For Media Processing & Delivery, Transcoding, Cloud gaming, AI Visual Inferencing
As demand for media and game streaming and visual inferencing continues to increase rapidly, organizations need efficient, scalable solutions that can deliver services to thousands to millions of concurrent users without affecting quality or latency. Supermicro's accelerated computing solutions feature the new Intel Data Center GPU optimized for media and cloud workloads.
Intel GPUs support an open, standards-based software stack optimized for density and quality with critical server capabilities for high reliability, availability and scalability in media processing, media delivery, AI visual inference, cloud gaming and virtualization.
- Video Transcode: 30+ 1080p Streams
- Cloud Gaming: 40+ Game Streams
- Virtual Desktop Infrastructure: 62 Virtualized Functions
- Inference: 150 AI TOPS
- Up to 4 Xe Media Engines
- Up to 32 Xe Cores & Ray Tracing Units
- Industry First AV1 HW Encode & Decode
- XMX AI Acceleration Built in
Watch the TechTalk
Supermicro’s Senior Director, Technology Enablement Thomas Jorgensen sits down to discuss the unique advantages of Supermicro systems based on Intel Data Center GPU Flex Series.
Solution Brief
Supermicro and Intel collaborated to deliver outstanding performance for a large-scale cloud gaming platform establishing over 560 1080p @60Hz transcoded streams per system.
Transcoding Optimized
High performance design for maximum media processing performance, with up to 10 GPUs in a 4U chassis
- GPU: Up to 10 Intel® Data Center GPUs (in PCI-E 4.0 x16)
- CPU: Dual 3rd Gen Intel® Xeon® Scalable Processors
- Memory: 32 DIMMs; up to 8TB, or 12TB with Intel® Optane® Persistent Memory
- Drives: 24x 2.5” hot-swap drive bays (8x NVMe/8x SATA/8x SATA/SAS)
Media Delivery Optimized
Multi-node system with high compute density optimized for media and gaming streaming at the cloud Edge
- GPU: Up to 2 Intel® Data Center GPUs per node (in PCI-E 4.0 x16)
- CPU: Dual 3rd Gen Intel® Xeon® Scalable Processors per node
- Memory: 20 DIMMs; up to 4TB, or 6TB per node with Intel® Optane® Persistent Memory
- Drives: 6x 2.5” hot-swap NVMe/SATA drive bays per node
Cloud Gaming Optimized
Multi-node system designed for high-density GPU configurations in a 2U form factor
- GPU: Up to 3 Intel® Data Center GPUs per node (in PCI-E 4.0 x16)
- CPU: Single 3rd Gen Intel® Xeon® Scalable Processor per node
- Memory: 8 DIMMs; up to 2TB per node
- Drives: 2x 2.5” hot-swap U.2 NVMe drive bays per node
Visual Inferencing Optimized
Scalable platform with up to 6 GPUs designed for image AI processing in the cloud
- GPU: Up to 6 Intel® Data Center GPUs per node (in PCI-E 4.0 x16/x8)
- CPU: Dual 3rd Gen Intel® Xeon® Scalable Processors
- Memory: 16 DIMMs; up to 4TB, or 6TB with Intel® Optane® Persistent Memory
- Drives: 12x 2.5”/3.5” hot-swap NVMe/SAS/SATA hybrid drive bays
For Cloud Scale AI Training
Demand for high-performance AI/Deep Learning (DL) training compute has doubled in size every 3.5 months since 2013 (according to OpenAI) and is accelerating with the growing size of data sets and the number of applications and services based on computer vision, natural language processing, recommendation systems, and more. With the increased demand for greater training performance, throughput, and capacity, the industry needs training systems that offer increased efficiency, lower cost, ease of implementation, flexibility to enable customization, and scaling of training systems. AI has become an essential technology for diverse areas such as virtual assistants, manufacturing operations, autonomous vehicle operations, and medical imaging, to name a few. Supermicro has partnered with Habana Labs to address these growing requirements.
AI Training Optimized
The Supermicro X12 Gaudi AI Training System prioritizes two key real-world considerations: training AI models as fast as possible, while simultaneously reducing the cost of training with unprecedented scale-out bandwidth.
