AI’s Storage Problem Is a Packaging Problem

Most conversations about AI start and end with compute. But every training run and every inference query is ultimately a data problem, and data must live somewhere. Memory, and increasingly, the packaging that makes dense memory manufacturable, is doing as much to define AI system performance as the accelerators getting all the attention. AI models, cloud services, smart devices and connected systems create, process and store information at rates that would have seemed implausible a decade ago.