Topic: Computational Math

Highlights include innovative solutions for contact mechanics, HPC optimization, quantum dynamics, and carbon capture.

Widely viewed as the highest recognition in HPC, the Gordon Bell Prize recognizes innovations that push the limits of computational performance, scalability and scientific impact on pressing real-world problems.

The open-source MFEM library enables application scientists to quickly prototype parallel physics application codes based on PDEs discretized with high-order finite elements.

Five years strong, the MFEM workshop fosters connection and collaboration among the computational math community.

Morphing an interest in simulation into a career in sophisticated software development, Yohann Dudouit helps the Laboratory visualize complex scientific phenomena in the national interest.

LLNL is participating in the 37th annual Supercomputing Conference (SC25) in St. Louis on November 16–21, 2025.

This project solves initial value problems for ODE systems, sensitivity analysis capabilities, additive Runge-Kutta methods, DAE systems, and nonlinear algebraic systems.

Scientists at LLNL have helped develop an advanced, real-time tsunami forecasting system—powered by El Capitan, the world’s fastest supercomputer—that could dramatically improve early warning capabilities for coastal communities near earthquake zones.

A new CASC paper proposes unity and clarity around foundation models in computational science, offering an implementation framework inspired by finite element methods.

Researchers at Brown University, LLNL, and Simula Research Laboratory have developed a new algorithm to help optimizers arrive at solutions in fewer iterations, saving valuable computing time.

LLNL researchers have posters and workshop papers accepted to the 42nd International Conference on Machine Learning on July 13–19.

A new mathematical technique improves the computational efficiency of evaluating the solution in large-scale, high-order meshes on advanced HPC systems.

GLVis is a lightweight tool for accurate and flexible finite element visualization that provides interactive visualizations of general FE meshes and solutions.

In a recent study published in the Astrophysical Journal, LLNL researchers developed an innovative approach to map cosmic shear using linear algebra, statistics, and HPC.

LLNL's Bruce Hendrickson joins other HPC luminaries in this op-ed about the future of the field.

The DarkStar inverse design technique blends AI, machine learning, and advanced hydrodynamics simulations to optimize science and engineering solutions starting from the final state.

Held for the first time in a hybrid format, the multi-day MFEM workshop drew participants from around the globe.

LLNL is participating in the 36th annual Supercomputing Conference (SC24) in Atlanta on November 17–22, 2024.

As Computing’s eighth Fernbach Fellow, postdoctoral researcher Robert Stephany will develop specialized algorithms under the mentorship of Youngsoo Choi.

Follow along at your own pace through tutorials of several open-source HPC software projects.

Developed by LLNL, Colorado, and Purdue researchers, a new approach eases the implementation of curved geometries into computing simulations.

Developed by LLNL and Portland State University researchers, innovative matrix-free solvers offer performance gains for complex multiphysics simulations.

A new method defines a formal specification for convergence, which can be used to derive a set of machine-checkable conditions to guarantee a convergent solution to a differential equation.

LLNL researchers have achieved a milestone in accelerating and adding features to complex multiphysics simulations run on GPUs, a development that could advance HPC and engineering.

The Society for Industrial and Applied Mathematics (SIAM) announced the selection of Lawrence Livermore National Laboratory (LLNL) computational mathematician Ulrike Meier Yang as one of the 2024 Class of SIAM Fellows, the highest honor the organization bestows on its members.