Intel introduces Arctic Sound-M graphics cards


Intel’s Arctic Sound graphics cards for data centers have been around for quite some time in one form or another. These cards were announced in late March (without fanfare, though) and are expected to be available in Q3 2022. Our colleagues at ServeTheHome were lucky enough to see these cards on display at the Intel Vision event last week,

Intel’s Arctic Sound family for data centers includes two boards: the ATS-M75 and ATS-M150; their model numbers correspond to their maximum graphics power (TGP). The low-profile ATS-M75 card is based on two ACM-G10 GPUs with eight GPU compute units, while the full-height ATS-M150 card is powered by the larger ACM-G11 GPU with 32 compute units, according to ServeTheHome.

(Image credit: Intel)

While Intel’s Arctic Sound-M graphics cards position themselves as data center GPUs, they’re primarily intended for video, gaming, remote desktops, and other similar applications, but not heavy-duty loads. heavy GPU computing work. Meanwhile, as a bonus, Intel’s DG2 family discrete GPUs also support XMX instructions, so they can accelerate AI inference workloads. Therefore, you won’t find Intel’s ATS-M cards among the best graphics cards available today, although ACM-G11 GPUs power desktop graphics cards for gamers.

Intel will offer its compute GPUs codenamed Ponte Vecchio, designed explicitly for highly parallel computing workloads and leveraging the appropriate microarchitecture (Xe-HPC). Ponte Vecchio targets artificial intelligence and high-performance computing applications that require performance beyond what Intel’s Arctic Sound products can deliver.

Image 1 of 2


(Image credit: ServeTheHome)
Picture 2 of 2


(Image credit: ServeTheHome)

One of the advantages of Intel’s Arc Alchemist GPUs (and therefore Arctic sound cards) over competing products is support for AV1 hardware encoding. For obvious reasons, Intel is going to heavily promote this feature coupled with the relatively low power consumption of these cards.

Intel’s own Xeon processors and Nvidia’s GPUs dominate the market for video encoding/decoding applications in the data center, so Arctic Sound will allow Intel to meet the need since it already knows the market quite well. Meanwhile, Google’s YouTube today uses the company’s custom Argos video transcoding units (VCUs) developed in-house, so it remains to be seen whether the video streaming service finds Intel’s GPUs a more efficient solution than its own VCUs.

Intel will begin shipping its Arctic Sound cards for virtual desktop, media processing, AI inference, and cloud gaming applications in Q3 2022.


About Author

Comments are closed.