Open Compute Project Courses

Multi-Headed Composable Memory Appliance MHCMA Next Generation

Explore next-generation ASIC-based composable memory architecture with 8x8 PCIe-Gen5 CXL2.0 host ports per blade, advancing from FPGA to 12nm ASIC for enhanced pooled memory solutions.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

Ultra Ethernet - Escaping the Chaos of Order

Explore how Ultra Ethernet 1.0 eliminates network packet ordering requirements, reducing costs while delivering scalable AI-era communication solutions over proven Ethernet infrastructure.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

Data Center Facility Project Highlights - Integrated Solutions for Mechanical Performance and Thermal-Electrical Efficiency

Discover how Open Compute Project optimizes data center infrastructure through integrated mechanical, thermal, and electrical solutions for enhanced operational efficiency.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Operating Temperatures to Support Performance, Energy Efficiency, and Heat Recovery

Discover how to optimize data center fluid temperatures for maximum compute performance, energy efficiency, and heat recovery as rack power densities increase.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Infinite HBD Scale-Up Outside the Box - Disaggregated Switch Networks for AI Computing

Discover how InfinitHBD revolutionizes AI scale-up networks using disaggregated switches instead of high-radix switches for improved cost efficiency and fault resilience.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Large CXL Memory Expansion Systems and Workloads

Discover how CXL memory expansion systems enable 100 TiB-class workloads through composable provisioning, shared memory paradigms, and breakthrough performance architectures.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Hyperconverged Quantum Cluster Architecture and Operational Insights from a Live Quantum Data

Discover hyperconverged quantum cluster architecture and gain operational insights from live quantum data in this technical presentation by Dr. Nikola Šibalić.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Harnessing Time Coordinated Computing (TCC) to Enable the Next Generation of Applications

Discover how Intel's Time Coordinated Computing enables real-time applications through secure, deterministic connectivity across platform and network stacks for next-gen computing.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Wired for Success - Enhancing AI Cluster Reliability with Copper Cables

Discover how Active Electrical Cables enhance AI cluster reliability through cost-efficient, low-power solutions and innovative cable management strategies for hyperscale deployments.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

New Strategic Initiative - Open Cluster Designs for AI

Discover standardized designs for AI cluster infrastructure, covering scale-up/scale-out networks, modularity principles, and management solutions for high-performance AI-ML systems.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

OCP Telemetry White Paper - A Summary of the Work Led by Hyperscalers on DC Telemetry Guidelines

Discover how hyperscalers are standardizing data center telemetry to enable secure tenant access to critical infrastructure data for optimized operations and efficiency.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

Scale Out Networks and Scale Up Architectures with Co-Packaged Optics

Discover how Co-Packaged Optics (CPO) enables scale-up domains beyond 512 nodes while addressing bandwidth, power, and latency constraints for growing AI model parameter sizes.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Accelerating HPC and AI Applications by Offloading Computation and Communication to SmartNICs

Discover how SmartNICs accelerate HPC and AI applications through computation and communication offloading techniques for enhanced performance.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Scaling OCP NIC to 1.6T and Beyond for AI

Explore scaling network interface cards to 1.6T speeds and beyond for AI training clusters, addressing thermal, power, and bandwidth challenges in modern data centers.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

OpenXLA - Portable Performance for the Heterogeneous Hardware Era

Discover how OpenXLA delivers portable performance optimization across diverse hardware architectures in today's heterogeneous computing landscape.

• YouTube
• 17 minutes
• Self-Paced
• Free Video