Scrutinizing Variables for Checkpoint Using Automatic Differentiation

TL;DR

This paper introduces a systematic method using automatic differentiation to identify critical data within variables for checkpointing, significantly reducing storage needs in HPC applications.

Contribution

It presents a novel approach leveraging AD to scrutinize each variable element for checkpointing, enabling selective data saving and improving efficiency.

Findings

Up to 20% storage savings in checkpointing.

Effective visualization of critical/uncritical regions.

Patterns align with algorithm logic.

Abstract

Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in the computation in typical HPC applications; such unused data should be excluded from checkpointing for better storage/compute efficiency. To find out, we propose a systematic approach that leverages automatic differentiation (AD) to scrutinize every element within variables (e.g., arrays) for checkpointing allowing us to identify critical/uncritical elements and eliminate uncritical elements from checkpointing. Specifically, we inspect every single element within a variable for checkpointing with an AD tool to determine whether the element has an impact on the application output or not. We empirically validate our approach with eight benchmarks from the NAS Parallel Benchmark (NPB) suite. We successfully visualize critical/uncritical elements/regions within a variable with respect to its impact (yes or no) on the application output. We find patterns/distributions of critical/uncritical elements/regions quite interesting and follow the physical formulation/logic of the algorithm.The evaluation on NPB benchmarks shows that our approach saves storage for checkpointing by up to 20%.