Launched Intel Data Center GPU Flex Series for Intelligent Visual Cloud

Intel introduced the Intel Data Center GPU Flex series (officially named Arctic Sound-M), designed to meet the demands of intelligent visual cloud workloads. Originally announced in May, the Flex Series GPU is a unique graphics processing solution designed to handle a wide range of workloads without compromising performance or quality.

Intel introduced the Intel Data Center GPU Flex series (officially named Arctic Sound-M), designed to meet the demands of intelligent visual cloud workloads. Originally announced in May, the Flex Series GPU is a unique graphics processing solution designed to handle a wide range of workloads without compromising performance or quality.

Delivering 5X media transcoding throughput performance and up to 68 simultaneous cloud gaming streams, the new GPU helps reduce and optimize TCO for various cloud workloads such as streaming media, cloud gaming , AI, Metaverse, and other emerging visual cloud use cases.

Jeff McVeigh, Intel Vice President and General Manager of the Super Compute Group, explained:

“We are in the midst of a pixel explosion driven by more consumers, more applications and higher resolutions. Today’s data center infrastructure is under intense pressure to compute, encode, decode, move, store and display visual information.The Intel Flex Series GPU is a revolutionary design that uniquely addresses today’s computing demands while providing flexibility and scalability for tomorrow’s immersive experiences.

Jeff has a launch video that we shortened for those who want the highlights.

Intel Data Center GPU Flex Series

Flex Series GPUs meet quality, density, and latency requirements. Featuring the industry’s first hardware-based AV1 encoder in a data center GPU and, according to Intel, delivers five times the media transcoding throughput performance and twice the decoding throughput performance at half power competing solutions. The new GPU offers over 30% improvement in bandwidth for significant total cost of ownership (TCO) savings and broad support for the latest media tools, APIs, frameworks and codecs.

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

Media processing and delivery, AI visual inference, cloud gaming, and desktop virtualization are all ramping up in data centers. As a result, based on the findings of several researchers, the data center GPU silicon market segment for visual cloud is expected to reach $15 billion by 2026. proprietary and licensed coding models, such as CUDA for GPU programming.

The Flex Series GPU solution stack overcomes these limitations while providing significant advantages over alternative solutions, improving flexibility, scalability, and power consumption. The Intel GPU can result in lower TCO for solution providers by supporting more subscribers with fewer servers.

The software stack is API-enabled, the productive path to accelerated computing. This single stack relieves developers of the burden of proprietary programming models, allowing users to develop open, portable code that takes advantage of various combinations between Intel processors and GPUs.

Up to four Xe Media Engines power the media architecture of the Flex Series GPU and focus on the highest stream density demands of the modern data center without compromising quality. The Intel Flex GPU delivers five times the media transcoding throughput and twice the decoding throughput at half the power (Intel Flex Series 140 GPU vs. NVIDIA A10). It offers up to 36 streams of 1080p60 transcoding bitrate and eight streams of 4K60 transcoding bitrate per card. When scaled up to 10 cards in a 4U server configuration, the Intel Flex GPU supports up to 360 HEVC-HEVC 1080p60 transcoding bitrate streams.

The open source AV1 hardware encoder of the Flex Series GPU saves more than 30% bandwidth. The media engine improves the performance of various industrial codecs, including HEVC, AVC and VP9. Leveraging Intel’s Deep Link Hyper Encode feature, the half-height 140 with two devices on a single card meets the industry’s one-second delay requirement while providing real-time 8K60 transcoding. This capability is available for AV1 and HEVC HDR formats.

The explosive growth of cloud gaming has created the need for more flexible solutions to maximize concurrent gaming streams for users. The Flex Series GPU is designed for high quality gaming, delivering an unparalleled gaming experience across various devices, and is validated on nearly 90 of the most popular Google Play Android game titles. For example, a single Flex Series 170 GPU can achieve up to 68 streams of 720p30, while a single Flex Series 140 GPU can achieve up to 46 streams of 720p30 (measured on select game titles) and when scaled with six Flex Series 140 GPU cards, it can achieve up to 216 streams of 720p30.

The Open Software Stack gives developers access to a comprehensive software stack that combines open source components and tools to efficiently realize the Flex-series GPU capabilities for cloud visual workloads, including support for oneAPI and OpenVINO support. Intel’s oneAPI tools enable developers to deliver accelerated applications and services, including the Intel oneAPI Video Processing Library (oneVPL), Intel VTune Profiler, and more.

Availablity

Systems with Flex Series GPUs will be available from global vendors including Dell Technologies, HPE, H3C, Inspur, Lenovo, and Supermicro. Solutions with the Flex Series GPU will ramp up over the next few months, starting with media streaming and Android cloud gaming workloads, followed by Windows cloud gaming workloads, d ‘IA and VDI10.

Click the link for more information on the Intel Data Center GPU Flex series.

Engage with StorageReview

Newsletter | YouTube | iTunes/Spotify Podcasts | Instagram | Twitter | Tik Tok | RSS feed

Comments are closed.