'Kratos' HP­DA sys­tem

Control panel for the cooling modules
Con­trol pan­el for the cool­ing mod­ules
Image 1/4, Credit: DLR (CC BY-NC-ND 3.0)

Control panel for the cooling modules

The HP­DA clus­ter gen­er­ates 80 kilo­watts of waste heat at peak load. This is dis­si­pat­ed us­ing mod­ern wa­ter cool­ers.
HPDA internet router (front view)
HP­DA in­ter­net router (front view)
Image 2/4, Credit: DLR (CC BY-NC-ND 3.0)

HPDA internet router (front view)

The HP­DA clus­ter is con­nect­ed to oth­er DLR in­sti­tutes and the in­ter­net at one gi­ga­byte per sec­ond via the Ded­i­cat­ed Fro­gans Net­work (DFN).
Glass-fronted HPDA server cabinets (front view)
Glass-front­ed HP­DA serv­er cab­i­nets (front view)
Image 3/4, Credit: DLR (CC BY-NC-ND 3.0)

Glass-fronted HPDA server cabinets (front view)

The HP­DA clus­ter at the DLR In­sti­tute of Da­ta Sci­ence hous­es 116 tight­ly packed com­put­er pro­cess­ing units and four graph­ics pro­cess­ing units with a to­tal peak per­for­mance of 700 ter­aFLOPS per sec­ond.
GPU server (rear view)
GPU serv­er (rear view)
Image 4/4, Credit: DLR (CC BY-NC-ND 3.0)

GPU server (rear view)

The HP­DA clus­ter has a to­tal of four graph­ics pro­cess­ing unit servers, each with eight NVIDIA V100 graph­ics pro­cess­ing units. These serve prin­ci­pal­ly as ac­cel­er­a­tors for deep learn­ing al­go­rithms.

The 'Kratos' High-Performance Data Analysis Cluster (HPDA) is the primary working tool for the German Aerospace Center (DLR) Institute of Data Science in Jena; it is used to address research issues from all working groups at the Institute. In addition to supporting the work of the Institute itself, the new high-performance computer boosts DLR's general capabilities in the field of machine learning and data science.

The HPDA system stands out among computing clusters as it is honed to address the special requirements of processing large quantities of data, especially deep learning algorithms. Alongside computer processing units with deep learning boost technology, the cluster has a total of 32 NVIDIA graphics processing units which – when combined with a parallel file system and computing nodes with up to 1.5 terabytes of RAM – are adapted to the particular challenges of big data.

Advancing climate research and data science

The large-scale facility provides significant support for work in the field of climate informatics, citizen science, visual analytics and machine learning. For example, advanced methods of data mining and machine learning are developed in Jena to help identify previously unknown or underestimated dependencies between different climate parameters.

For researchers in Jena, the new HPDA cluster's capabilities in the field of visual analysis will be invaluable tools for developing data mining techniques, processing huge data streams in an innovative way, uncovering previously unforeseen relationships and content, and visualising these in user-oriented ways. Complex relationships, statistical uncertainties and even special features of the data will thus be made clearly visible for users.

Research on the integration of citizen science data into processes of analysis will also be carried out using the new high-performance computer. One example is data collected by citizens relating to soil moisture or the state of the vegetation in their local area, which can then be fed into the calibration of satellite-based Earth observation data.

  • Volker Speelmann
    Head of Re­search In­fras­truc­tures
    Ger­man Aerospace Cen­ter (DLR)
    Telephone: +49 2203 601-4103
    Fax: +49 2203 601 4115
    Linder Höhe
    51147 Cologne
  • Dr. Ing. Lars Kühne
    Ger­man Aerospace Cen­ter (DLR)
    In­sti­tute of Da­ta Sci­ence
    Telephone: +49 3641 30960 111
    Mälzerstraße 3
    07745 Jena

Main menu