RAPIDS Highlights

The RAPIDS SciDAC Institute for Computer Science and Data has objective of assisting Office of Science (SC) application teams in overcoming computer science and data challenges in the use of DOE supercomputing resources to achieve science breakthroughs.

The following slides contain brief overviews of recent the scientific achievement:

• Enabling Global Adjoint Tomography at scale through next-generation I/O
• Graphical Model Structure Learning at Unprecedented Scale
• Global Particle-in-Cell Simulation of Fusion Plasmas
• Multivariate, Temporal Visual Analytics for Climate Model Analysis
• Accelerating Earthquake Detection
• Accelerating Weather Research Forecasting Simulations with Deep Neural Network Surrogates
• Accelerating Computational Kernels of Tokamak Simulations (with FASTMath)
• Performance Optimization for Multiscale Gyrokinetic Turbulence
• Accelerating HEP Event Generation and Analysis on HPC Systems
• Accelerating Fusion Fission Simulations
• Image Enhancements in Compressed Sensing using Deep Neural Networks
• In situ Viz Unlocks Unsteady Dynamics at Extreme Scale
• Roofline-Based Modeling in Intel Advisor
• Improving Network Throughput with Global Communication Reordering
• Improving Collective Reduction Performance On Manycore Architectures
• Deep Stack Program Optimization
• Autonomic Data Movement for Data Staging-based In-Situ Workflows
• Robust IO Performance Modeling in Leadership-Class Systems by Automated Change Detection