Navigation and service


As a result of the generic method activities, the HAF project produces software components that are developed as open source software and made available for download.


HeAT is a flexible and seamless open-source software for high performance data analytics and machine learning. It provides highly optimized algorithms and data structures for tensor computations using CPUs, GPUs and distributed cluster systems on top of MPI. The goal of HeAT is to fill the gap between data analytics and machine learning libraries with a strong focus on on single-node performance on the one hand, and traditional high-performance computing (HPC) on the other. Further information and links are available in our section about generic methods.


Hyppopy is a Python-based toolbox for blackbox optimization. It attempts to find the best possible solution to a pre-defined objective functions. This can be for example the parameters of simulation or the hyperparameters of a machine learning models. Hyppopy offers a unified and easy-to-use interface to a collection of blackbox optimization solver backends and algorithms. Further information and links are available in our section about generic methods.


DLR's Surrogate Modeling for AeRo Data Toolbox (SMARTy) is a modular, object-oriented Python package (API) for rapidly predicting aerodynamic data based on high-fidelity CFD. In the HAF project, DLR is further developing SMARTy to evaluate promising SBDA methods, e.g. Bayesian methods and clustering algorithms, on the Virtual Aircraft use case and to transfer them to industry. It is also planned to interface SMARTy with both the HeAT framework and with Hyppopy.


diSTruct is in essence an implementation of the MaxEnt-Stress graph drawing algorithm (Gansner, E.; Hu, Y. and North, S. C.: "A Maxent-Stress Model for Graph Layout" in IEE Trans. Vis. Comput. Graph. 2013) for generating biomolecular structures from distance constraints. The sources are available on GitHub.