Something to anticipate: The Intel Xe graphics job constructs on top of over a years of experience making incorporated GPUs and its associated software stack. With the company getting closer to developing a full-fledged video gaming GPU, expectation is high because they might really take on AMD’s Big Navi and Nvidia Ampere (RTX 30 series), ray tracing and all.
Earlier this year, Intel started delivering the very first generation Xe desktop graphics cards to system contractors. These are fairly modest entertainers that can just take on some entry-level mobile graphics chipsets for laptops, however they’re a terrific start and definitely more engaging than something like Nvidia’s reanimated GeForce GT 710.
In the meantime, Intel engineers have been working hard on a new Xe microarchitecture that will scale from integrated graphics on mobile CPUs all the method up to the information. During Intel’s Architecture Day 2020 occasion, the company described that it’s working on Xe HPG chips that will pack GDDR6 memory and support for ray tracing.
Gamers and PC lovers have been awaiting details on its advancement, but it was just last month that we got a tweet from Intel’s chief GPU designer, Raja Koduri, who revealed the company is already evaluating an Xe HPG chip using 3DMark’s new Mesh Shader efficiency test.
Today, we got the very first genuine tip (thanks, PC World)– Intel’s upcoming gamer-focused GPU needs to be able to reach a minimum of GeForce RTX 3070 levels of efficiency according to synthetic workloads.
From 2012 to 2021 – very same Intel Folsom lab, many of the exact same engineers with more grey hair, I was at Apple back then, getting hands on with pre-production crystalwell, 9 years later having fun with a GPU that’s>20 x faster! pic.twitter.com/RgmRJuhOXw
— Raja Koduri (@Rajaontheedge) March 12, 2021
Koduri shared a picture that reveals much of the very same individuals that worked on Intel’s Crystal Well tech back in 2012, are now working on Xe HPG at the very same Intel Folsom laboratory and seeing 20 x the efficiency in artificial benchmarks. Crystal Well describes the Intel Iris Pro 5200 incorporated graphics that featured an embedded DRAM cache and is capable of anywhere between 1,350 to 1,450 points on the 3DMark Fire Strike test.
Nvidia’s almost unobtainable RTX 3070 and RTX 3080 graphics cards can get around 25,000 points and 30,000 points, respectively. Intel’s own Xe Max is able to get around 5,800 points.
Of course, that doesn’t state how well an Xe HPG graphics card would compare with Nvidia’s offering in terms of video gaming efficiency. Still, there are a few things to enhance the plausibility of this contrast. Initially, is that Intel will utilize a different procedure node than its 10 nm SuperFin, that makes it one of the possible purchasers of TSMC’s excess wafer capability.
Intel’s big “fabulous” Xe HP packages
The second thing to think about is that Intel’s Xe HP architecture is developed to scale well utilizing “tiles” that each have 512 execution systems, or the rough equivalent of 4,096 shader cores for Nvidia and AMD graphics options. The Xe HPG will no doubt cut a lot of the unnecessary functions of its server counterpart in favor of more execution systems performing at higher clocks. And Intel could also use 2 HPG tiles connected via an embedded multi-die interconnect bridge (EMIB) to pack a lot more brute power, similar to SLI and Crossfire but with better scaling and less stuttering.
In any case, Intel could be preparing to hit Nvidia and AMD with a compelling graphics solution at a time when both are having a hard time to meet need for their newest offerings. If the performance, power intake, and prices are right, Intel’s Xe HPG might get adopted into a lot of gamer rigs whenever it arrives.