Self-Learning Tuning for Post-Silicon Validation

Autor:	Domanski, Peter, Pflüger, Dirk, Rivoir, Jochen, Latty, Raphaël
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Increasing complexity of modern chips makes design validation more difficult. Existing approaches are not able anymore to cope with the complexity of tasks such as robust performance tuning in post-silicon validation. Therefore, we propose a novel approach based on learn-to-optimize and reinforcement learning in order to solve complex and mixed-type tuning tasks in a efficient and robust way. Comment: Paper is currently under review for TuZ 22 (Testmethoden und Zuverl\"assigkeit von Schaltungen und Systemen)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2111.08995 Zobrazit plný text záznamu View this record from Arxiv