Issue link: https://iconnect007.uberflip.com/i/1520213
38 SMT007 MAGAZINE I MAY 2024 Interview by Nolan Johnson I-CONNECT007 As we examine the entire AI ecosystem more closely, it becomes clear that AI algorithms are intensely hungry for compute power. is demand is accelerating beyond the custom- ary rate predicted by Moore's Law, just as tra- ditional semiconductor fabrication methods are failing to maintain Moore's Law. It's a real dilemma. ose watching AI say that advanced pack- aging techniques, which have been in R&D development for some time, see AI as their killer app. AI is needed to propel these cutting- edge packages into the mainstream. At a 2022 symposium on advanced packag- ing in Washington, D.C., I met Dale McHer- ron, a researcher on AI compute hardware. As we discussed IBM's work in this area, Dale introduced me to Arvind Kumar, a principal research scientist and manager in AI hardware and chiplet architectures. I reached out to Arvind to discuss his key- note presentation at the recent IMAPS con- ference where he discussed the AI hard- ware ecosystem and role of advanced pack- aging. ose in the assembly services indus- try know that any new packages will require accurate and reliable placement on the EMS manufacturing floor. Arvind shares his per- spective and some predictions based on his research. It is also clear there is still much coordination and communication needed to make this work. Nolan Johnson: What is chiplet architecture and why does it matter? How is advanced packaging moving forward? Arvind Kumar: Chiplet architectures, which allow the partitioning of complex designs into tightly co-packaged sub-elements, are influ- encing the way we think about packaging. We Chiplet Architecture for AI Will Create New Demands for Assembly