


16 Nov 2026 · 56m · 25 chapters

Steve Furber recounts how first-timers helped create the ARM processor, starting from building early computers at Cambridge, joining Acorn/working on the BBC Micro, learning semi-custom chip design (ULAs), adopting RISC ideas from Berkeley/Stanford, and designing ARM’s instruction set and microarchitecture to maximize memory bandwidth. He also discusses word-size choices, testing via emulators, ARM’s later corporate history, and his later Spinnaker neuromorphic project.
Steve Furber (co-creator of ARM processor and BBC Micro; Cambridge University Processor Group participant; later Acorn chip designer; later academia; Spinnaker neuromorphic computing work). No other guest appears in the provided transcript.
ARM’s performance came from RISC simplicity enabling pipelining and better memory use (load-store, page-mode-friendly sequential access), not from complex instructions. Industry was slow to adopt risk due to investment in CISC and the “semantic gap” philosophy.
Furber’s first computer built with TTL chips and Verowire; BBC Micro contract for TV support; BBC Micro ULAs from Ferranti; ARM reference model in BBC BASIC (808 lines); instruction test programs; BBC telesoftware via TV scanlines; Spinnaker’s goal of ~1 million ARM processors with brain-like connectivity.
Written by AI. May contain mistakes.
Steve shares his early experiences with computing and flight simulation.
“What's the first computer you built and why did you build it?”
Discover how Steve built his first computer using microprocessors.
“And then in that society, the real men, and it was principally male as I remember it, built computers out of TTL chips.”
An explanation of TTL chips and their importance in early computing.
“and this had a very fine copper wire with a I think a polyurethane insulation layer.”
Learn about DIY techniques for creating printed circuit boards.
“7400 was a quad NAND gate so it would have about 30 40 components on there forming these four nan gates.”
Steve discusses how he got involved with Acorn and the BBC Micro project.
“What's the story behind you getting involved in that project?”
How enthusiasts built computers before the internet era and shared knowledge.
“And at the end of my research fellowship, I joined Acorn as a formal employee in October 81.”
Insight into how computers were manufactured in the UK during the 1980s.
“When I think of manufacturing consumer electronics at scale, I usually think of it being done in China or some other country.”
Steve explains the shift from building computers to designing chips.
“was done for the UK machines, was done locally in the UK.”
Exploration of the challenges faced in selecting microprocessors for new projects.
“And it was pretty clear that the world was moving from 8-bit microprocessors to 16-bit.”
Learn about the importance of memory bandwidth and the principles of RISC in microprocessor design.
“And secondly, through all these experiments, we'd come to the strong view that the main thing that determined the performance of a computer was the amount of memory bandwidth the processor could access and use.”
Discover how the ARM architecture was conceived and the advantages of its design over predecessors.
“I turned those instruction sets, architectures into a micro-architecture, built a reference model.”
Explore the implications of word size on performance in modern processors and why 64-bits is common.
“Going from 8 to 32-bit gives you a factor of 4.”
Understand how interpreters and emulators are used in testing and developing microprocessor hardware.
“For 8-bit microprocessors, most addresses were 16-bit.”
Learn about the distinctions and interactions between instruction set architecture and microarchitecture in processors.
“Can you explain the role of the interpreter in developing hardware?”
Learn about the intricacies of microarchitecture design and its components.
“The micro architecture is is the structure of the hardware which supports that instruction set architecture.”
Discover how the Acorn team learned to design processors with limited resources.
“But we designed hardware, high performance memory systems, graphic systems, and so on.”
Explore how the Acorn team became confident in their innovative projects.
“So we did get technically pretty confident that we could do things that we hadn't done before.”
Understand the differences between RISC and CISC architectures and their implications.
Gain insights on the cultural differences in computing between the UK and US.
“Why were all the CISC people saying CISC was obvious?”
Learn why Acorn did not pursue building their own chip fabrication facility.
