Introducing Intel Data Center GPU Flex Series Optimized for the Intelligent Visual Cloud

by Tech Mainstream


August 29, 2022


Introducing Intel Data Center GPU Flex Series Optimized for the Intelligent Visual Cloud

Intel Data Center GPU Flex Series, Image/Intel


Equipped with the industry's first hardware-based AV1 encoder in a data center GPU, the Flex Series GPU delivers five times media transcode throughput performance, two times decode throughput performance at half the power of competitive solutions and up to 68 simultaneous cloud gaming streams.

With increasing data center infrastructure demand to compute, encode, decode, move, store and display visual information, the Intel ​Flex Series GPU is designed to resolve today’s computing demand and provide flexibility and scalability for the future.

The Flex Series GPU decreases the total cost of ownership for complex cloud workloads like media delivery, cloud gaming, AI, metaverse and other significant visual cloud use cases:

"Powered by Intel’s Xe-HPG architecture and backed by an expansive ecosystem of hardware vendors and software developers, these GPUs provide flexible scaling of AI inference workloads from media analytics to smart cities to medical imaging between CPUs and GPUs without locking developers into proprietary software."

Normally, data center GPU is hampered with dependence on proprietary, licensed coding models, like CUDA for GPU programming. The Flex Series GPU changes that scenario:

"The Flex Series GPU solution stack overcomes these limitations while delivering significant advantages over alternative solutions, improving flexibility, scalability and power consumption. It helps deliver a lower TCO for solution providers by supporting more subscribers with fewer servers."

The Flex Series GPU technology is run through oneAPI which works without proprietary models and links into different Intel CPUs and GPUs:

"The software stack is enabled by oneAPI – the productive path for accelerated computing – freeing developers from the economic and technical burdens of proprietary programming models. It’s an open alternative to proprietary language lock-in that enables the full performance of the hardware with a complete, proven set of tools that complement existing languages and parallel models. This allows users to develop open, portable code that will take maximum advantage of various combinations across Intel CPUs and GPUs."

The Flex Series GPU will be be advantageous for two particular visual cloud areas:

Media processing and delivery:

1. The Flex Series GPU media architecture, powered by up to four Xe Media Engines, focuses on the highest stream density demands for the modern data center without compromising quality.

2. The Flex Series GPU’s hardware-based, open-source AV1 encoder delivers more than 30% bandwidth savings.

3. Leveraging Intel Deep Link Hyper Encode feature, the Intel Data Center GPU Flex Series 140 with two devices on a single card can meet the industry’s one-second delay requirement while providing 8K60 real-time transcode

Android cloud gaming:

The Flex Series GPU is built for high gameplay quality, delivering an unparalleled gaming experience across different devices. It is validated on nearly 90 of the most popular Google Play Android game titles