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.

Today as part of CES 2022, Intel demonstrated advancements and momentum with Mobileye, progress toward discrete graphics leadership and the launch of the newest members of the 12th Gen Intel Core family. With these milestones, Intel furthers its commitment to enable the industry and its customers and partners to harness the technology superpowers - ubiquitous computing, cloud-to-edge infrastructure, pervasive connectivity and artificial intelligence - at the heart of the digital transformation.

During the Intel news conference, Gregory Bryant, executive vice president and general manager of the Client Computing Group, was joined by Lisa Pearce, vice president of the Visual Compute Group, and Prof. Amnon Shashua, Mobileye CEO, to share Intel's progress across multiple strategic businesses. "The Intel execution engine is back. From advancing the PC to high-performance graphics to autonomous driving solutions, Intel and Mobileye are proud to create new ecosystems and opportunities across multiple industries," Bryant said. "Together with our partners and customers, we are driving new innovation across products, platforms and services, and delivering on our vision of enabling world-changing technology that improves the lives of every person on the planet."

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.

Intel plans to go full tilt with gaming graphics, with its newly announced Arc line of graphics processors designed for high-performance gaming. The top Arc "Alchemist" part meets all requirements for DirectX 12 Ultimate logo, including real-time raytracing. The company, during the technology's reveal, earlier this week, also said that it's working on an AI-accelerated supersampling technology. The company is calling it XeSS (Xe SuperSampling). It likely went with Xe in the name, as it possibly plans to extend the technology to even its Xe LP-based iGPUs and the entry-level Iris Xe MAX discrete GPU.

Intel claims that XeSS cuts down 4K frame render-times by half. By all accounts, 1440p appears to be the target use case of the top Arc "Alchemist" SKU. XeSS would make 4K possible (i.e., display resolution set at 4K, rendering at a lower resolution, with AI-accelerated supersampling restoring detail). The company revealed that XeSS will use a neural network-based temporal upscaling technology that incorporates motion vectors. In the rendering pipeline, XeSS sits before most post-processing stages, similar to AMD FSR.

While AMD's FSR technology is purely shader based, the Intel algorithm can either use XMX hardware units (new in Intel Xe HPG), or DP4a instructions (available on nearly all modern AMD and NVIDIA GPUs). XMX stands for Xe Matrix Extensions and is basically Intel's version of NVIDIA's Tensor Cores, to speed up matrix math, which is used in many AI-related tasks. The Intel XeSS SDK will be available this month, in open source, using XMX hardware, the DP4a version will be available "later this year".