“Building a fab was, even then, very expensive and completely out of proportion to Acorn's business.”
Learn about the development and challenges of ARM technology and Acorn's history.
“I mean, Apple had come knocking saying they wanted to use the arm in the Newton, but they would be more comfortable if it was an independent company.”
Discover the concepts behind neuromorphic computing and the Spinnaker project.
“And I got interested in thinking about computers and brains, what's similar, what's different.”
Understand the differences between synchronous and asynchronous circuit designs.
“An asynchronous circuit does not have that global clock.”
Hear about the challenges and experiences of competing in the IMO.
“I saw that, I think this was in 1970, you won an IMO medal representing UK.”
Gain insights on career choices and future opportunities in engineering and AI.
“I think my advice is still the same, that when you start, you know, you go through school, you have subjects you like, subjects you don't.”

Get the gist, explore an idea or ask about something said.
On The Peterman Pod, what are the key points of this episode?
Automatic transcript. May contain errors.
0:00Steve Furber: Well, if they can design a processor, maybe we can too.
0:03Sophie Wilson: This is Steve Furber, co-creator of the ARM processor and BBC Micro, and I asked him about how two people who had never designed a chip before created the world's most popular processor.
0:14Steve Furber: Nobody taught us. We picked up what we could from books and papers and made the rest up. We kind of thought all the while that Acorn's efforts would get trampled underfoot, but at least we'd have learned something. Here's the full episode.
0:30Sophie Wilson: What's the first computer you built and why did you build it?
0:34Steve Furber: I'd been interested in flying as a teenager. I flew model aircraft, not very successfully. I did a bit of glider flying at university. But then I'd kind of thought, well, you know, you have to spend a long time to get a few minutes in the glider. Maybe I should be interested in flight simulation. and then I heard about some guys who were starting a student society at the university called the Cambridge University Processor Group and this was people who built computers for fun so I thought well you know if I'm interested in building a flight simulator then maybe you know starting off understanding how to build a computer would be a good idea so I wasn't a founder of this society but I went along to therefore their foundation meeting and became quite closely involved.
1:27Steve Furber: And then in that society, the real men, and it was principally male as I remember it, built computers out of TTL chips. And the wimps like me use these newfangled microprocessor things. And I ordered a microprocessor. It was a Cignetics 2650 from a store in California. This was very scary, ordering by phone with credit cards, which were relatively new at the time, and some other components, and hand-assembled the machine using a technique called Verowire. You've got a standard PCB, and you could put chip sockets in, and then you could wire them together with a wiring pen. and this had a very fine copper wire with a I think a polyurethane insulation layer.
2:22Steve Furber: When you soldered it it melted the insulation and you got a connection but when you ran these wires around the board the insulation meant you could run the different wires through the same routes and they wouldn't short. So that was my first computer. What's a TTL chip? If you were building computers in the 1970s you're almost certainly building with TTL it was it stood for transistor-transistor logic. And there was an orange data book from Texas Instruments, which was the TTL data book. And TTL chips came from small chips that had maybe four NAND gates on to slightly bigger chips that had something like a 4-bit ALU or a 4-8-bit bus buffer.
3:11Steve Furber: They were at the level of individual logic gates or a couple of flip-flops or something like that. So all the functional components you need to build a computer, but you need a lot of TTL chips to build a functioning computer.
3:27Sophie Wilson: So it's the components within the CPU. So you could buy an ALU and hook it up to whatever other AND or OR gates.
3:37Steve Furber: Yeah. TTL logic had a standard format, so they had compatible logic swings and I guess each logic gate was I don't know half a dozen transistors and similar number of resistors or so so if you looked at the standard basic part was the 7400 they all started with 74. 7400 was a quad NAND gate so it would have about 30 40 components on there forming these four nan gates.
4:12Sophie Wilson: Somewhere in some interview you mentioned that you were anodizing aluminum in your own kitchen sink. What is that for when you were building your own computer? Why would you need to do that?
