Cluster track · Presentation
Node-to-Rack Efficiency for Real-World AI Inference: Arm and FuriosaAI
- When
- Thursday, February 4, 202711:45 AM to 12:05 PM PT
- Where
- Room BSan Jose McEnery Convention Center
- Track
- ClusterArchitecting 1M GPU Clusters. Programmed by CloserStill with OCP
- Format
- Presentation
About this session
AI inference moves from isolated accelerator performance to production-scale deployment, efficiency needs to be evaluated across the full system: host CPU, accelerator, software stack, server node, and rack-level architecture. In this session, Arm and FuriosaAI will explore how Arm-based host infrastructure and FuriosaAI RNGD accelerators can work together to improve real-world inference efficiency from node to rack. Building from node-level architecture, the session will then discuss how these efficiency gains translate into rack-level considerations, including performance density, power and thermal envelope, serviceability, and deployability in OCP-aligned infrastructure environments.
General rate, until Feb 2, 2027
Register for Digital Infrastructure World 2027
One pass covers this session and every other session, plus OCP Tech Day, the keynotes and the exhibit hall, on all three days.
- All Access$799
- Open Compute Project members$399
- Teams of 3 or more, each$599.25
More in the Cluster track
- From Hardware to Useful Capacity: Provisioning AI Infrastructure at Scale
- Beyond Physical Digital Twins: Why Logical Digital Twins Are Essential for AI Factory Design, Validation and Operations
- Overcoming AI's Power and Space Constraints with Scale-Across Deployments
- One Rack, More Than One Accelerator: Lessons from Building an Open AI Rack