Open Compute Project Courses

NVIDIA Spectrum-X Network Platform Architecture for AI Cloud Performance

Dive into NVIDIA's Spectrum-X networking innovations, exploring how this Ethernet platform revolutionizes AI cloud performance through advanced routing, telemetry, and multi-tenant capabilities.

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

Optcast: Open-Source Aggregation Offloading for Distributed Deep Learning

Discover how to accelerate distributed AI training through open-source in-network aggregation, achieving 1.72x faster performance across multiple GPUs without specialized hardware requirements.

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

Scheduled Ethernet Fabric for Large-Scale AI Training Clusters

Discover how Scheduled Ethernet Fabric optimizes large-scale AI training clusters, enabling efficient GPU connectivity, workload management, and resilient networking for enhanced computational performance.

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

SONiC Evolution for Enterprise Networks - From Data Centers to Campus Infrastructure

Discover how SONiC's disaggregated networking and open-source software are evolving to meet enterprise needs, from campus edge to core networks, with purpose-built hardware solutions.

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

Software Defined Connectivity in Enterprise Networks - A Holistic Approach

Explore how Software Defined Connectivity, SONiC, and White Label Switches integrate with business architectures and FinOps to create optimized, cost-effective enterprise network solutions.

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

Analog In-Memory Computing with Multilevel Memristive Devices for High Performance Computing

Discover how multilevel memristive devices revolutionize computing by enabling analog in-memory processing, boosting throughput and energy efficiency for deep learning applications and high-performance computing.

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

Chiplet-Based Compressed LLC Cache and Memory Expansion for Data Centers

Explore hardware-accelerated chiplet technology for real-time memory compression, enabling cost-effective cache expansion and improved data center performance through innovative architectural solutions.

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

Scaling Systems for Generative AI - Building and Deploying Large Language Models

Discover key strategies for efficiently scaling and deploying generative AI models and large language models across distributed systems using Intel's advanced technologies.

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

Ceramic Nano Memory - Enabling the AI Storage Dataverse

Discover how Ceramic Nano Memory revolutionizes data storage with sustainable, high-density solutions using inorganic nanolayers on glass, enabling fast access and scalability for AI-driven data centers.

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

Breaking the Barrier: Chip Level Cooling Up to and Beyond 1000W in Single Phase Dielectric Fluid

Discover groundbreaking advancements in single-phase dielectric fluid cooling technology for data centers, achieving unprecedented 1000W+ chip-level cooling capabilities for AI applications.

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

Environmental Impact Analysis of Air and Liquid Cooled Servers - Choosing the Right Cooling Technology

Explore the environmental impact comparison between air and liquid-cooled server systems across different locations, focusing on carbon emissions and sustainability considerations.

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

Open Infrastructure Platforms to Usher in the Age of Generative AI

Explore Meta's infrastructure innovations for GenAI, from MTIA chips to Grand Teton systems, covering deployment strategies, liquid cooling advances, and future data center challenges.

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

Enabling Synchronization for Seamless Integration of Data Centers in 5G

Dive into advanced synchronization techniques for integrating data centers with 5G networks, focusing on holdover capabilities and tight synchronization requirements.

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

Composable Memory Systems Overview for Hyperscale Infrastructure

Explore the latest developments in composable memory systems, focusing on CXL-based solutions, system architecture, and hyperscale infrastructure optimization for enhanced performance.

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

Delivering Unprecedented Scale for AI Infrastructure and Cloud Connectivity

Discover how purpose-built connectivity solutions like PCIe, CXL, and Ethernet overcome performance bottlenecks and scale memory bandwidth, processing, and rack connectivity for AI infrastructure.

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