OpenFabrics Alliance Courses

Peer Provider Composability and API Design in libfabric

Dive into advanced network communication optimization using libfabric's peer provider architecture for enhanced performance across multiple hardware and transport configurations.

• YouTube
• 1 hour
• On-Demand
• Free Video

The Next Decade of Networking Challenges and Opportunities

Explore emerging advances in network technology, from transport protocols to hardware, and understand key challenges in supporting future applications across edge, cloud, and data centers.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Conversational AI-Enabled User Interface for HPC Tools

Discover how AI-powered conversational interfaces can simplify complex HPC tools, making performance analysis more accessible through natural language commands and improving productivity for both novice and expert users.

• YouTube
• 22 minutes
• On-Demand
• Free Video

High Performance Scalable Support for Big Data Stacks with MPI - Leveraging MPI4Spark and MPI4Dask

Discover how MPI4Spark and MPI4Dask enhance big data frameworks by leveraging high-speed networks and HPC systems for improved performance and scalability in distributed computing environments.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Accelerating Scientific Computing Workloads with InfiniBand DPUs

Discover how InfiniBand DPUs and In-Network Computing accelerate complex scientific workloads, boost performance, and enable faster research insights through advanced networking capabilities.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Congestion Management for Multicast on ROCE v2 - Implementing Backpressure Mechanisms

Explore RDMA multicast migration from InfiniBand to Ethernet (ROCE v2), focusing on congestion management techniques like ECN and Cisco Pause Frames for reliable data transmission.

• YouTube
• 17 minutes
• On-Demand
• Free Video

Status of OpenFabrics Interfaces (OFI) Support in MPICH

Discover the latest developments in OpenFabrics Interfaces (OFI) support within MPICH, exploring implementation status and advancements in high-performance computing infrastructure.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Universal Chiplet Interconnect Express - Building an Open Ecosystem of Chiplets

Discover how UCIe technology enables mixing chiplet components from multiple vendors for customized System-on-Chip construction, addressing growing compute demands across various sectors.

• YouTube
• 48 minutes
• On-Demand
• Free Video

Designing Networking Stacks for Machine Learning Frameworks

Dive into networking stack design for machine learning frameworks, exploring challenges, solutions, and real-world applications through NCCL case studies and prototype implementations.

• YouTube
• 41 minutes
• On-Demand
• Free Video

DPU-Powered File System Virtualization - Improving Cloud Infrastructure Efficiency

Discover how DPU-powered file system virtualization improves cloud infrastructure efficiency by offloading client-side drivers, enhancing tenant isolation, and delivering 4.4× CPU efficiency gains without host modifications.

• YouTube
• 28 minutes
• On-Demand
• Free Video

iCheck - Leveraging RDMA and Malleability for Application-Level Checkpointing in HPC Systems

Discover how RDMA and malleable multilevel checkpointing can enhance HPC system reliability through iCheck framework, offering improved performance and efficient data transfer mechanisms for supercomputing applications.

• YouTube
• 32 minutes
• On-Demand
• Free Video

OpenFabrics Interfaces Support and GPU Integration in MPICH

Discover the latest updates on OFI integration in MPICH, focusing on GPU support implementation, network API enhancements, and Libfabric development for high-performance computing systems.

• YouTube
• 22 minutes
• On-Demand
• Free Video

RDMA and Linux TCP - Zero-Copy Kernel Bypass for High-Performance Networking

Dive into high-performance networking with RDMA interfaces and Linux TCP stack optimization, exploring zero-copy techniques and kernel bypass for achieving 800Gbps throughput.

• YouTube
• 41 minutes
• On-Demand
• Free Video

Open MPI and Libfabric Integration for the Frontier Supercomputer

Delve into high-performance computing optimization through Open MPI and libfabric implementation on Frontier supercomputer, focusing on AMD MI250X architecture and HPE Slingshot NICs integration.

• YouTube
• 27 minutes
• On-Demand
• Free Video

Supporting an Upstream First Kernel Driver for HPC Fabrics

Explore the evolution and improvements of the HPC fabric driver hfi1, from its staging phase to mainline kernel integration, focusing on upstream development and open-source delivery methods.

• YouTube
• 34 minutes
• On-Demand
• Free Video