4:24Steve Furber: Well I did quite a lot of chemistry in the kitchen sink one of which was I can't remember what the technique was called but with single-sided PCBs you could etch off the copper so you get you get a pcb that was just a solid copper sheet you could draw on it with a with a pen that sort of waterproof that area of the board and then stick it in ferric chloride and that would etch off the copper where you hadn't used the pen and you'd have a circuit board okay so now anodizing aluminium was something i did for the front panel of my first computer so it's it gave the aluminium a nice finish you could then attach letter set to it to label things um and and uh produced a nice sort of reasonably professional
5:19Sophie Wilson: looking front panel did you have roommates at the time what did they think of well you know i cleaned up right i didn't leave the stuff lying around so one of the famous things that you worked on was the BBC Microcomputer. What's the story behind you getting involved in that project?
5:37Steve Furber: I became involved in Acorn because Acorn grew out of a company called CPU Limited, Cambridge Processor Unit Limited. It was formed by Herman Hauser and Chris Curry, who wanted to build a business around these newfangled microprocessor things. and in order to find people to do some of the technical work um they went to the cambridge university processor group is obvious place to go look um and that's where they found me and and sophie wilson and um and one or two other people now i was um a phd student at the time you know i I couldn't actually do paid work for them, but I could do bits of design.
6:27Steve Furber: And we had a kind of deal where they'd give me components and I'd build my own computers, which I used in my PhD research and subsequently in my research fellowship. So there was synergy between my day job and what I was doing with ACORN. but as I was getting towards the end of my research fellowship which ended the end of September 81 Acorn got to hear about the BBC looking for a computer to support a series of TV programs and Acorn secured the contract based on a design that was to a considerable extent based on the machine I built at home, not the 2650 system, but the one after that. And at the end of my research fellowship, I joined Acorn as a formal employee in October 81.
7:18Steve Furber: How does someone
7:19Sophie Wilson: go about building a computer back then? Because when I think about doing anything today, I think, okay, I'm going to look it up on the internet, and I'm going to, you know, find all these tutorials, or, but none of that existed back then. So how did you figure out everything you needed to build commercial computer?
7:37Steve Furber: There were various ways of approaching the computer, one of which was, of course, joining the University Society and talking to other people who were doing it, sharing ideas. There were also hobbyist magazines. A very long-standing hobbyist magazine in the UK was called Wireless World, which wasn't just about computers, but it did cover aspects of computer technology. And there was something, I think, called Electronics Today International or something. So there were people publishing magazines that included hobbyist designs for people to build their own things. But a lot of the time, we were just working from data sheets.
8:26So my first microprocessor was the 2650.
8:31Steve Furber: I got the 2650 data sheet, worked out how to connect that to memory and get that up and running.
8:44Steve Furber: And friends in the student society would come around and poke at it and find bugs and generally help you fix things. So, yeah, it was a social activity. And of course, the Internet did exist at that time, but the World Wide Web did not. So the Internet was a very different beast and not particularly useful in this context.
9:09Sophie Wilson: When I think of manufacturing consumer electronics at scale, I usually think of it being done in China or some other country. but at this time in history I believe it was before China had rose to prominence and being a manufacturing powerhouse so how were all of these computers manufactured were there factories in the UK that put together everything yes yes I mean I don't remember all the details
9:38Steve Furber: but I know that at one time quite a lot of BBC micros were manufactured by ICL in in Kidsgrove which is not that far from here. And ICL was the big UK mainframe computer manufacturer. You know, a sort of British IBM. But as a computer manufacturer, they had production lines for assembling printed circuit boards and they subcontracted assembly of BBC microcomputers. So yes, most of the manufacture, I think, was done for the UK machines, was done locally in the UK. I mean, the BBC Micro was also manufactured under license in India for the Indian market and in some other places. But the UK manufacturer was basically here.
10:28Sophie Wilson: After the BBC Micro, later you worked on ARM, which I think most people are very familiar with. It's in most all of our devices. What's the story behind going from building a computer to building the actual chips themselves?
