Intel teases Arctic Sound M GPU for data centre at its Vision 2022 Event

More From Author

See more articles

Myntra Upcoming Sales 2025: Your Fashion Calendar for Maximum...

Myntra Upcoming Sales 2025 In the ever-evolving world of fashion e-commerce, Myntra continues to be India's go-to destination...

Dimensity 6020 vs Snapdragon 695: Mid-Range Chipset Battle

Dimensity 6020 vs Snapdragon 695: Qualcomm Snapdragon 695 5G (SD695) is a fast mid-range ARM-based SoC found...

My Jio Recharge Plans as of January 4,...

My Jio Recharge Plans: Since its establishment in 2016, Reliance Jio has made a remarkable impact on...

Intel has described its Arctic Sound M data centre GPU, stating that it will be ready in Q3 2022 — but with all of Intel’s Arc GPU delays, no one in their right mind would trust their GPU shipment dates — still, let’s get this Arctic Sound M GPU show on the road.

The Arctic Sound M comes in two versions, the first of which is the flagship model with a single ACM-G10 GPU and a 150W power supply. The second card has two ACM-G11 GPUs and a lower TDP of 75W, but it’s designed for high-density multi-purpose tasks. “Super flexible data centre GPUs geared at cloud gaming, media processing and delivery, virtual desktop infrastructure, and inference,” according to Intel.

According to reports, Arctic Sound GPUs can manage 30+ 1080p streams, 40+ gaming streams, 62 Virtualized Functions, and 150 AI TOPs. Intel claims that its new Arctic Sound M GPUs will have cutting-edge technology like as AV1 HW Encode/Decode and XMX AI-Accelerators.

Arctic Sound M enables AV1 encoding, which is expected to become a popular standard among streamers, content suppliers, and artists

Arctic Sound M
credit: Intel

The necessity for AV1 hardware compatibility may provide Intel with a significant edge in the near to medium term if AV1 becomes more commonly adopted by streaming services. Arc desktop GPUs are also expected to enable AV1 encoding.

At the occasion, Raja Koduri, Intel’s chief architect, stated that the company’s silicon strategy is oriented toward applications such as the metaverse. Project Endgame, he added, is about delivering continuous compute for the metaverse. On an ordinary PC, he demonstrated Epic Games’ Unreal Engine 5 at an extremely slow FPS.

Arctic Sound M
credit: Unreal Engine 5

The demo in the Matrix Awakens city becomes much more fluid and real-time after turning on the continuous compute infrastructure, which looks for compute power in the cloud. According to Koduri, such experience will be four to five years away.

The Aurora supercomputer, which uses Intel’s Ponte Vecchio graphics chips, was built in collaboration with Argonne National Laboratory. There are six of these chips on a single card and several blades across the supercomputer, which has 60,000 Ponte Vecchio chips spread across 10,000 nodes.

The new Arctic Sound M GPUs from Intel are set to launch in Q3 2022, but nobody knows if that will materialise. Intel has just stated that its new desktop-focused Arc Alchemist GPUs will be delayed and will instead be available in China later this year.

also read:

Nvidia and AMD Graphics cards are now selling for just 10% over MSRP in Germany

source

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.

━ Related News

Featured

━ Latest News

Featured