| |
 |
| Paper: |
HeAT: a High-Performance-Computing Library for Scientific Big Data Analytics |
| Volume: |
527, Astronomical Data Analysis Software and Systems XXIX |
| Page: |
191 |
| Authors: |
Comito, C.; Coquelin, D.; Debus, C.; Götz, M.; Hagemeier, B.; Hanselmann, S.; Knechtges, P.; Krajsek, K.; Schmitz, S.; Tarnawa, M. |
| Abstract: |
HeAT is a flexible and seamless open-source software for high performance data analytics and machine learning/deep learning (ML/DL). 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 ML/DL libraries with a strong focus on on single-node performance, and traditional High-Performance Computing (HPC).
We demonstrate some of HeAT's basic functionalities by finding star clusters in the Gaia database through unsupervised machine learning. |
|
|
|
|
|
