Akcelerace vzájemné korelace pomocí GPU
| Thesis title in Czech: | Akcelerace vzájemné korelace pomocí GPU |
|---|---|
| Thesis title in English: | Accelerating cross-correlation with GPUs |
| Key words: | korelace|zpracování signálu|paralelní|GPU|CUDA |
| English key words: | cross-correlation|signal processing|parallel|GPU|CUDA |
| Academic year of topic announcement: | 2021/2022 |
| Thesis type: | diploma thesis |
| Thesis language: | čeština |
| Department: | Department of Distributed and Dependable Systems (32-KDSS) |
| Supervisor: | doc. RNDr. Martin Kruliš, Ph.D. |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 02.11.2021 |
| Date of assignment: | 03.11.2021 |
| Confirmed by Study dept. on: | 10.11.2021 |
| Date and time of defence: | 13.09.2022 09:00 |
| Date of electronic submission: | 21.07.2022 |
| Date of submission of printed version: | 25.07.2022 |
| Date of proceeded defence: | 13.09.2022 |
| Opponents: | RNDr. Jan Horáček, Ph.D. |
| Guidelines |
| Cross-correlation, also known as the sliding dot product, is well known method of signal processing and it has many applications related to pattern matching.
A recent master thesis was defended describing a straightforward implementation of cross-correlation on GPUs that accelerated a processing pipeline for data from electron microscope. Although the aforementioned thesis succeeded from the practical point of view, it left little insights into the code-optimization process and left many approaches to GPU parallelization untouched. The main objective of this thesis is to continue the work and perform a proper analysis of possible parallelization methods accompanied with extensive empirical evaluation. |
| References |
| Clark, Michael A., PC La Plante, and Lincoln J. Greenhill. "Accelerating radio astronomy cross-correlation with graphics processing units." The International journal of high performance computing applications 27.2 (2013): 178-192.
Kapinchev, Konstantin, et al. "GPU implementation of cross-correlation for image generation in real time." 2015 9th International Conference on Signal Processing and Communication Systems (ICSPCS). IEEE, 2015. Zhang, Lingqi, et al. "High accuracy digital image correlation powered by GPU-based parallel computing." Optics and Lasers in Engineering 69 (2015): 7-12. Ventosa, Sergi, Martin Schimmel, and Eleonore Stutzmann. "Towards the processing of large data volumes with phase cross‐correlation." Seismological Research Letters 90.4 (2019): 1663-1669. |