GPTune v.1

Software · Wed Aug 07 00:00:00 EDT 2019

DOI:https://doi.org/10.11578/dc.20191003.2· OSTI ID:1569031 · Code ID:28677

Demmel, James W. ^[1]; Li, Sherry Xiaoye ^[1]; Lakhdar, Mohamed Wissam Sid ^[1]

---

1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

GPTune is an autotuning framework for exascale applications. Given an application with a set of parameters controlling its performance (e.g. runtime, memory and/or energy consumption, numerical accuracy, ...), GPTune aims at finding a combination of the parameters that yields the best possible performance. Although general enough, GPTune specializes in the tunning of expensive-to-run applications, where the cost of running the application is very expensive (in terms of computing power requirement and/or runtime).

• Project Type: Open Source, Publicly Available Repository
• Site Accession Number: 2019-138
• Software Type: Scientific
• License(s): BSD 3-clause "New" or "Revised" License
• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE

  ---

  Primary Award/Contract Number:

  AC02-05CH11231
• DOE Contract Number: AC02-05CH11231
• Code ID: 28677
• OSTI ID: 1569031
• Country of Origin: United States