A Survey of Machine Learning for Computer Architecture and Systems

It has been a long time that computer architecture and systems are optimized for efficient execution of machine learning (ML) models. Now, it is to reconsider the relationship between ML let transform way designed. This embraces twofold meaning: improvement designers’ productivity completion virtuous cycle. In this article, we present comprehensive review work applies system design. First, perform high-level taxonomy by considering typical role techniques take in architecture/system design, i.e., either fast predictive modeling or as design methodology. Then, summarize common problems can be solved employed resolve each them. addition emphasis on narrow sense, adopt concept data centers recognized warehouse-scale computers; sketchy discussions provided adjacent systems, such code generation compiler; also give attention how aid automation. We further provide future vision opportunities potential directions envision applying would thrive community.