Project Profile

HPL

High Performance LINPACK

Overview

The High Performance LINPACK (HPL) benchmark solves a dense linear system in double precision (64-bit arithmetic) on distributed-memory computers. HPL is written in a portable ANSI C and requires an MPI implementation and either BLAS or Vector Signal and Image Processing Library (VSIPL). HPL is often the first program to run on large HPC machines. Carefully optimized versions of HPL are available from major HPC hardware vendors.

When HPL was updated in 2018 to version 2.3, the reporting of the benchmark results was improved both in terms of accuracy and ease of installation: configuring and building the code on the newer HPC platforms was streamlined. Since then, the development of HPL has moved to GitHub. The benchmark now features more detailed reporting of the scaled residual of the linear system’s solution as well as the achieved performance number. Additionally, the code base does not use deprecated MPI functions any more. Finally, HPL now allows the users to configure and build the code using the GNU Autotools portability system.

Associated Print Material
Find out more at https://icl.utk.edu/hpl/

In Collaboration With

  1. Oak Ridge National Laboratory

Sponsored by

  1. The United States Department of Energy