Driving AI Efficiency
in the Datacenter
For Advanced Training and Inference Performance
With a leap in deep learning training and inference performance while preserving cost-efficiency.
Supermicro Gaudi®2 AI Training Server SYS-820GH-TNR2.
- Featuring eight Habana® Gaudi®2 AI Training Processors
- Dual 3rd Gen Intel® Xeon® Scalable processors
- Expanded networking capacity with 24x 100 Gb RoCE ports integrated onto every Gaudi2
- 700 GB/second scale within the server and 2.4TB/second scale out
- Ease of system build or migration with Habana® SynapseAI® Software Stack
For cost-efficient training and Inference
Designed to deliver AI training efficiency, usability and scalability:
Supermicro X12 Gaudi Training Server: SYS 420 GH-TNGR
- Featuring eight Habana Gaudi HL-205 processors
- Each Gaudi processor contains ten 100 Gb RDMA over Converged Ethernet (RoCE) ports
- Dual-socket 3rd Gen Intel ® Xeon® Scalable Processors
- Two PCIe Gen 4 switches
- Four hot swappable NVMe/SATA hybrid hard drives
- Scale out with 24x 100 Gb RoCE ports (six QSFP-DDs)
- 32 DIMMs; up to 8TB of DDR4-3200MHz
Inference
Supermicro 4U Server SYS-4029GP-TRT2 featuring Habana First-generation Inference accelerators delivers superior AI inference efficiency and latency
- Up to eight Habana First-generation Inference accelerators
- Dual-socket 2nd Gen Intel® Xeon® Scalable Processors
- 24 DIMMs; up to 6TB 3DS ECC DDR4-2933MHz
- Single Root System for excellent AI processor peer-to-peer communication with sufficient CPU to AI processor throughput
- 11 total PCIe Gen 3 slots
- Hot-swappable high RPM fans
Supermicro AI Training and Inference systems
Based on Habana processors are supported by Habana SynapseAI® Software Suite, offering:
- Integration of TensorFlow and PyTorch frameworks
- Popular models for computer vision and natural language processing applications
- Habana Kernel Library and enablement of Custom Kernel Development
Habana offers extensive support for data scientists, developers, and IT and Systems Administrators with its:
Habana Developer Site: featuring documentation, customer-available software, “how to” content, community Forum
Habana GitHub: providing reference models, set-up and install instructions, snapshot scripts for analysis and debug, custom kernel examples,
roadmap, and “issues” sub-site tracking to dos, bugs, feature requests and more
