HPC News Bytes 20240219: AI Safety and Governance, Running CUDA Apps on ROCm, DOE’s SLATE, New Advanced Chips

Happy President’s Day morning to everyone! Today’s HPC News Bytes races (6:22) around the HPC-AI landscape with comments on: developments in AI security and governance, running CUDA (NVIDIA) apps on ROCm (AMD), DOE’s Exascale Software Linear….

Exascale’s New Software Frontier: SLATE

“Exascale’s New Frontier,” a project from the Oak Ridge Leadership Computing Facility, explores the new applications and software technology for driving scientific discoveries in the exascale era.  Why Exascale Needs SLATE For nearly 30 years, scores of science and engineering projects conducted on high-performance computing systems have used either the Linear Algebra PACKage (LAPACK) library […]

Video: ECP Project for Linear Algebra Targeting Exascale

In this video, Jakub Kurzak, Research Assistant Professor at the University of Tennessee’s Innovative Computing Laboratory, discusses the Software for Linear Algebra Targeting Exascale (SLATE) project. “The objective of SLATE is to provide basic dense matrix operations such as matrix multiplication, rank-k update, triangular solve, as well as linear systems solvers, least square solvers, singular value and eigenvalue solvers, in support of the ECP efforts to build a capable exascale computing ecosystem.”