to see a slide from @9950pro on Twitter that shows the laptop memory configuration of Intel's DG2 GPU. As the picture suggests, we can see that the top-end SKU1 with 512 EUs supports a 16 GB capacity of GDDR6 memory that runs at 16 Gbps speeds. The memory runs on a 256-bit bus and generates 512 GB/s bandwidth while having eight VRAM modules present.

When it comes to SKU2, which is a variant with 384 EUs, this configuration supports six VRAM modules on a 192-bit bus, running at 16 Gbps speeds. They generate a total capacity of 12 GBs and a bandwidth of 384 GB/s. We have SKU3 DG2 GPU going down the stack, featuring 256 EUs, four VRAM modules on a 128-bit bus, 8 GB capacity, and a 256 GB/s bandwidth. And last but not least, the smallest DG2 variants come in the form of SKU4 and SKU5, feating 128 EUs and 96 EUs, respectively. Intel envisions these lower-end SKUs with two VRAM modules on a 64-bit bus, and this time slower GDDR6 memory running at 14 Gbps. They are paired with 4 GB of total capacity, and the total bandwidth comes down to 112 GB/s.

Intel's Arc Alchemist discrete lineup of graphics cards is scheduled for launch this quarter. We are getting some performance benchmarks of the DG2-512EU silicon, representing the top-end Xe-HPG configuration. Thanks to a discovery of a famous hardware leaker TUM_APISAK, we have a measurement performed in the SiSoftware database that shows Intel's Arc Alchemist GPU with 4096 cores and, according to the report from the benchmark, just 12.8 GB of GDDR6 VRAM. This is just an error on the report, as this GPU SKU should be coupled with 16 GB of GDDR6 VRAM. The card was reportedly running at 2.1 GHz frequency. However, we don't know if this represents base or boost speeds.

When it comes to actual performance, the DG2-512EU GPU managed to score 9017.52 Mpix/s, while something like NVIDIA GeForce RTX 3070 Ti managed to get 8369.51 Mpix/s in the same test group. Comparing these two cards in floating-point operations, Intel has an advantage in half-float, double-float, and quad-float tests, while NVIDIA manages to hold the single-float crown. This represents a 7% advantage for Intel's GPU, meaning that Arc Alchemist has the potential for standing up against NVIDIA's offerings.

Intel has recently been promoting their upcoming Arc Alchemist (DG2) gaming graphics cards that are set to launch early next year possibly at CES 2022. We have recently seen a slide allegedly from Intel which states that the company will only be releasing products to compete in the upper mid-range segment and below. The slide details two DGPU GPUs where the SOC1 would have a TDP of 175 W - 225 W spawning SKUs to compete with the RTX 3070, 3060 Ti, RX 6700 XT, and 6600 XT while a cheaper SOC2 would have a TDP of 75 W and compete with the RTX 1650 Super. The SOC1 GPU would target the 300 to 499 USD price segment while the SOC2 would focus on the budget 100 - 200 USD market which AMD and NVIDIA have effectively abandoned with their latest architectures.

In its 2021 Architecture Day presentation, Intel revealed that its first performance gaming GPU, the Arc "Alchemist," is built on the TSMC N6 silicon fabrication node (6 nm). A more advanced node than the N7 (7 nm) used by AMD for its current RDNA2 GPUs, TSMC N6 leverages EUV (extreme ultraviolet) lithography, and offers 18% higher transistor density, besides power improvements. "With N6, TSMC provides an optimal balance of performance, density, and power-efficiency that are ideal for modern GPUs," said Dr Kevin Zhang, SVP of Business Development at TSMC.

With working prototypes of "Alchemist" already internally circulating as the "DG2," Intel has beaten AMD to 6 nm. Team Red is reportedly planning optical-shrinks of its RDNA2-based "Navi 22" and "Navi 23" chips to TSMC N6, and assigning them mid-range SKUs in the Radeon RX 7000 series. The company will build two higher-segment RDNA3 GPUs on the more advanced TSMC N5 (5 nm) process, which will release in 2022, and power successors to the RX 6700 series and RX 6800/6900 series.

Intel has recently released a promotional video teasing the dual-fan cooler design of their upcoming Arc gaming graphics card with 1000 drones. The company used 1000 drones fitted with lighting to create various shapes including a dual-fan desktop graphics card which has a strong resemblance to the previously leaked design for a DG2-512EU engineering sample. The two images also both include 9 blades on the fans giving further authority to the previous rumor. The first Intel Arc "Alchemist" products will begin shipping in Q1 2022 with the flagship desktop graphics card rumored to feature 512 Execution Units paired with 16 GB GDDR6 memory targeting RTX 3070 Ti performance. Intel is also preparing a NVIDIA DLSS/AMD FidelityFX Super Resolution competitor codenamed XeSS and will include hardware-accelerated raytracing support with the Arc lineup.

Intel today surprised us with the reveal of its new high-performance gaming graphics brand, Intel Arc. Competing with the AMD Radeon and NVIDIA GeForce brands, Arc enables Intel to take a stab at the gaming graphics market that's been a duopoly for the past 2 decades; and the company doesn't intend to only make low-cost e-sports chips. As if a statement of intent, the company revealed the codenamed of the first three generations of Arc: "Battlemage," "Celestial," and "Druid."

Of these "Battlemage" is likely the fancy new codename for the Xe HPG graphics architecture, which has been implemented in a working prototype referred to as the DG2, and which Intel is now referring to as "Alchemist." Intel revealed that "Battlemage" is being designed to meet DirectX 12 Ultimate requirements, which means it will support hardware-accelerated real-time raytracing; mesh shaders, sampler feedback, and variable-rate shading. Intel also announced that the chips will feature an AI-accelerated supersampling feature. This will rival NVIDIA DLSS and AMD FSR. Intel announced that the first consumer products based on the "Alchemist" silicon will release in the first quarter of 2022, the company will put out more specifics throughout 2021, in the run-up to this launch.

Intel has reportedly decided to launch their DG2 Xe-HPG discrete graphics cards at CES 2022 according to Hardware Academy on Weibo. Intel has already begun sampling these new GPUs to partners so this launch date appears feasible. The DG2 Xe-HPG discrete graphics cards are designed specifically for gaming and will offer up to 512 Execution Units paired with 16 GB of GDDR6 memory. Intel appears to be planning five separate DG2 Xe-HPG SKUs covering a large lineup of market segments with the top product competing with the NVIDIA GeForce RTX 3080 and AMD Radeon RX 6800. While these products won't be released until CES 2022 Intel may announce gaming processors with integrated Xe-HPG graphics sometime earlier.

Intel has begun sampling its Xe-HPG (High performance Gaming) products to ecosystem partners, which will allow them to verify performance, power, stability and board characteristics that are necessary variables in product development and launch. The information comes courtesy of Intel, who has updated its graphics product roadmap regarding DG2 sampling and for its Xe-HPC (High Performance Computing) products as well. Xe HPC products (codenamed Ponte Vecchio after a beautiful Florentine bridge) have now achieved power-on capabilities and are undergoing validation before subsequent steps in the hardware development workflow.