Accession Number:

AD1112724

Title:

SLATE Developers' Guide

Descriptive Note:

[Technical Report, Other]

Corporate Author:

TENNESSEE UNIV KNOXVILLE

Personal Author(s):

• Charara, Ali
• Gates, Mark
• Kurzak, Jakub
• YarKhan, Asim
• Dongarra, Jack

Report Date:

2019-12-31

Pagination or Media Count:

52

Abstract:

SLATE Software for Linear Algebra Targeting Exascale 1 is being developed as part of the Exascale Computing Project ECP 2, which is a joint project of the U.S. Department of Energys Office of Science and National Nuclear Security Administration NNSA. The objective of SLATE is to provide fundamental dense linear algebra capabilities to the U.S. Department of Energy and to the high-performance computing HPC community at large. SLATE provides coverage of existing LAPACK and ScaLAPACK functionality, including parallel implementations of Basic Linear Algebra Subroutines BLAS, matrix norms, linear systems solvers, least squares solvers, and singular value and eigenvalue solvers. In this respect, SLATE will serve as a replacement for ScaLAPACK, which, after two decades of operation, cannot bead equately retrofitted for modern, GPU-accelerated architectures.

Descriptors:

• high performance computing
• linear algebra
• linear systems
• computations
• standards
• bibliographies
• computers
• multiple access
• targets
• abstracts
• algebra
• algorithms
• computer programming
• conversion
• environment
• hierarchies
• parallel computing
• precision
• scheduling (production)
• specialization

Subject Categories:

• Theoretical Mathematics

Distribution Statement:

[A, Approved For Public Release]