Intel just gave its upcoming gaming graphics cards a name — Intel Arc. The first generation of cards is set to arrive in early 2022, and Intel confirmed that three future generations are already in the works. We’ve been waiting a long time to see what Intel has in store for gamers, and now, we have a clearer, if still slightly smudged, picture of what’s coming up.
Intel Arc is the brand that Intel is using for all gaming hardware, software, and services moving forward, and the company confirmed that it will span multiple hardware generations. Here’s everything we know so far about Intel Arc, including the first-generation Alchemist graphics cards.
What is Intel Arc?
Intel Arc is the branding that Intel is using for “upcoming consumer high-performance graphics products.” The name encompasses multiple generations of graphics cards targeted specifically at gaming, and you shouldn’t confuse it with Intel Xe. Arc products — at least the ones we know about — use the Xe architecture, but not all Xe products live under Arc.
Intel Xe is the architecture for all of Intel’s recent graphics products, including the integrated graphics in Tiger Lake laptops and data center GPUs like Ponte Vecchio. Xe is a scalable architecture that Intel can shrink or expand in a single package to accommodate multiple different applications.
Intel Arc products are based on the Xe HPG. Intel is using this same architecture for mobile and desktop applications, starting with the first generation of Intel Arc cards.
With the naming out of the way, we can talk about the Intel Arc products we know about. The first-generation cards were formerly known as DG2, but they now have the code name Alchemist. Alchemist cards are the only ones we even remotely have information about at this point, so we’ll be focusing on those here.
Intel revealed the code names for upcoming generations, too: Battlemage, Celestial, and Druid. For these generations, all we know right now are the names. In all likelihood, Battlemage will Alchemist, Celestial will follow Battlemage, and so on.
It looks like all upcoming Arc products are based on the Xe HPG architecture, so there could be a rapid release pace for each generation. Right now, Alchemist cards are rumored to use chipmaker TSMC’s 7nm or 6nm node, which is the same node that AMD uses for its RX 6000 graphics cards. Intel hasn’t named TSMC, but it has already confirmed that it’s using an external foundry for manufacturing.
Over time, it’s possible that Intel will move to smaller processes, but we’re not sure at this point.
Intel Arc Alchemist price and release date
Intel hasn’t revealed pricing information for Arc cards yet and only offered a vague hint at the release window. Keep in mind that Arc is the branding for all Xe HPG graphics products, so beyond this point, we’re talking about the upcoming generation of Arc cards — Alchemist.
For release, Intel says the first cards will arrive in the first few months of 2022. Information is sparse at this point, so there’s no saying when in that time frame the cards will release or how Intel will handle the rollout. It’s possible that Intel will release cards to system makers and laptop designers first, or everything could hit at once. We don’t know yet.
Previously, rumors suggested that Intel would release the cards at CES 2022. That event happens in January, so it’s possible that Intel will launch the cards then, with general availability following shortly after.
Unfortunately, we know even less about pricing. We’re purely speculating, but if rumors are to be believed, the flagship card should cost around $600. That’s in between the RTX 3080 and RTX 3070, which it looks like the top card is targeting. Intel isn’t a stranger to abnormally high prices, however, so it could be higher.
It really shouldn’t be, though. Intel is the underdog in the world of graphics. AMD and Nvidia are the price setters. We hope that Intel will enter the discrete graphics market with a lower price point compared to Nvidia and AMD, but that’s a tough thing to do in 2021.
The GPU shortage has driven up the cost of creating graphics cards. Unlike AMD and Nvidia, Intel doesn’t have a portfolio of add-in board partners that can adjust the price separately (at least, no partners have been announced yet). That will likely bloat the cost of the cards in the short term, but we still need to wait until Intel reveals more information.
Intel Arc specs
Intel hasn’t confirmed any specs for any Arc products yet. However, various leaks and rumors have given us a pretty good idea about how the Alchemist range is shaping up. The six rumored Alchemist cards are all based on the Intel Xe HPG architecture, with varying amounts of video memory and execution units (EUs) separating them.
|GPU||Execution units||Shading units||Memory||Memory bus|
|Xe-HPG 512EU||DG2-512EU||512||4,096||16GB or 8GB GDDR6||256-bit|
|Xe-HPG 384EU||DG2-384EU||384||3,072||12GB of 6GB GDDR6||192-bit|
|Xe-HPG 256EU||DG2-384EU||256||2,048||8GB or 4GB GDDR6||128-bit|
|Xe-HPG 192EU||DG2-384EU||192||1,536||4GB GDDR6||128-bit|
|Xe-HPG 128EU||DG2-128EU||128||1,024||4GB GDDR6||64-bit|
|Xe-HPG 96EU||DG2-128EU||96||768||4GB GDDR6||64-bit|
The specs above haven’t been confirmed by Intel. They’re the product of rumors, leaks, and speculation, so they’re subject to change.
