Memory Workload Synthesis Using Generative AI
Chengao Shi, Fan Jiang, Zhenguo Liu, Chen Ding, Jiang Rong Xu · Proceedings of the International Symposium on Memory Systems · 2023
Generative AI, a novel general-purpose technology, has the capability to produce outputs closely resembling its training inputs. This paper presents the first use of such learning in memory workload synthesis. By devising three learning techniques and comparing them with two existing techniques, the paper shows that by carefully choosing the training input and processing the generated output, AI-based synthesis can produce generated workloads that have similar or better accuracy than the best of existing methods.