OPI Summit on DPU/IPUs

October 15, 2026 * San Jose, CA

Mark you calendar! The Second OPI Summit on DPU/IPUs will be co-located with the OCP Global summit, and will take place in October 2026. The OPI Summit is open to everyone involved in the design, development, integration, marketing, use, or support of DPU/IPUs, or related hardware, software, or services. The Second OPI Summit on DPU/IPUs seeks original, high-quality submissions that improve and further the knowledge of DPU/IPUs, with an emphasis on ease-of-use, PoC implementations, and experimental results. We are interested in systems of all scales, from small embedded devices to data centers and clouds.

DATES TO REMEMBER:

• CFP Close: Sunday, August 23, 2026 at 11:59 PM PDT (UTC -7)
• CFP Notifications: Monday, August 24 – Friday, August 28
• Schedule Announced: Wednesday, September 2
• Event Date: Thursday, October 15, 2026

Submit to Speak:

At this year’s summit, we will focus heavily on ease-of-use, Proof of Concept (PoC) implementations, and real-world experimental results. We want to see how these technologies perform in the wild—across systems of all scales, from small embedded edge devices to massive, multi-tenant hyperscale clouds.

We are seeking original, high-quality submissions that dive deep into the practical aspects of DPU/IPU integration. If you are working on cutting-edge implementations, we want to hear from you! Please submit your proposal by August 23, 2026:

SUGGESTED TOPICS

• Applications on DPU/IPUs: Networking, security, storage (including disaggregated storage protocols like NVMe-oF), HPC, etc.
• Provisioning, LCM, and Fleet Management: Vendor-agnostic solutions and API standardization.
• Use DPU/IPUs in Kubernetes environments: Use-cases, operators, resource-management, and ensuring DPUs support multi-tenancy for different ISVs.
• Standards and Interoperability: Applicable to DPU/IPUs across the ecosystem.
• DPU/IPUs in AI Infrastructure & Inference: Managing AI inference data movement, AI-driven storage (KV cache offloads), secure GPU assignment via device attestation, and reducing virtualization compute overhead to free up rack space and power for AI hardware.
• Virtualization & Standard VM Workloads: Supporting legacy enterprise environments (OpenStack/QEMU), virtualization stack optimization (e.g., OVS offload), and utilizing Host-Initiated IPU (Standard NIC/FNIC mode) for frictionless adoption.
• Confidential Computing & Advanced Security: Securing boundaries between the host and IPU, providing tenant-specific secure tunnels (host pod isolation), and utilizing DPU/IPUs for crypto offloads
• Sustainability & Edge Computing: Optimizing power and thermal envelopes in high-density data centers, and leveraging DPUs at the network edge for low-latency localized processing.

Click here to submit your speaking proposal. 

Stay tuned for more details.