MIT processor database just released
About five years ago, my colleague Zachary Schmidt and I started compiling a database of historical central processing unit (CPU) characteristics, building on previous efforts from Stanford and elsewhere (Danowitz et al. 2012, Horowitz et al. 2005, Leiserson et al. 2020, Rupp 2018). The funding for this initial effort came from my client at Sony Playstation, Kieren Mayers, who wanted data to show to his engineers about recent trends in computing to spur their imaginations.
In March 2024, at a dinner party in Palo Alto given by my college roommate Eric Brynjolfsson, I met Neil Thompson of MIT in person for the first time. He had attended a talk I gave in 2010 and requested the paper I presented then, but we didn't interact beyond that until the dinner in 2024, where we had an animated conversation about recent trends in computing. We also agreed to chat about merging our efforts.
On November 17th, 2026 at the Supercomputing 2026 conference in Chicago, IL, MIT announced the culmination of that joint research project, the new Processor Database website. The publicly accessible database includes data on both CPUs and GPUs, and we'll be adding more device types soon. We have a distinguished panel of experts on our steering committee, with many industry luminaries whose names you'll probably recognize.
We have a commentary article now in what we hope will be the final stages of review for a peer reviewed journal, and I'll post more on that soon. For a peek at the latest CPU and GPU results, see my recent talk at PDF.
Here's one of the key graphs:

References
Danowitz, Andrew, Kyle Kelley, James Mao, John P. Stevenson, and Mark Horowitz. 2012. "CPU DB: Recording Microprocessor History." Processor. vol. 10, no. 4. April. pp. 10–27. [http://queue.acm.org/detail.cfm?id=2181798]
Horowitz, Mark, Elad Alon, Dinesh Patil, Samuel Naffziger, Rajesh Kumar, and Kerry Bernstein. 2005. Scaling, power, and the future of CMOS. Proceedings of the IEEE International Electron Devices Meeting, 2005. IEDM Technical Digest. December 5. [https://ieeexplore.ieee.org/document/1609253]
Leiserson, Charles E., Neil C. Thompson, Joel S. Emer, Bradley C. Kuszmaul, Butler W. Lampson, Daniel Sanchez, and Tao B. Schardl. 2020. "There’s plenty of room at the top: What will drive computer performance after Moore’s law?" Science. vol. 368, no. 6495. pp. eaam9744. [http://science.sciencemag.org/content/368/6495/eaam9744.abstract]
Rupp, Karl. 2018. 42 years of microprocessor trend data. February 15 2018. [https://www.karlrupp.net/2018/02/42-years-of-microprocessor-trend-data/]
