Loading...
Publication
A GPU implementation of the analog ensemble method
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 906.7 KB | Adobe PDF |
Advisor(s)
Abstract(s)
The Analog Ensemble (AnEn) method can be used to reconstruct incomplete time series using correlated series.
Since the AnEn method may use data including several variables through long periods of time, its storage and computational cost may be substantial, slowing down reconstructions. This paper presents a full GPU implementation of the AnEn method, based on PyCUDA, that leads to a significant a cceleration of its execution. The implementation resorts to several techniques that seek to minimize the consumption of GPU global memory in the various steps of the AnEn algorithm, thus making room for larger input datasets. This is further reinforced by the use of batch processing as a way to automatically adapt the datasets size to the GPU memory available. The GPU implementation was tested on a meteorological dataset spanning 10 years, exhibiting a 30-fold speedup in the reconstruction time against a comparable CPU-based multicore version executed with up to 48 cores. The impact
on the reconstruction error of changes on several important parameters of the implementation was also assessed.
Description
Keywords
Hindcasting Analog Ensemble Scientific Computing Parallel Computing: GPU Computing
Citation
Crico, Ruben; Charles, Ines; Balsa, Carlos; Rufino, José (2025). A GPU implementation of the analog ensemble method. In the 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing. p. 1-8
Publisher
Institute of Electrical and Electronics Engineers