The TRIPS project: an explicit data graph execution (EDGE) processor

Keep in mind this was an academic project. The project ran its course, produced many dissertations, and more importantly successful researchers and engineers, and inspired many others to look at FPGAs and dataflow. It wasn't ever meant to be about a product or building a company...

I would counter that the project was immensely successful with the stated academic goals: as proof, the Microsoft Azure AI HW division (formerly people responsible for project catapult) was almost entirely bootstrapped by many of the same people who worked on the TRIPS project.

Here's Doug Burger providing a small retrospective on the project: https://www.microsoft.com/en-us/research/podcast/clouds-cata...

Microsoft and I believe Qualcomm research took this and did two follow-on versions. They gave a joint keynote talk at ISCA (2018?) on their experiences, but I can't seem to find any slides or video on it.

I recall them saying it looked to give them roughly the same performance as state-of-the-art processors with ~30% less power; but that's a hard gamble for the $100Ms required to get to a product (especially if it requires a new ISA).