10:45Steve Furber: the story of designing our own chips does start with the BBC Micro because the BBC Micro the main circuit board had 102 chips on and 100 of those were standard off-the-shelf parts 6502 quite a lot of TTL packages some CMOS but two of the chips on there were semi-custom chips designed specifically for the BBC Micro and they were uncommitted logic arrays manufactured by Ferranti in North Manchester and the uncommitted logic array was basically a chip with a sea of gates that with a single layer of metallization you could customize to your bespoke function. Sinclair used these as well in the ZX81 And you could get the equivalent of 10 or perhaps 20 TTL packages, the functionality of those 10 or 20 packages, onto a single chip with ULAs, and thereby bring the size of the circuit board down somewhat.
11:56Steve Furber: So that was my introduction to semi-custom chip design. but early in the 80s Acorn in particular Herman Hauser had decided that the company needed to get more into chip design one of his quotes I remember was that he was saying in 10 years time there'll be two sorts of computer companies those that have learnt to design chips and those that have gone bust so acorn recruited a small team of chip designers professional chip designers and it adopted chip design software from vela sci technology in the states and and so it had this chip design resource available now we and principally sophie wilson and I were thinking about what we did to follow on from the BBC Micro.
12:58Steve Furber: And it was pretty clear that the world was moving from 8-bit microprocessors to 16-bit. And we tried several 16-bit microprocessors. The BBC Micro had a dual processor capability, so you could plug a fairly simple board in with another processor and some memory. And the BBC Micro did all the I.O. So the system you had to design was relatively simple. So we built quite a number of second processors with 16-bit microprocessors on them. And we didn't particularly like what we found. And the things we didn't like were, firstly, those 16-bit microprocessors had worse real-time performance than the 6502.
13:46Steve Furber: On the BBC Micro, we made very heavy use of interrupt handling real-time data streams from floppy disks. And you just couldn't do that with these 16-bit microprocessors. Their interrupt response was too slow. And secondly, through all these experiments, we'd come to the strong view that the main thing that determined the performance of a computer was the amount of memory bandwidth the processor could access and use. And all of these 16-bit microprocessors were effectively slower than the memories at the time. They would take multiple cycles to access the memory. And the memory was capable of significantly higher bandwidth.
14:30Steve Furber: So we were sitting there with these two sort of thoughts, frustrating us a bit, as we were deciding which microprocessor we might choose for a successor product. When we heard about the risk papers, particularly from UC Berkeley, but also from Stanford, under Dave Patterson and John Hennessey's leadership respectively. And we looked at these and we saw that in the Berkeley case, a postgraduate class had designed a competitive microprocessor in a year. and so that started us thinking if they can do that maybe we can and and the principle underpinning that success was risk which i've mentioned reduced instruction set computing and this is the idea that instead of making your processor more powerful by adding ever more complex instructions you make it more powerful by simplifying the instruction set and enabling those instructions to run much faster.
15:33Steve Furber: The microprocessor is a different design environment from the mini computers of the 70s upon which a lot of the 16-bit processors were based. You have a finite transistor resource and how you use those transistors matters and the optimization point is different. And what RISC showed was that if you make the instruction set simply enough that you can pipeline the processor you get more performance than you ever get from adding complex instructions so it was that inspiration that fed into the design of the arm and and it started i think in 83 um sophie wilson looking at the berkeley and stanford designs and coming up with her own instruction set.
16:26Steve Furber: Sophie had written all Acorn's basic interpreters, so she had a very good idea of what instructions needed to do to support a high-level language. And that went into her instruction set design. I turned those instruction sets, architectures into a micro-architecture, built a reference model. I built it in BBC Basic. It's 808 lines of BBC Basic. Describes all the internal operation of the first ARM chip. And this silicon design team we'd assembled then translated the reference model into a silicon implementation. And 18 months after we started, we had the first ARM silicon.
