Computer Science and Mathematics Research Highlights

Research Highlights

Comparing default (red) and optimized (blue) methods for in transit visualization with Sensei. The optimized approach was made possible by innovations in distributed metadata handling. Image Credit: B. Loring CSMD ORNL Computer Science and Mathematics Divison

Improving In Transit and In Situ Analysis and Visualization

October 1, 2021

Progressive data retrieval workflow: Given a requested tolerance 𝜏0, the retriever fetches data to form a low-resolution/precision representation; later, as the requested tolerance changes to 𝜏0, the retriever fetches additional data and add it with the existing data to form a high-resolution/precision representation

Error-controlled Progressive Retrieval of Scientific Data

October 1, 2021

Variational Generative Flows for Reconstruction Uncertainty Estimation

July 18, 2021

A research team from ORNL and Pacific Northwest National Laboratory has developed a deep variational framework to learn an approximate posterior for uncertainty quantification.

Scalable In Situ Computation of Lagrangian Representations via Local Flow Maps

June 1, 2021

Catalyst Revised: Rethinking the ParaView In Situ Analysis and Visualization API

June 1, 2021

Data Analysis Approach for Large Data Volumes in a Connected Community

June 1, 2021

Accelerating Multigrid-based Hierarchical Scientific Data Refactoring on GPUs

June 1, 2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

June 1, 2021

MGARD+: Optimizing Multilevel Methods for Error-bounded Scientific Data Reduction

June 1, 2021

Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures

June 1, 2021

91��

Computer Science and Mathematics Division

Research Highlights

Filter Research Highlights

Area of Research

Date

Improving In Transit and In Situ Analysis and Visualization

Error-controlled Progressive Retrieval of Scientific Data

Variational Generative Flows for Reconstruction Uncertainty Estimation

Scalable In Situ Computation of Lagrangian Representations via Local Flow Maps

Catalyst Revised: Rethinking the ParaView In Situ Analysis and Visualization API

Data Analysis Approach for Large Data Volumes in a Connected Community

Accelerating Multigrid-based Hierarchical Scientific Data Refactoring on GPUs

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

MGARD+: Optimizing Multilevel Methods for Error-bounded Scientific Data Reduction

Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures