High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark

RESOURCE

Abstract

SAND2024-08539O The High Performance GMRES Mixed-Precision (HPG-MxP) is a benchmark for ranking high-performance supercomputers, allowing use of mixed-precision. Similar to HPCG benchmark, it is designed to profile the computers' capabilities to perform the computational and communication tasks that are commonly found in important classes of real-world applications. At the same time, like HPL-MxP benchmark, it allows the use of mixed-precision arithmetic, while ensuring the double-precision accuracy of the computed solution. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Developers:
Rajamanickam, Sivasankaran [1][2][3] Loe, Jennifer [1][2][3] Glusa, Christian [1][2][3] Yamazaki, Ichitaro [1][2][3] Luszczek, Piotr [4] Dongarra, Jack [4]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  3. Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
  4. University of Tennessee
Release Date:
2023-05-25
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
C++
Version:
0.1
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
145977
Site Accession Number:
SCR #2923.0
Research Org.:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Country of Origin:
United States
Keywords:
SciDAC

RESOURCE

Citation Formats

Rajamanickam, Sivasankaran, Loe, Jennifer, Glusa, Christian, Yamazaki, Ichitaro, Luszczek, Piotr, and Dongarra, Jack. High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark. Computer Software. https://github.com/iyamazaki/hpcg. USDOE. 25 May. 2023. Web. doi:10.11578/dc.20241023.6.
Rajamanickam, Sivasankaran, Loe, Jennifer, Glusa, Christian, Yamazaki, Ichitaro, Luszczek, Piotr, & Dongarra, Jack. (2023, May 25). High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark. [Computer software]. https://github.com/iyamazaki/hpcg. https://doi.org/10.11578/dc.20241023.6.
Rajamanickam, Sivasankaran, Loe, Jennifer, Glusa, Christian, Yamazaki, Ichitaro, Luszczek, Piotr, and Dongarra, Jack. "High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark." Computer software. May 25, 2023. https://github.com/iyamazaki/hpcg. https://doi.org/10.11578/dc.20241023.6.
@misc{ doecode_145977,
title = {High-Performance GMRES Mixed-Precision (HPG-MxP) Benchmark},
author = {Rajamanickam, Sivasankaran and Loe, Jennifer and Glusa, Christian and Yamazaki, Ichitaro and Luszczek, Piotr and Dongarra, Jack},
abstractNote = {SAND2024-08539O The High Performance GMRES Mixed-Precision (HPG-MxP) is a benchmark for ranking high-performance supercomputers, allowing use of mixed-precision. Similar to HPCG benchmark, it is designed to profile the computers' capabilities to perform the computational and communication tasks that are commonly found in important classes of real-world applications. At the same time, like HPL-MxP benchmark, it allows the use of mixed-precision arithmetic, while ensuring the double-precision accuracy of the computed solution. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.},
doi = {10.11578/dc.20241023.6},
url = {https://doi.org/10.11578/dc.20241023.6},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20241023.6}},
year = {2023},
month = {may}
}