A 21×21 Dynamic-Precision Bit-Serial Computing Graph Accelerator for Solving Partial Differential Equations Using Finite Difference Method

📋 论文概要

该论文提出了一种21×21动态精度位串行计算图加速器，用于使用有限差分法求解偏微分方程。通过动态精度和位串行计算，解决了传统求解器高精度迭代计算效率低的问题。

💡 主要创新点

• 采用动态精度的位串行计算图架构，根据计算需求动态调整精度，提高能效。
• 构建21×21的加速器阵列，专门针对有限差分法的迭代计算进行优化。

🏷 关键词

📄 原文摘要

now with University of California, Santa Barbara, CA 1 2 Partial differential equations (PDEs) are ubiquitous in physics and engineering and used for understanding various physical phenomena, including heat, diffusion, fluid and electrodynamics, and quantum mechanics. Analytical PDE solutions are rare, and hence, we approximate using numerical methods. The finite difference method (FDM) approximates PDEs by computing finite differences between discretized solutions. Since finite differences approximate the derivatives of PDEs, many iterations of high-precision computations are required to achieve higher accuracy in their numerical solutions. Hence, computationally-expensive FDM necessitates the use of high-performance computers. As such, their energy consumption is excessive (e.g. 15mJ per iteration and >320J in total for solving PDE with a 128×128 grid using GPU [1]). Consequently, there

👥 作者与机构

Junjie Mu1, Bongjin Kim1,2

Nanyang Technological University, Singapore, Singapore