PrETi: Predicting Execution Time in Early Stage with LLVM and Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Risheng, Sieweck, Philipp, von Hasseln, Hermann, Nowotka, Dirk
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913742323712000
author Xu, Risheng
Sieweck, Philipp
von Hasseln, Hermann
Nowotka, Dirk
author_facet Xu, Risheng
Sieweck, Philipp
von Hasseln, Hermann
Nowotka, Dirk
contents We introduce preti, a novel framework for predicting software execution time during the early stages of development. preti leverages an LLVM-based simulation environment to extract timing-related runtime information, such as the count of executed LLVM IR instructions. This information, combined with historical execution time data, is utilized to train machine learning models for accurate time prediction. To further enhance prediction accuracy, our approach incorporates simulations of cache accesses and branch prediction. The evaluations on public benchmarks demonstrate that preti achieves an average Absolute Percentage Error (APE) of 11.98\%, surpassing state-of-the-art methods. These results underscore the effectiveness and efficiency of preti as a robust solution for early-stage timing analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13679
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PrETi: Predicting Execution Time in Early Stage with LLVM and Machine Learning
Xu, Risheng
Sieweck, Philipp
von Hasseln, Hermann
Nowotka, Dirk
Performance
Machine Learning
We introduce preti, a novel framework for predicting software execution time during the early stages of development. preti leverages an LLVM-based simulation environment to extract timing-related runtime information, such as the count of executed LLVM IR instructions. This information, combined with historical execution time data, is utilized to train machine learning models for accurate time prediction. To further enhance prediction accuracy, our approach incorporates simulations of cache accesses and branch prediction. The evaluations on public benchmarks demonstrate that preti achieves an average Absolute Percentage Error (APE) of 11.98\%, surpassing state-of-the-art methods. These results underscore the effectiveness and efficiency of preti as a robust solution for early-stage timing analysis.
title PrETi: Predicting Execution Time in Early Stage with LLVM and Machine Learning
topic Performance
Machine Learning
url https://arxiv.org/abs/2503.13679