NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling
Ongoing climate change calls for fast and accurate weather and climate modeling. However, when solving large-scale weather prediction simulations, state-of-the-art CPU and GPU implementations suer from limited performance and high energy consumption. These implementations are dominated by complex irregular memory access patterns and low arithmetic intensity that pose fundamental challenges to acceleration. To overcome these challenges, we propose and evaluate the use of near-memory acceleration using a reconfigurable fabric with high-bandwidth memory (HBM). We focus on compound stencils that are fundamental kernels in weather prediction models. By using high-level synthesis techniques, we develop NERO, an FPGA+HBM-based accelerator connected through IBM CAPI2 (Coherent Accelerator Processor Interface) to an IBM POWER9 host system. Our experimental results show that NERO outperforms a 16-core POWER9 system by 4.2× and 8.3× when running two dierent compound stencil kernels. NERO reduces the energy consumption by 22× and 29× for the same two kernels over the POWER9 system with an energy efficiency of 1.5 GFLOPS/Watt and 17.3 GFLOPS/Watt. We conclude that employing near-memory acceleration solutions for weather prediction modeling is promising as a means to achieve both high performance and high energy efficiency.
- NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling
G. Singh, D. Diamantopoulos, C. Hagleitner.J Gómez-Luna, S. Stuijk, O. Mutlu and Henk Corporaal.
In International Conference on Field-Programmable Logic and Applications, FPL 20, Proceedings, pages xyz-xyz. Virtual, 31 augutus - 4 september, 2020. IEEE, 2020. (abstract, pdf, doi).