Workflow
Constellation's Wang on Google-Nvidia Chips Rivalry

It's good to have you. First of all, maybe start with the whole idea of CPU's versus GPUs. What are some of those differences and why do you think TPS are gaining a bit more traction or at least more talk these days.You know, you're absolutely right on the analysis. Reason TPS are so important. These are tensor processing units.They're purpose built for A. I. , for deep learning.This means training and inference. This means lower total costs. This means they're more power efficient than GPUs.And, of course, ...