17:15Sophie Wilson: The new generation of chips after the 6502, they were too slow when they used the memory. Well, what's the intuition behind why they were bad at using the memory and why the ARM processor was able to fully utilize memory bandwidth?
17:35Steve Furber: the the processors were slow because they they they typically used microcoded instruction execution and that meant that each instruction took several clock cycles and clocks were not that fast i mean those days we're talking about clocks around six megahertz the memory chips available at the time could support about four million random accesses per second, or twice that if you use locality. They had an optimization called page mode, where if you're accessing a location close to the previous location, i.e. in the same basic row of the memory, then you didn't have to do a full access. You could do effectively a double speed access.
18:30Steve Furber: so effectively these memories would go up to eight mega accesses per second and the processors were using multiple cycles of a clock around four or six megahertz so they just couldn't work the memories hard on arm by adopting risk principles we had an architecture where a lot of instructions execute in a single cycle not all of them but and and by designing the processor so that it gave out a signal which told you if the next address it wanted to access was close to the previous one effectively sequential was the only interpretation of close that we used so if you're fetching sequential instructions then you can do a lot of that in page mode right and and reach the full speed of the memory.
19:25Steve Furber: ARM also had load store multiple instructions which used sequential addresses quite deliberately, again to make use of this double memory speed. So we could see that by using this approach we could, and the other thing about ARM of course is it was not a 16-bit processor, it was 32-bit from the outset, which immediately gives you double the bandwidth and therefore double the performance. So we could see that going from the 6502 in the BBC Micro, we could get something like 25 times increase in the useful memory bandwidth. Going from 8 to 32-bit gives you a factor of 4. Going up by about a factor of 6 in clock speed gives you a factor of 6.
20:12Steve Furber: So we could see a huge step in potential performance, provided we could design the processors that it could run smoothly at that higher rate.
20:22Sophie Wilson: If increasing the word size from 8-bit to 32-bit improves memory bandwidth, how come in modern-day processors I don't see anything past 64-bit? Why not go to 128 or something like that and designing a computer?
20:42Steve Furber: That's a good question. The answer is that the point at which that width matters has moved. So pretty much all current processors actually run much faster than the memory. Okay. But they don't talk directly to the external memory. They talk to a cache memory that's on chip. And then the cache memory does reloads from external memory. and that can, often in multi-word chunks. So that could use a very wide bus. But there is cost associated with width. Every time you double the bus width, you need twice as many pins to make the connections. You need twice as many memory chips to build the memory.
21:32Steve Furber: And so 64 seems to be a useful place to stop. I mean, 32 bits was a great place because it was the first point at which a processor could handle an address as a single data item. For 8-bit microprocessors, most addresses were 16-bit. For the 16-bit microprocessors, the addresses had pushed through to at least 24 bits. At 32 bits, for quite a long period, you could hold a whole address as a single datum on the processor. so that was quite 32 bits was was a sweet spot and 64 was quite a long time coming
22:15Sophie Wilson: why are the word sizes often powers of two is that complete convention like why not 63 bit or 65 bit or 30 bit or something well that's that's that's a very good question as well
22:28Steve Furber: if you look at some of the very early computers then you do see quite a wide range of different word widths in the machine. Although interestingly, the first operational stored program computer, which was the Manchester Baby machine, was a 32-bit machine. But it was a serial machine. And after then, you find all sorts of issues. I mean, there was no real agreement on how big a byte should be for some time. I mean, for a basic alphabet in digits, you can manage with six bits, just about. But eventually, everybody settled on 8-bit bytes as the basic unit of storage. And so a multiple of eight became a natural feature.
23:23Steve Furber: You can build machines that have, you know, 40 bits or 48 bits. But I guess if 32 bits is a natural unit, then being able to hold two of those at once is a sensible next step.