- GPU: 8 Gaudi HL-205 mezzanine cards
- CPU: Dual 3rd Gen Intel® Xeon® Scalable Processors
- Memory: 32 DIMMs: up to 8TB registered ECC DDR4-3200MHz SDRAM
- Drives: 4 hot-swappable NVMe/SATA hybrid hard drives
- Power: 4x 3000W Titanium Level redundant power supplies
- Networking: 24x 100GbE RDMA (6 QSFP-DDs)
- Workloads: AI Training and Inferencing
Computer Vision Applications:
- Manufacturing defect detection, resulting in better products with fewer warranty issues
- Fraud detection, saving billions of dollars annually
- Inventory management, allowing enterprises to become more efficient
- Medical imaging to detect abnormalities
- Identification of photos and videos to enhance security
Language Applications
- Question answering
- Subject matter queries
- Chatbots and translations
- Sentiment analysis for recommendation systems
Supermicro Gaudi®2 AI Training Server (SYS-820GH-TNR2)
Building on the success of the original Supermicro Gaudi AI training system, the Gaudi2 AI Training Server prioritizes two key real-world considerations: integrating multi AI training system to analyze diverse AI models faster, while simultaneously multiple scalability function and price advantages.
- 8 Gaudi2 HL-225H mezzanine cards
- Dual 3rd Gen Intel® Xeon® Scalable processors
- 2 PCIe Gen 4 switches
- 24 hot-swappable hard drives (SATA/NVMe/SAS)
- Fully redundant power supplies
- 24x 100GbE (48 x 56Gb) PAM4 SerDes Links by 6 QSFP-DDs
| Habana Gaudi AI Training System Specifications | X12 Gaudi AI Training Server | Gaudi2 AI Training Server |
|---|---|---|
| Processor Support | Dual 3rd Gen Intel® Xeon® Scalable processors, Socket P+ (LGA-4189), up to 270W TDP | |
| Serverboard | X12DPG-U6 | X12DPG-OA6-GD2 |
| System Memory | 32x DIMM slots, 3200/2933/2666MHz ECC DDR4 RDIMM/LRDIM | |
| AI Processors | 8x Habana Gaudi AI processors on OAM mezzanine cards, 350W TDP, passive heatsinks | 8x Habana Gaudi2 AI processors on OAM mezzanine cards, 600W TDP, passive heatsinks |
| Expansion Slots | Dual x16 PCI-E AIOM (SFF OCP 3.0 superset) plus single x16 PCI-E 4.0 full height, half-length expansion slot | 3 PCI-E Slots: 2x PCI-E 4.0 x8 (FHHL) & 1x PCI-E 4.0 x16 (FHHL). Optional 4x PCI-E 4.0 x8 (LP) or 2x PCI-E 4.0 x16 (LP) |
| Connectivity | 1x 10GbE dedicated IPMI LAN via RJ45, 6x 400Gb QSFP-DD ports, 2x USB 3.0 | |
| VGA/Audio | VGA via BMC | |
| Drive Bays | 4x internal 2.5" hot-swap NVMe/SATA/SAS Drive Bays. | 24x internal 2.5" hot-swap NVMe/SATA/SAS Drive Bays |
| Storage | 2x M.2 NVMe OR 2x M.2 SATA3 | 2x M.2 PCIe 3.0 x4 slots |
| Power Supply | 4x 3000W redundant power supplies, 80+ Titanium level Tested power draw: 4922W* | 6x 3000W High efficiency (54V+12V) |
| Cooling System | 5x removable heavy-duty fans | 12x removable heavy-duty fans |
| Operating Temperature | 10°C ~ 35°C (50°F ~ 95°F) | |
| Form Factor | 178 x 447 x 813mm (7" x 17.6" x 32") | 447 x 356 x 800mm (17.6" x 14" x 31.5) |
| Weight | Gross weight: 137lbs (62kg) | TBD |
| * Tested configuration: | ||
Supermicro TECHTalk: New Media Processing Solutions Based on Intel Data Center GPU Flex Series
Watch as our product experts discuss the new Supermicro solutions based on the just announced Intel Data Center GPU Flex Series. Learn how these solutions can help benefit you and your company.
Delivering Scalable Cloud-Gaming
Supermicro Systems with Intel® Data Center GPU Flex Series
Supermicro offers all the system components for cloud service providers to build green, cost-effective, and profitable cloud gaming infrastructure.
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Sep 08 2022, 10:00am PDT
Supermicro and Intel product and solution experts will discuss, in an informal session, the benefits of the solutions in the areas of Cloud Gaming, Media Delivery, Transcoding, and AI Inferencing using the recently announced Intel Flex Series GPUs. The webinar will explain the advantages of the Supermicro solutions, the ideal servers and the benefits of using the Intel Flex Series GPUs.
Supermicro and Habana® High-Performance, High-Efficiency AI Training System
Enabling up to 40% better price/performance for Deep Learning training than traditional AI solutions