Simple port of GPU SCAMP, a scalable matrix profile calculation algorithm, using the task-based programming model HALadapt.
- Latest HALadapt version
- CUDA toolkit, our code is tested with CUDA 10.1
- gflags
- Latest protobuf
- cmake 3
- gcc-7+
The original SCAMP Algorithm and GPU SCAMP is developed by the UCR Matrix Profile team at University of California, Riverside. Adaptations for HALadapt is joint developed at
- Chair of Computer Architecure and Parallel Systems at Techincal University of Munich by Yannick Schaelow, Amir Raoofy, and Dai Yang, and
- Chair of Computer Architecture and Parallel Processing at Karlsruhe Institute of Technology by Thomas Becker.
This work is partially funded by German Federal Ministry of Education and Research under project "ENVELOPE", and it is also partially funded by the Bayerische Forschungsstiftung under project "Optimierung von Gasturbinen mit Hilfe von Big Data (TurbO)".