Achtung:

Sie haben Javascript deaktiviert!
Sie haben versucht eine Funktion zu nutzen, die nur mit Javascript möglich ist. Um sämtliche Funktionalitäten unserer Internetseite zu nutzen, aktivieren Sie bitte Javascript in Ihrem Browser.

Team Show image information

Ampehre Screenshot

Ampehre: Accurately Measuring Power and Energy for Heterogeneous Resource Environments

Ampehre is a modular software framework based on the famous PAPI project used to sample various types of sensors embedded in integrated circuits or circuit boards deployed to heterogeneous compute nodes. Ampehre enables accurate measurements of power, energy, temperature, and device utilization for computing resources such as CPUs (Central Processing Unit), GPUs (Graphics Processing Unit), FPGAs (Field Programmable Gate Array), and MICs (Many Integrated Cores) as well as several system-wide measurements via IPMI (Intelligent Platform Management Platform). Dedicated measuring equipment such as digital multimeters is not required for using Ampehre. Ampehre has been designed in a way that minimizes the influence of the measuring procedures to the overall CPU load. The modular design of the software facilitates the integration of new resources.

Ampehre is an open source project published under the 2-clause BSD license. The development of Ampehre is supported by the German Research Foundation (DFG) within the Collaborative Research Centre “On-The-Fly Computing” (SFB 901).

Ampehre Citation

Please cite the following reference when publishing results obtained with Ampehre:

Achim Lösch, Alex Wiens and Marco Platzner. Ampehre: An Open Source Measurement Framework for Heterogeneous Compute Nodes. In Architecture of Computing Systems - ARCS 2018 - 31st International Conference, Braunschweig, Germany, April 9-12, 2018, Proceedings, pages 73–84, 2018. doi:10.1007/978-3-319-77610-1_6

Publications

  • Achim Lösch and Marco Platzner. A Highly Accurate Energy Model for Task Execution on Heterogeneous Compute Nodes. In 29th IEEE International Conference on Application-specific Systems, Architectures and Processors, ASAP 2018, 2018. Accepted for publication.
  • Achim Lösch, Alex Wiens and Marco Platzner. Ampehre: An Open Source Measurement Framework for Heterogeneous Compute Nodes. In Architecture of Computing Systems - ARCS 2018 - 31st International Conference, Braunschweig, Germany, April 9-12, 2018, Proceedings, pages 73–84, 2018. doi:10.1007/978-3-319-77610-1_6
  • Achim Lösch and Marco Platzner. reMinMin: A Novel Static Energy-centric List Scheduling Approach Based on Real measurements. In 28th IEEE International Conference on Application-specific Systems, Architectures and Processors, ASAP 2017, pages 149–154, 2017. doi:10.1109/ASAP.2017.7995272
  • Achim Lösch, Tobias Beisel, Tobias Kenter, Christian Plessl and Marco Platzner. Performance-centric scheduling with task migration for a heterogeneous compute node in the data center. In Design, Automation Test in Europe Conference Exhibition (DATE), 2016.

The University for the Information Society