Large Language Models to Generate System-Level Test Programs Targeting Non-functional Properties
This addresses the tedious and manual task for test engineers in approximating end-user environments, though it appears incremental as it applies existing LLMs to a new domain without major methodological innovations.
The paper tackles the lack of systematic approaches for generating system-level test programs targeting non-functional properties in integrated circuits by proposing the use of Large Language Models (LLMs) to generate C code snippets, achieving optimization of instructions per cycle in simulation through prompt and hyperparameter tuning.
System-Level Test (SLT) has been a part of the test flow for integrated circuits for over a decade and still gains importance. However, no systematic approaches exist for test program generation, especially targeting non-functional properties of the Device under Test (DUT). Currently, test engineers manually compose test suites from off-the-shelf software, approximating the end-user environment of the DUT. This is a challenging and tedious task that does not guarantee sufficient control over non-functional properties. This paper proposes Large Language Models (LLMs) to generate test programs. We take a first glance at how pre-trained LLMs perform in test program generation to optimize non-functional properties of the DUT. Therefore, we write a prompt to generate C code snippets that maximize the instructions per cycle of a super-scalar, out-of-order architecture in simulation. Additionally, we apply prompt and hyperparameter optimization to achieve the best possible results without further training.