In 1961 when I was a Freshman, one of the guys in the dorm became almost
religiously convinced that ESP, specifically telepathy, was genuine.
He wanted to show this by picking pairs of subjects from among his dorm
mates. The "sender" would draw a playing card from a deck and
concentrate on it while the "receiver" would sit in the next room and
try to divine the identity of the card.
The rest of us decided to give him a run for his money. I rigged a little telegraph consisting of a
battery, a flashlight bulb for the receiver, and a key made from two
little metal strips taped at one end to a wood insulator and projecting
beyond it so that they could be squeezed together to make contact.
Since the other guys didn't know Morse, I devised a simple code where
the first series of "dots" indicated the suit while the second gave the
value of the card within that suit.
Needless to say, the "telepathy" was amazingly successful. Even when the receiver did not get the card right, he was generally off by only one bit, for example calling a 9 an 8, or a diamond a heart. We strung this believer along for several days before revealing the source of the "magic."
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.