MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet/iWARP, RoCE, and Slingshot

High-Performance and Smart-Networking Technologies for HPC and AI

[Tutorial]

Principles and Practice of High-Performance AI Training and Inference

[Tutorial]

Workshop on High Performance Fabrics for AI and HPC

[Workshop]

Exploiting Performance and Scalability with MVAPICH Libraries

[Talk]

Overview of the OSU HPC-AI Stack - MPI-driven Runtime for High-Performance AI

[Talk]

MLPerf Training 6.1 Insights

[Talk]

NIC-Bench: Accurate Benchmarking and Modeling of Network Performance for Modern HPC and AI Systems

[Talk]

OpenSHMEM: Toward a Unified GPU-Aware Auxiliary Specification and 2.0

[BoF]

Connecting GPU Resources Across Sites: A Collaboration Between 1FINITY and X-ScaleSolutions

[Talk]

MVAPICH Performance and Scalability on the TACC Horizon System

[Talk]

One Memory-Many Paths: Early Experiences with Allocation and Data Copy Strategies on MI300A

[Talk]

AI Fabric Load Balancing Benchmark Practices

[Talk]

X-ScaleAI: Scaling Your Challenging AI Applications with Efficiency and Ease

[Talk]

Agentic Computing and Services for the Computing Continuum

[BoF]

System-Aware Co-Design for Accelerating End-to-End Deep Learning Lifecycles on Heterogeneous HPC Platforms

[Talk]

Accelerating HPC and AI Applications using Novel Products from X-ScaleSolutions

[Talk]

Presentation at the Broadcom Booth: High-Performance and Scalable Middleware for HPC and AI

[Talk]

HAT-MPI: Hierarchical Auto Tuning of MPI Inter-Node Communication on InfiniBand Clusters

[Talk]

Unified Communication X (UCX) Community

[BoF]

Introducing Thor Ultra NIC: The first enhanced RoCE (eRoCE) NIC for HPC and AI

[Talk]

Enhanced MPI Intra-node Communication Framework: A Hybrid Approach with Cooperative DMA Channel-based Data Transfer

[Talk]

ParaTools Pro for E4S(TM): An HPC-AI Software Ecosystem for Science

[Talk]

Characterizing Communication Patterns in Distributed Large Language Model Inference

[Talk]

From Transport to Collectives: Building an End-to-End Communication Stack for AI Supercomputers with MRC and MSCCL++

[Talk]

MPICH: A High Performance Open-Source MPI Implementation

[BoF]

Ultra Ethernet: Next-Generation Networking for HPC Supercomputers and AI Factories

[BoF]

Supporting Ultra-High Resolution Digital Agriculture Tasks with Fully Synthetic Curriculum Learning

[Talk]

Experiences with MVAPICH-Plus on Miyabi at JCAHPC

[Talk]

Agentic Development of HPC Runtimes: MPI and OpenSHMEM

[Talk]

Accelerating HPC and AI Applications over Trinetra through GPU-Aware and Topology-Aware Communication

[Talk]

Slingshot-network accelerated collectives for PGAS

[Talk]

Application performance using MVAPICH-Plus on the SDSC Cosmos MI300A cluster

[Talk]

Governed Agents: An Evidence-Based Architecture for the Computing Continuum, In 4th Annual Trillion Parameter Workshop: Building Open AI Infrastructure, Models, and Agentic Systems for Science

[Talk]