TY - GEN
T1 - GPU acceleration of numerical weather prediction
AU - Michalakes, John
AU - Vachharajani, Manish
PY - 2008
Y1 - 2008
N2 - Weather and climate prediction software has enjoyed the benefits of exponentially increasing processor power for almost 50 years. Even with the advent of large-scale parallelism in weather models, much of the performance increase has come from increasing processor speed rather than increased parallelism. This free ride is nearly over. Recent results also indicate that simply increasing the use of large-scale parallelism will prove ineffective for many scenarios. We present an alternative method of scaling model performance by exploiting emerging architectures using the fine-grain parallelism once used in vector machines. The paper shows the promise of this approach by demonstrating a 20x speedup for a computationally intensive portion of the Weather Research and Forecast (WRF) model on an NVIDIA 8800 GTX Graphics Processing Unit (GPU). We expect an overall 1.3x speedup from this change alone.
AB - Weather and climate prediction software has enjoyed the benefits of exponentially increasing processor power for almost 50 years. Even with the advent of large-scale parallelism in weather models, much of the performance increase has come from increasing processor speed rather than increased parallelism. This free ride is nearly over. Recent results also indicate that simply increasing the use of large-scale parallelism will prove ineffective for many scenarios. We present an alternative method of scaling model performance by exploiting emerging architectures using the fine-grain parallelism once used in vector machines. The paper shows the promise of this approach by demonstrating a 20x speedup for a computationally intensive portion of the Weather Research and Forecast (WRF) model on an NVIDIA 8800 GTX Graphics Processing Unit (GPU). We expect an overall 1.3x speedup from this change alone.
UR - https://www.scopus.com/pages/publications/51049099597
U2 - 10.1109/IPDPS.2008.4536351
DO - 10.1109/IPDPS.2008.4536351
M3 - Conference contribution
AN - SCOPUS:51049099597
SN - 9781424416943
T3 - IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM
BT - IPDPS Miami 2008 - Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM
T2 - IPDPS 2008 - 22nd IEEE International Parallel and Distributed Processing Symposium
Y2 - 14 April 2008 through 18 April 2008
ER -