Joshi Sumit·Oct 14Building AI Accelerators: Infrastructure, Compilers, and HW-SW Co-Design — Part 1A: PCIe Hardware…DMA as a Distributed System
HyperAI·Aug 12In the Agent Era, How Should We Rethink AI Compilers?The first time I listened to Tianqi Chen’s podcast, he said you should focus your energy on the hard things — it immediately reminded me of…
Rajveer Rathod·Mar 29The Blueprint Nobody Built: What an Ex-TPU, Ex-GPU Engineer Would Do DifferentlyA deep dive into Bjarke Roune’s candid, insider guide to designing AI chip hardware and software
Tom Tan·Oct 20, 2025Cracking the CUDA Moat: How Open Compilers Could Democratize AI ComputeThe blog was triggered by a question from an investment friend. What makes Nvidia the most valued company in the world, and insofar no one…
Mineralsteins·Oct 13, 2025Ultimate Code Compression with Slotted EGraphConsider a simple IR in a compiler: (x-y)*(y-x)
