Repositories (31)
RAJA Performance Portability Layer (C++)
Caliper is an instrumentation and performance profiling library
A streamlined CMake build system foundation for developing HPC software
Future home of hpc-tutorials.llnl.gov
An application-focused API for memory management on NUMA & GPU architectures
Simplified Data Exchange for HPC Simulations
Livermore Big Artificial Neural Network Toolkit
HPC solver for nonlinear optimization problems
Magpie contains a number of scripts for running Big Data software in HPC environments, including Hadoop and Spark. There is support for Lustre, Slurm, Moab, Torque. LSF, Flux, and more.
CS infrastructure components for HPC applications
Structured Adaptive Mesh Refinement Application Infrastructure - a scalable C++ framework for block-structured AMR application development
RAJA Performance Suite
Allows safer access to model specific registers (MSRs)
Fusion models for Atomic and molecular STructures (FAST)
Vendor-neutral library for exposing power and performance features across diverse architectures
Data race benchmark suite for evaluating OpenMP correctness tools aimed to detect data races.
An open collaborative repository for reproducible specifications of HPC benchmarks and cross site benchmarking environments
Public home for LLNL software catalog
STAT - the Stack Trace Analysis Tool
Pragmatic, Productive, and Portable Affinity for HPC
Wrapper library for model-specific registers. APIs cover RAPL, performance counters, clocks and turbo.
A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.
MPI benchmark to test and measure collective performance
MPI wrapper generator, for writing PMPI tool libraries
Apollo: Online Machine Learning for Performance Portability
Visualization tool for analyzing call trees and graphs
Comb is a communication performance benchmarking tool.
C++ library for graph ordering
AutoParBench is a benchmark framework to evaluate compilers and tools designed to automatically insert OpenMP directives.
FAROS: A Framework for Benchmarking and Analysis of Compiler Optimization