Our research projects vary in size, scope, and duration, but they share a focus on developing tools and methods that help LLNL deliver on its missions to the nation and, more broadly, advance the state of the art in scientific HPC. Projects are organized here in three ways: Active projects are those currently funded and regularly updated. Legacy projects are no longer actively developed. The A-Z option sorts all projects alphabetically, both active and legacy.
This tool that automatically diagnoses performance and correctness faults in MPI applications. It identifies abnormal MPI tasks and code regions and finds the least-progressed task.
The Extreme Resilient Discretization project (ExReDi) was established to address these challenges for algorithms common for fluid and plasma simulations.
This scalable first-principles MD algorithm with O(N) complexity and controllable accuracy is capable of simulating systems that were previously impossible with such accuracy.
This first-principles simulation method models the interaction of laser light with diffraction gratings, giving scientists a powerful tool to predict the performance of a laser compressor.
Responding to a DOE grid optimization challenge, an LLNL-led team developed the mathematical, computational, and software components needed to solve problems of the real-world power grid.
These techniques emulate the behavior of anticipated future architectures on current machines to improve performance modeling and evaluation.
Livermore researchers are enhancing HARVEY, an open-source parallel fluid dynamics application designed to model blood flow in patient-specific geometries.
hzip 1.0.1 is a C++ library for lossless compression of structured and unstructured meshes composed of cells with hypercube topology.
LLNL's interconnection networks projects improve the communication and overall performance of parallel applications using interconnect topology-aware task mapping.
libMSR provides a convenient interface to access Model Specific Registers and to allow tools to utilize their full functionality.
This project's techniques reduce bandwidth requirements for large unstructured data by making use of data compression and optimizing the layout of the data for better locality and cache reuse.
MPI_T is an interface for tools introduced in the 3.0 version of MPI. The interface provides mechanisms for tools to access and set performance and control variables that are exposed by an MPI…
The NSDE project is focused on research and development of nonlinear solvers and sensitivity analysis techniques for nonlinear, time-dependent, and steady-state partial differential equations.
These Fortran solvers tackle the initial value problem for ODE systems. The collection includes solvers for systems given in both explicit and linearly implicit forms.
Based on a discretization and time-stepping algorithm, these equations include a local order parameter, a quaternion representation of local orientation, and species composition.
PnMPI is a thin, low-overhead wrapper library that is automatically generated from mpi.h file and that can be linked by default.
LLNL’s version of Qbox, a first-principles molecular dynamics code, will let researchers accurately calculate bigger systems on supercomputers.
A new algorithm for use with first-principles molecular dynamics codes enables the number of atoms simulated to be proportional to the number of processors available.
Drawing from data mining, image and video processing, statistics, and pattern recognition, these computational tools improve the way scientists extract useful information from data.
SOAR (Stateless, One-pass Adaptive Refinement) is a view-dependent mesh refinement and rendering algorithm.
Sphinx, an integrated parallel microbenchmark suite, consists of a harness for running performance tests and extensive tests of MPI, Pthreads and OpenMP.
Veritas provides a method for validating proxy applications to ensure that they capture the intended characteristics of their parents.