Building High-performance AI Training Systems with Gaudi
Habana's Eitan Medina gives a deep-dive on how AI datacenter and cloud systems can scale up and scale out with GAUDI's integrated on-chip RoCE RDMA.
Startup Expects to Top Nvidia V100 Performance at Half the Power
Linley Group comments on early assessments of Gaudi’s Training performance and power in its June 17 Microprocessor Processor Report. See the report.
Gaudi Performance
A single Gaudi card dissipating 140 Watts,
delivers 1,650 images/second training throughput.
delivers 1,650 images/second training throughput.
And, Gaudi’s training performance scales — from small scale servers to large-scale
deployments— with record-breaking performance.
Gaudi vs. V100
ResNet-50 Training Throughput at Scale
Based on nVidia reported MLPerf V0.5 performance metrics
Designed to Scale
Gaudi is designed for versatile and efficient system scale out and scale up
with integrated on-chip RoCE RDMA, enabling high-performance interconnectivity.
Habana’s use of standards-based connectivity gives
customers freedom from lock-in with proprietary vendor solutions.
Check out our "Scaling AI Training" video
Gaudi Hardware
Gaudi HL-205 Mezzanine Card
Gaudi HL-200 PCIe Card
Gaudi HLS-1
HLS-1 Block Diagram
HLS-1 in a Rack
Based on the Gaudi HLS-1,
the AI Training Rack is modular and flexible to efficiently support
the growing demands on AI compute infrastructure.
+1000 System Scale-out with Gaudi
This shows how a larger system can be built using the Gaudi system as a basic component. It shows three reduction levels—one within the system, another between 11 Gaudi systems and another between 12 islands. Altogether, this system hosts 8*11*12 = 1056 Gaudis. Larger systems can be built with an additional aggregation layer or with less bandwidth per Gaudi
and scalability of Habana Gaudi
Gaudi Software
SynapseAI™ Software Development Platform and Tools simplify building with or migrating to Gaudi-based systems
Habana SynapseAI™ compiler and runtime
- Seamlessly integrates with existing/popular frameworks
- Can be interfaced directly using C or Python API
- Supports both Imperative/Eager and Graph modes
SynapseAI features
- Multi-stream execution environment
- JIT compiler
- Support for dynamic shapes
- Habana Communication Library (HCL), tailored to Gaudi’s high-performance RDMA
- Pre-written and performance optimized TPC kernels
Gaudi Platform state-of-the-art development tools
- Enable users to quickly and easily deploy a variety of network models and algorithms.
- Feature visual real-time performance profiling and tools for advanced users –LLVM-based C compiler, simulator, debugger and profiling capabilities
- Facilitate the development of customized TPC kernels to augment Habana-provided kernels.