Intel Introduces Data Center GPU Flex Series (Arctic Sound-M)
Delivering 5x media transcoding throughput performance and up to 68 simultaneous cloud game streams, the Flex Series GPU is designed to meet the demands of intelligent visual cloud workloads.
New: The Intel® Data Center GPU Flex Series (formerly known as Arctic Sound-M) frees customers from the constraints of siled, proprietary environments and reduces the need for data centers to use separate, discrete solutions. Intel offers customers a unique graphics processing unit (GPU) solution designed to flexibly handle a wide range of workloads without compromising performance or quality. It also helps reduce and optimize TCO for various cloud workloads, such as streaming media, cloud gaming, AI, metaverse, and other emerging use cases. visual cloud.
“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 McVeigh, Intel Vice President and General Manager of the Super Compute Group
What they offer: Flex-series GPUs meet quality, density, and latency requirements. With the industry’s first AV1 hardware encoder in a data center GPU, the Flex Series GPU delivers five times1 media transcoding throughput performance and two times2 decoding throughput performance at half the power of competitive solutions . It offers a bandwidth improvement of more than 30%3 for significant savings in total cost of ownership (TCO), in addition to broad support for the most popular multimedia tools, APIs, frameworks and codecs. more recent.
Powered by Intel’s Xe-HPG architecture and backed by a broad 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.
Why it matters: Media processing, media streaming, AI visual inference, cloud gaming, and desktop virtualization are proliferating in data centers. As a result, the data center GPU silicon market segment for the visual cloud is expected to grow to reach $15 billion by 20264. This rapid increase is in an industry largely beset by reliance on licensed proprietary coding models , like 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. It helps reduce TCO for solution providers by supporting more subscribers with fewer servers.
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 is an open alternative to proprietary language locking that enables full hardware performance with a comprehensive and proven set of tools that complement existing languages and parallel models. This allows users to develop open, portable code that will make the most of various combinations between Intel processors and GPUs.
About performance: From the outset, the Intel Data Center GPU Flex series will offer Android cloud media and gaming processing and streaming capabilities.
Media processing and delivery: The video processing demands of video conferencing, streaming, and social media have transformed the computing resource needs of the data center.
- 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:
- Delivered five times1 media transcoding bit rate, twice2 decoding rate at half power (Intel Flex Series 140 GPU vs. Nvidia A10).
- Provides up to 36 streams of 1080p60 transcoding bitrate per card5.
- Provides eight streams of 4K60 transcoding bitrate per card6.
- When scaled up to 10 cards in a 4U server configuration, it can support up to 360 HEVC-HEVC 1080p60 transcoding bitrate streams4.
- Open Source AV1 Hardware Encoder in Flex Series GPU Delivers Over 30% Bandwidth Savings6. The Flex Series GPU’s media engine also supports and improves the performance of a wide range of industrial codecs, including HEVC, AVC, and VP9.
- Leveraging the Intel® Deep Link Hyper Encode feature, the Intel® Data Center Flex Series 140 GPU with two devices on a single card can meet the industry’s one-second delay requirement while providing transcoding in real time 8K60seven. This capability is available for AV1 and HEVC HDR formats.
Android Cloud Gaming: The explosive growth of cloud gaming has created the need for more flexible solutions that maximize concurrent gaming streams for users. The Flex Series GPU is designed for high quality gaming, delivering unparalleled gaming experience across various devices. It is validated on nearly 90 of the most popular Google Play Android game titles8.
- A single Flex Series 170 GPU can reach up to 68 streams of 720p30 while a single Flex Series 140 GPU can reach up to 46 streams of 720p30 (measured on select game titles)9.
- When scaled with six Flex Series 140 GPU cards, it can achieve up to 216 streams of 720p30.
About the Open Software Stack: Developers can access a comprehensive software stack that combines open-source components and tools to efficiently realize the Flex-series GPU capabilities for visual workloads in the cloud, including shooting in charge of oneAPI and OpenVINO™. 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.
About availability: 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 delivery and Android cloud gaming workloads. Windows cloud gaming, AI and VDI10 workloads will follow.
Click here to post a comment for this news on the message board.