Next-Gen Intel Arc Gaming GPUs To Utilize Multi-Chiplet Design As Hinted Within Patent

As we get close to the launch of Intel's start major discrete graphics family, the latest patent has revealed that the blueish squad is also working on its own multi-chiplet GPU blueprint for the next-gen Arc gaming lineup.

Intel's Next-Gen Arc Gaming GPUs To Leverage From MCM Design, Hints New Patent

Intel is no stranger to MCM technology, in fact, their Ponte Vecchio GPU is a full-on Multi-chiplet blueprint though it is beingness designed and built for the data center segment. However, a new patent titled 'Position-Based Rendering Appliance and Method for Multi-Dice/GPU Graphics Processing', which has been discovered by Underfox, talks about how several GPUs (MCM) can work together for paradigm rendering.

Patent: Position-based rendering apparatus and method for multi-die/GPU graphics processing - Intel

Intel MCM GPUs is coming...

More details: https://t.co/GIkfwrXGzV pic.twitter.com/sXGt9nbJ1S

— Underfox (@Underfox3) February 3, 2022

In the patent, Intel proposes a solution to GPU-based graphics rendering by integrating multiple silicon dies into a single cohesive unit (MCM) capable of running a single 3D context in social club to address manufacturability, salinity, and power commitment problems. Information technology is stated that doing this volition require solutions for multiple classes of scalability and interconnect challenges in order to deliver the best performance on a single 3D application running multiple GPU dies. Some of the algos that are currently in utilise to solve these problems include AFR (Alternating Frame Rendering) and SFR (divide frame rendering).

The patent specifically talks about integrating tile-based checkerboard rendering, which is a very common rendering technique used on current GPUs, forth with distributed GPU vertex position adding to enable more efficient scaling on multi-die GPUs. The draw calls are partitioned in the form of puzzles and sent to the individual GPUs on the MCM chip so that they tin can execute POSH (Position-Only Shaders) to determine the full-frame visibility data for the draws for all dies.

Visibility data then point if the given primitive is present on each of the pre-defined set of screen infinite tiles (checkerboard). When the relevant visibility information is received, each GPU die volition utilise it to limit the geometry work just to relevant primitives and perform pixel processing work for all the titles of the checkerboard that it owns. These GPUs work really fast in working on the single-frame.

Overall, with such a design, the adjacent generation of Intel Arc gaming MCM GPUs can deliver scaled-upward operation with more dies existence added to the chip without facing the performance limitations of existing multi-dice solutions such as AMD XDMA/Crossfire and NVIDIA SLI/NVLINK. Intel states that these solutions are limited in terms of performance and while one should await a perfect scaling of 200% operation with a 2-mode and 400% with a four-mode configuration, the actual GPU performance is significantly lower, and in about cases, not-existent hence why most GPU makers aren't investing in these technologies any more.

This would permit the GPU system to scale more efficiently. Now 1 would say that the 4-GPU/tile solution that is used every bit the instance is official but that's the design that has been proposed and the final number of GPUs per tile could exist vastly unlike.

As mentioned earlier, all GPU makers are investing in multi-GPU technologies with AMD already out with the world's first MCM solution in the form of their Instinct MI200 series, NVIDIA releasing Hopper this year with MCM. There are also the gaming consumer parts such every bit the AMD RDNA 3 lineup which is expected to utilise the same tech when it launches afterward this twelvemonth. Intel themselves are working on several tile-based multi-chip CPU & GPU solutions such as their Shooting star Lake and Granite Rapids designs and within i or ii gens, we could encounter a proper MCM solution within the Arc gaming graphics lineup.

Intel ARC Gaming GPU Lineup

GPU Family	Intel Xe-HPG	Intel Xe2-HPG	Intel Xe3-HPG	Intel Xe Next	Intel Xe Adjacent Side by side
GPU Products	ARC Alchemist GPUs	ARC Battlemage GPUs	ARC Angelic GPUs	ARC Druid GPUs	ARC East*** GPUs
GPU Segment	Mainstream / High-End Gaming (Detached)	Mainstream / High-End Gaming (Discrete)	Mainstream / High-Stop Gaming (Discrete)	Mainstream / High-End Gaming (Discrete)	Mainstream / High-End Gaming (Discrete)
GPU Gen	Gen 12	Gen 13?	Gen 14?	Gen 15?	Gen xvi?
Process Node	TSMC 6nm	TBA	TBA	TBA	TBA
Specs / Design	512 EUs / one Tile / one GPU	TBA	TBA	TBA	TBA
Retention Subsystem	GDDR6	TBA	TBA	TBA	TBA
Launch	2022	2023?	2024?	2025?	2026?