Analyzing the Performance and Accuracy of Lossy Checkpointing on Sub-Iteration of NWChem

Future exascale systems are expected to be characterized by more frequent failures than current petascale systems. This places increased importance on the application to minimize the amount of time wasted due to recompution when recovering from a checkpoint. Typically HPC application checkpoint at i...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE/ACM 5th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-5) pp. 23 - 27
Main Authors Reza, Tasmia, Calhoun, Jon, Keipert, Kristopher, Di, Sheng, Cappello, Franck
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2019
Subjects
Bandwidth
checkpoint-restart
Checkpointing
Chemistry
Compressors
Computational modeling
coupled-cluster singles and doubles
Data compression
lossy data compression
NWChem
Tensors
Online AccessGet full text

Cover

More Information
Summary:Future exascale systems are expected to be characterized by more frequent failures than current petascale systems. This places increased importance on the application to minimize the amount of time wasted due to recompution when recovering from a checkpoint. Typically HPC application checkpoint at iteration boundaries. However, for applications that have a high per-iteration cost, checkpointing inside the iteration limits the amount of re-computation. This paper analyzes the performance and accuracy of using lossy compressed check-pointing in the computational chemistry application NWChem. Our results indicate that lossy compression is an effective tool for reducing the sub-iteration checkpoint size. Moreover, compression error tolerances that yield acceptable deviation in accuracy and iteration count are quantified.
DOI:10.1109/DRBSD-549595.2019.00009