arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.09568cs.PLcs.NAmath.NA
收藏

基于步进的检查点方法与高层算法微分

Step-based checkpointing with high-level algorithmic differentiation

James R. Maddison

AI总结:

本文提出将高层算法微分与基于步进的检查点调度相结合,应用于时间依赖偏微分方程求解器,通过动态构建的前向操作记录并利用前向与伴随数据差异优化检查点性能。

摘要:

自动代码生成允许将通过领域特定语言表达的模型开发与底层实现细节相分离。算法微分可以在领域特定语言层面符号化地应用,并复用代码生成器来实现伴随计算所需的代码。然而,伴随计算因存储或重新计算伴随所需的前向数据这一众所周知的问题而变得复杂,目前已开发出不同的检查点策略来解决此问题。本文考虑将高层算法微分与基于步进的检查点调度相结合,主要应用于求解时间依赖偏微分方程的求解器。重点在于使用动态构建的前向操作记录进行算法微分,其中原始前向计算的精确结构是预先未知的。此外,高层方法提供了模型本身的简化视图。这使得能够识别重启和推进前向所需的数据,以及推进伴随所需的数据。本文利用这两类数据之间的差异来实现性能更优的检查点策略。

英文摘要:

Automated code generation allows for a separation between the development of a model, expressed via a domain specific language, and lower level implementation details. Algorithmic differentiation can be applied symbolically at the level of the domain specific language, and the code generator reused to implement code required for an adjoint calculation. However the adjoint calculations are complicated by the well-known problem of storing or recomputing the forward data required by the adjoint, and different checkpointing strategies have been developed to tackle this problem. This article considers the combination of high-level algorithmic differentiation with step-based checkpointing schedules, with the primary application being for solvers of time-dependent partial differential equations. The focus is on algorithmic differentiation using a dynamically constructed record of forward operations, where the precise structure of the original forward calculation is unknown ahead-of-time. In addition, high-level approaches provide a simplified view of the model itself. This allows data required to restart and advance the forward, and data required to advance the adjoint, to be identified. The difference between the two types of data is here leveraged to implement checkpointing strategies with improved performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