f `888888x./<br>' `*88888~<br>\. . `?)X.<br>`~=-^ X88><br>X8888<br>488888<br>.xx. 88888X .@8c<br>'*8888. '88888> 02025<br>88888 '8888> ^*<br>`8888> `888<br>"8888 8%<br>`"888x--> Richard Feynman and The Connection Machine — LONG NOW IDEAS

Close

Menu<br>Ideas<br>Dr. Richard Feynman during the Special Lecture: the Motion of Planets Around the Sun, 01964

Long-term Thinking<br>Richard Feynman and The Connection Machine<br>For Richard, a crazy idea was an opportunity to either prove it wrong or prove it right.<br>by Danny Hillis<br>Feb 8, 02017<br>One of the most popular pieces of writing on our site is Long Now co-founder Danny Hillis’ remembrance of building an experimental computer with theoretical physicist Richard Feynman. It’s easy to see why: Hillis’ reminisces about Feynman’s final years as they worked together on the Connection Machine are at once illuminating and poignant, and paint a picture of a man who was beloved as much for his eccentricity as his genius.<br>Photo by Faustin BrayRichard Feynman and The Connection Machine<br>by W. Daniel Hillis for Physics Today<br>Reprinted with permission from Phys. Today 42(2), 78 (01989). Copyright 01989, American Institute of Physics.

One day when I was having lunch with Richard Feynman, I mentioned to him that I was planning to start a company to build a parallel computer with a million processors. His reaction was unequivocal, "That is positively the dopiest idea I ever heard." For Richard a crazy idea was an opportunity to either prove it wrong or prove it right. Either way, he was interested. By the end of lunch he had agreed to spend the summer working at the company.<br>Richard's interest in computing went back to his days at Los Alamos, where he supervised the "computers," that is, the people who operated the mechanical calculators. There he was instrumental in setting up some of the first plug-programmable tabulating machines for physical simulation. His interest in the field was heightened in the late 1970's when his son, Carl, began studying computers at MIT.<br>Richard Feynman, taken in 1984 in the woods of the Robert Treat Paine Estate in Waltham, MA, while he and the photographer worked at Thinking Machines Corporation on the design of the Connection Machine CM-1/CM-2 supercomputer. Copyright Tamiko Thiel 1984, CC BY-SA 3.0, via Wikimedia CommonsI got to know Richard through his son. I was a graduate student at the MIT Artificial Intelligence Lab and Carl was one of the undergraduates helping me with my thesis project. I was trying to design a computer fast enough to solve common sense reasoning problems. The machine, as we envisioned it, would contain a million tiny computers, all connected by a communications network. We called it a "Connection Machine." Richard, always interested in his son's activities, followed the project closely. He was skeptical about the idea, but whenever we met at a conference or I visited CalTech, we would stay up until the early hours of the morning discussing details of the planned machine. The first time he ever seemed to believe that we were really going to try to build it was the lunchtime meeting.<br>Richard arrived in Boston the day after the company was incorporated. We had been busy raising the money, finding a place to rent, issuing stock, etc. We set up in an old mansion just outside of the city, and when Richard showed up we were still recovering from the shock of having the first few million dollars in the bank. No one had thought about anything technical for several months. We were arguing about what the name of the company should be when Richard walked in, saluted, and said, "Richard Feynman reporting for duty. OK, boss, what's my assignment?" The assembled group of not-quite-graduated MIT students was astounded.<br>After a hurried private discussion ("I don't know, you hired him..."), we informed Richard that his assignment would be to advise on the application of parallel processing to scientific problems.<br>"That sounds like a bunch of baloney," he said. "Give me something real to do."<br>So we sent him out to buy some office supplies. While he was gone, we decided that the part of the machine that we were most worried about was the router that delivered messages from one processor to another. We were not sure that our design was going to work. When Richard returned from buying pencils, we gave him the assignment of analyzing the router.<br>The Machine<br>The Connection Machine CM-1. Judson McCranie, CC BY-SA 3.0, via Wikimedia CommonsThe router of the Connection Machine was the part of the hardware that allowed the processors to communicate. It was a complicated device; by comparison, the processors themselves were simple. Connecting a separate communication wire between each pair of processors was impractical since a million processors would require 1012 wires. Instead, we planned to connect the processors in a 20-dimensional hypercube so that each processor would only need to talk to 20 others directly. Because many processors had to communicate simultaneously, many messages...