Based on the specs, the flagship unit looks fit to compete with Nvidia’s Ampere and AMD’s RDNA 2 ranges. It comes with 512 EUs for a total of 4,096 cores, as well as up to 16GB of GDDR6 memory. Both 16GB and 8GB models have been rumored, though it’s possible the slimmer version is being reserved for laptops.
Otherwise, the cards step down similar to AMD and Nvidia. The 384 EU model looks like it will compete with the AMD RX 6700 XT with 12GB of memory, and the 256EU card will likely compete in the range of an RTX 3060 or RTX 3060 Ti. Keep in mind that this is a spec comparison, which doesn’t always reveal how cards will perform in the real world.
The bottom three cards all come with 4GB of GDDR6 memory, and the lowest two use a 64-bit memory bus. It’s not clear now if these cards will be available as add-in cards for desktops or exclusively for mobile platforms. So far, Intel has only confirmed that Alchemist cards are coming to desktops and laptops, not which cards will go where.
Intel hasn’t revealed any performance numbers for Arc cards yet. However, the first-generation Alchemist cards look capable of running a good chunk of recent AAA video games and hopefully at playable frame rates. Following the announcement, Intel released a montage of gameplay footage captured on pre-production silicon.
— Intel Gaming (@IntelGaming) August 16, 2021
The video shows the Crysis Remastered trilogy, Forza Horizon 4, Days Gone, and Metro Exodus, among other titles. Crysis Remastered and Metro Exodus, in particular, are fairly demanding. That’s a good sign for Intel’s first foray into gaming graphics cards, but it’s important to reiterate that we don’t have any performance numbers at this time.
A benchmark leak from August showed a DG2 card (now known as Alchemist) reaching speeds of up to 2,200MHz, which is faster than most cards from AMD and Nvidia. That doesn’t mean the card is faster than its competition, just that Intel is able to drive its silicon harder.
The leak showed performance on-par with a Nvidia GTX 760 or AMD RX 550, which you should take with a spoonful of salt. In fact, the benchmark showed the DG2 performing worse than Intel’s own DG1, which likely isn’t the case.
Another leak from April showed performance that’s more in-line with what we expect. The leak showed the flagship model performing about as well as the Nvidia RTX 3080 and AMD RX 6800 XT. In 3DMark TimeSpy, the leaker claimed results could even rival Nvidia’s $1,500 RTX 3090. That would be great, but we’re still waiting on benchmarks to see how the cards will stack up.
Real-time ray tracing and supersampling
Intel has confirmed that its first-generation Arc cards will support real-time ray tracing and artificial intelligence (A.I.)-assisted supersampling, and future generations should as well. We’re not sure how these features will work once the cards release, but Intel has confirmed that they will support DirectX 12 Ultimate. That means support DirectX Raytracing (DXR) and features like variable rate shading.
For DXR, you’ll be able to turn on ray tracing in any game that uses the DirectX 12 features package. Most titles that support ray tracing do so with DXR, including Cyberpunk 2077, Metro Exodus, Minecraft, and Fortnite. Others use the Vulkan application programming interface (API) instead.
Intel hasn’t confirmed if Vulkan is supported, but that’s probably a safe bet. Most ray tracing titles are brand-agnostic when it comes to real-time ray tracing, utilizing whatever hardware is available on the card to render the realistic lighting. Right now, however, we don’t know how real-time ray tracing will work or how Intel will implement it on the upcoming GPUs.
The implementation will make a big difference. Currently, Nvidia uses dedicated ray-tracing cores while AMD packs a “ray accelerator” into each compute unit. The end result is vastly better ray-tracing performance on Nvidia graphics cards compared to AMD, as you can see in our review of the recently launched AMD RX 6600 XT.
Intel also announced that its first-generation cards will support A.I.-assisted supersampling. That sounds similar to Nvidia’s Deep Learning Super Sampling (DLSS), which can improve frame rates in demanding games, especially with ray tracing turned on. Intel hasn’t said if its feature works like DLSS yet, but it’s likely similar.
Intel actually poached the creator of DLSS and Nvidia RTX ray tracing, so if there’s anyone who can compete with DLSS, it’s the person who helped create it. DLSS uses a general A.I. model that has been trained on reference images of video games. Then, an algorithm leverages Tensor cores inside of RTX graphics cards to upscale the image while maintaining as much detail as possible.
AMD has a similar feature in the form of FidelityFX Super Resolution (FSR). However, FSR doesn’t leverage dedicated hardware or use A.I. anywhere in the process. The result is an upscaled image that looks good but not as good as one rendered with DLSS.
Based on what we know right now, it looks like Intel is targeting DLSS, not FSR. That will likely mean that you can only use the supersampling feature with an Intel graphics card, but we don’t know for sure at this point.