English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Test stimuli generation has been a crucial but labor-intensive task inhardware design verification. In this paper, we revolutionize this process byharnessing the power of large language models (LLMs) and present a novelbenchmarking framework, LLM4DV. This framework introduces a prompt template forinteractively eliciting test stimuli from the LLM, along with four innovativeprompting improvements to support the pipeline execution and further enhanceits performance. We compare LLM4DV to traditional constrained-random testing(CRT), using three self-designed design-under-test (DUT) modules. Experimentsdemonstrate that LLM4DV excels in efficiently handling straightforward DUTscenarios, leveraging its ability to employ basic mathematical reasoning andpre-trained knowledge. While it exhibits reduced efficiency in complex tasksettings, it still outperforms CRT in relative terms. The proposed frameworkand the DUT modules used in our experiments will be open-sourced uponpublication.

LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation