This website uses cookies to manage authentication, navigation, and other functions. By using our website, you agree that we can place these types of cookies on your device.

View e-Privacy Directive Documents

The system software developments with respect to the DEEP-ER I/O stack are a prime example of how the project’s co-design approach connects everything with everything. The I/O team for instance collaborated closely for instance with:

  • Collaboration with the architecture design team:
    • Evaluation of the NVMe devices

 

  • Integration of continuous benchmarking into the monitoring Collaboration with the resiliency team:
    • Request to add CRC checksum calculation during flush/prefetch to the BeeGFS cache API
    • Addition of functions to check status of asynchronous operations

 

  • Design and development of SCR extensions and buddy checkpointing in SIONlib
    • Collaboration with the application developers
    • Support for implementation of I/O layers in different applications
    • Documentation of the different I/O layers for the application developers

 

  • Collaboration the I/O, the resiliency and the application developers  
    • Modification of the JUBE-integrated application GERShWIN to support SCR