![diagram of multiple arrays of data points moving between CPU and GPU architectures](/sites/default/files/styles/front_page_card/public/chai-llnl-project-card.png?itok=rjh9eRpY)
CHAI
A new software model helps move million-line codes to various hardware architectures by automating data movement in unique ways.
![Sphinx logo](/sites/default/files/styles/front_page_card/public/sphinx-llnl-project-card.png?itok=JHLbt4Gi)
Sphinx
Sphinx, an integrated parallel microbenchmark suite, consists of a harness for running performance tests and extensive tests of MPI, Pthreads and OpenMP.
![graph of different colored candlesticks](/sites/default/files/styles/front_page_card/public/apollo-llnl-project-card.png?itok=NBaRlyy5)
Apollo
Apollo, an auto-tuning extension of RAJA, improves performance portability in adaptive mesh refinement, multi-physics, and hydrodynamics codes via machine learning classifiers.
Video: Utilizing HPC to model, simulate, & mitigate wildfire risk
LLNL's Ian Lee joins a Dots and Bridges panel to discuss HPC as a critical resource for data assimilation and numerical weather prediction research.
![closeup of a metal structure](/sites/default/files/styles/front_page_card/public/2023-08/rd100-2023-winner-news.png?itok=df-NMpZE)
R&D 100 winners for 2023 are announced
LLNL's zfp and Variorum software projects are winners. LLNL is a co-developing organization on the winning CANDLE project.
![three people install an early access system rack in the machine room](/sites/default/files/styles/front_page_card/public/2023-06/road-el-cap-2-leaderboard-eas.png?itok=hX2iopJ4)
Road to El Capitan 2: All the moving parts
Siting a supercomputer requires close coordination of hardware, software, applications, and Livermore Computing facilities.