A great yarn about how the ARM1, the original ARM architecture microprocessor, was built, is told by Professor Steve Furber, Professor of Computer Engineering at Manchester University, who co-developed the chip with Sophie Wilson.
Acorn realised that it needed a 16-bit microprocessor instead of an 8-bit, for its microcomputer which had been adopted as the BBC Micro. Acorn CEO Hermann Hauser asked Intel if they could license the 286 but Intel said No.
There were, however, other 16-bit microprocessors, and the job of evaluating them fell to Furber
"We looked at National Semiconductor's and Motorola's but they were too slow ", says Furber. The obvious answer was to design their own but this looked daunting.
"The general view was that microprocessors had a mystique - that they were designed by very special people", says Furber, "I'd never designed a microprocessor, and everything I knew about them I'd learned at the Cambridge University Microprocessor Group where people met to make computers for fun. We knew that it had taken National 200 years of development time to build their 16-bit microprocessor, and Acorn couldn't afford that - we only had 300 people at the time."
"Then we came across the Berkeley RISC. A group of graduate students had built a microprocessor with only a tiny percentage of the resources used by National. In late 1983, I started working closely with Sophie Wilson who had developed all the versions of BASIC for the BBC Micro."
"Sophie and I went on a trip to Phoenix to the Western Design Centre (an independent microprocessor design house which designed the 6502)", remembers Furber, "we found it to be a cottage industry working in a bungalow in a back street. That gave us confidence. Sophie started playing with instruction set design. Our mentality was: 'Let's have a go at building a microprocessor'."
The next problem was to persuade the boss. "Hermann was a great guy to work for " says Furber, "if he had confidence in you technically he'd back a crazy idea. Building our own microprocessor was a crazy idea - but he backed it."
"Steve is one of the brightest guys I've ever worked with - brilliant " says Hauser, "and when we decided to do a microprocessor on our own I made two great decisions - I gave them two things which National, Intel and Motorola had never given their design teams: the first was no money; the second was no people. The only way they could do it was to keep it really simple."
Furber defined the architecture while Sophie developed the instruction set. "While IBM spent months simulating their instruction sets on large mainframes, Sophie did it all in her brain," remembers Hauser.
It was the birth of a microprocessor phenomenon - a chip which did the same amount of work as other 16-bit microprocessors but used one tenth of their transistors - and consequently one tenth of their electricity.
"At 1pm on April 13th 1984, the first ARM microprocessors arrived back from the manufacturer - Plessey", recalls Furber, "they were put straight into the development system which was fired up with a tweak or two and, at 3 pm, the screen displayed: 'Hello World, I am ARM'."
Subscribe to this blog's feed