Expedera Inc

Expedera's Athish Rahul Rao argues that the core hardware question is no longer how many TOPS can fit within a given power and area budget. It is whether an architecture is built around real multimodal workload behavior, especially memory movement, activation lifetimes, utilization under irregular graphs, and the software needed to schedule all of it effectively.

Why Vision LLMs Force A Rethink Of Edge AI Hardware Peak TOPS is becoming a weaker proxy for delivered edge performance.

How much of the energy consumed in an AI chip is spent doing something useful? This question affects everything from software to system architecture to chip design - this issue is explored in a SemiEngineering feature, with comments from Expedera's Chief Scientist and Co-founder, Sharad Chole

Minimum Energy Per Query How much of the energy consumed in an AI chip is spent doing something useful? This question affects everything from software to system architecture to chip design.