Posts from the field

In a multi-die package, no chiplet is thermally independent. Heat generated in one component travels through shared materials and changes the...

AI systems are becoming limited by heat as much as by compute and memory bandwidth. Modern accelerators use 2.5D and 3D integration to bring GPUs,...

Yesterday, I visited the Computer History Museum after a while to spend some time reflecting on the giants whose shoulders today’s computing industry...

For decades, hardware engineering has been mediated by tools. EDA stacks, PDKs, simulation environments — these defined not just workflows, but

The Industry Assumption

Chiplet Summit 2026 · Technical Talk

In this podcast episode, we explore the fascinating journey of "chipletization" from its academic roots at Stanford University to becoming the...

How modular silicon became inevitable in the age of AI

At the recent Open Compute Project (OCP) Global Summit, the

As 2.5D systems bring GPUs, CPUs, HBM, and other chiplets closer together, thermal management stops being just a heatsink problem and becomes a...

OCP’s Material Design Kit tackles an unglamorous but consequential problem: getting trustworthy material data into the tools used to design and...

🔥 The Industry Has Crossed a Line

This question comes quite often. When is a chip a chiplet? The team at the Chiplet Design Exchange (CDX) under the Open Compute Project (OC)...

The industry shift from monolithic chips to disaggregated chiplets, bound together through Heterogeneous Integration (HI), marks a significant...

IEEE2416 'Standard for Power Modeling to Enable System-Level Analysis' became official in May 2019. Among its many cool aspects it defines a new way...

The CDX (Chiplet Design eXchange) workstream under Open Compute Project’s ODSA sub-project is actively looking at the problems of chiplet...