2014-06-01
Accelerating an iterative Helmholtz solver with FPGAs
Publication
Publication
Presented at the
EAGE Conference & Exhibition 2014, Amsterdam
We implement the Kaczmarz row-projection algorithm (Kaczmarz (1937)) on a CPU host + FPGA accelerator platform using techniques of dataflow programming. This algorithm is then used as the preconditioning step in CGMN, a modified version of the conjugate gradients method (Björck and Elfving (1979)) that we use to solve the time-harmonic acoustic isotropic constant density wave equation. Using one accelerator we achieve a speed-up of over 2× compared with one Intel core.
| Additional Metadata | |
|---|---|
| Unspecified | |
| European Association of Geoscientists and Engineers | |
| Mathematical Aspects of Discrete Tomography | |
| EAGE Conference & Exhibition 2014 | |
| Organisation | Scientific Computing |
|
Petrenko, A., van Leeuwen, T., Oratio, D., Tilbury, S., & Herrmann, F. (2014). Accelerating an iterative Helmholtz solver with FPGAs
. In Proceedings of 76th EAGE Conference & Exhibition 2014. European Association of Geoscientists and Engineers. |
|