NERO: A Near High-Bandwidth Memory Stencil Accelerator for Weather Prediction Modeling

TL;DR

NERO is an FPGA+HBM-based near-memory accelerator that significantly improves performance and energy efficiency for weather prediction kernels compared to traditional CPU systems.

Contribution

This paper introduces NERO, a novel FPGA-based accelerator with high-bandwidth memory designed specifically for weather prediction stencil computations.

Findings

NERO outperforms POWER9 by 4.2x and 8.3x in speed.

NERO reduces energy consumption by over 20x.

Achieves high energy efficiency of up to 17.3 GFLOPS/Watt.

Abstract

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 suffer 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 4.2x and 8.3x when running two different compound stencil kernels. NERO reduces the energy consumption by 22x and 29x 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.