Training Large Language Models for System-Level Test Program Generation Targeting Non-functional Properties

Denis Schwachhofer, Peter Domanski, Steffen Becker, Stefan Wagner, Matthias Sauer, Dirk Pfluger, Ilia Polian

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

System-Level Test (SLT) has been an integral part of integrated circuit test flows for over a decade and continues to be significant. Nevertheless, there is a lack of systematic approaches for generating test programs, specifically focusing on the non-functional aspects of the Device under Test (DUT). Currently, test engineers manually create test suites using commercially available software to simulate the end-user environment of the DUT. This process is challenging and laborious and does not assure adequate control over non-functional properties. This paper proposes to use Large Language Models (LLMs) for SLT program generation. We use a pre-trained LLM and fine-tune it to generate test programs that optimize non-functional properties of the DUT, e.g., instructions per cycle. Therefore, we use Gem5, a microarchitectural simulator, in conjunction with Reinforcement Learning-based training. Finally, we write a prompt to generate C code snippets that maximize the instructions per cycle of the given architecture. In addition, we apply hyperparameter optimization to achieve the best possible results in inference.

Original languageEnglish
Title of host publicationProceedings - 2024 29th IEEE European Test Symposium, ETS 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350349320
DOIs
StatePublished - 2024
Event29th IEEE European Test Symposium, ETS 2024 - The Hague, Netherlands
Duration: 20 May 202424 May 2024

Publication series

NameProceedings of the European Test Workshop
ISSN (Print)1530-1877
ISSN (Electronic)1558-1780

Conference

Conference29th IEEE European Test Symposium, ETS 2024
Country/TerritoryNetherlands
CityThe Hague
Period20/05/2424/05/24

Keywords

  • Functional Test
  • Large Language Models
  • Optimization
  • System-Level Test
  • Test Generation

Fingerprint

Dive into the research topics of 'Training Large Language Models for System-Level Test Program Generation Targeting Non-functional Properties'. Together they form a unique fingerprint.

Cite this