23:38Sophie Wilson: When I was reading about the development of the ARM microprocessor, and I think you also mentioned earlier, in the development, the idea of using or building an interpreter to facilitate, I guess, testing of the instruction set or something like that was useful. Can you explain the role of the interpreter in developing hardware? Yes.
24:00Steve Furber: Was it an interpreter or an emulator? I think at Acorn we built a number of software models that would execute ARM code. The one I built, the microarchitecture, very much modeled the way the processor would work. so it had a sort of model of a two phase clock and it had latches on phase one and latches on phase two every 32 bit register in the processor is represented by a variable in the model today I think we'd call that a register transfer level an RTL model of the processor but if you want to test code that tends to be a slightly slow way of doing it. So Acorn also built instruction level emulators that just implemented the function of the instruction without attempting to emulate the hardware at all.
25:02Steve Furber: And that allows you to write bigger programs and test them before you've got real hardware available. And one of the most important things that was developed in the course of the ARM development was a set of instruction test programs. So these were programs that tried to exhaustively test every function of, for example, the barrel shifter or the ALU or the register file or whatever. And these were much quicker to develop on a higher level emulator before you then ran them on the microarchitecture emulator to check that the microarchitecture didn't have bugs.
25:50Sophie Wilson: So this emulator, it's a way to, I guess, simulate the hardware before actually crystallizing it. Yes. Okay. I read that Sophie Wilson, and you mentioned as well, Sophie Wilson worked on the instruction set and then you worked on the microarchitecture. could you explain the these two pieces of work and how they're interrelated so the instruction
26:16Steve Furber: set is is the interface between um the computer the the processor and the programmer at the lowest level okay most programmers work in high level languages but and then they have a compiler that works from their high level language down to this interface so i guess today it's more accurate to say that the instruction set architecture is the interface between the computer hardware and the compiler. And it defines things such as how many registers there are, how they're organized. So on ARM there are separate registers for handling interrupts and so on. And then what you can do by way of individual operations.
27:01Steve Furber: So ARM follows the risk philosophy of using a load architecture which means that the only interactions you have with memory are loading bytes, half words, words from memory into the register or storing them back. Unlike earlier 16-bit processors which would do things like memory, memory, add or divide, on ARM if you wanted to add two values in memory first you loaded those two values into separate registers and then you used a different instruction to add those registers together to get a result in the third register and then you could save that third register to memory if that's where you wanted the result so the instruction set architecture defines the functionality of those loan store instructions and adds and multiplies and also more subtle things such as operating system calls, subroutine calls and so on.
28:01Steve Furber: The micro architecture is
28:07Steve Furber: is the structure of the hardware which supports that instruction set architecture. So the architecture has defined you know there are 16 registers plus a number for handling interrupts so in the micro architecture you physically implement 16 registers and those registers are then connected by things called buses to for example the barrel shifter a barrel shifter is a a functional unit which will take a 32-bit number and shift it an arbitrary number of bits to the left or to the right possibly rotating the bits that fall off the end back onto the beginning or possibly not, possibly doing a sign extension as it goes.
28:53Steve Furber: And the instruction set architecture defines what functionality is required there, but then the microarchitecture could implement that in a number of ways. So on the ARM, we implemented it as a highly parallel structure, which would do any of these shifts in a fraction of a clock cycle. But we could have implemented it as a shift register, which took the value in and then shifted it one bit per clock. So if you wanted to shift 15 bits, it would take 15 clocks. That's at the microarchitecture level. And a typical microarchitect works by drawing block diagrams and buses between the units on the block diagrams and working out which values go down which bus at which point in each instruction.
29:46Steve Furber: So I literally started the microarchitecture design by sketching an arrangement of registers and barrel shifters and ALUs and so on on a piece of paper making lots of photocopies and then for each instruction for each clock cycle, colouring in what was happening on this micro architecture in this phase one of this cycle phase two next cycle and so on and you get to a point where there's an instruction you want to implement that doesn't map nicely and at that point you think well actually what I need is a slightly slight rearrangement of the buses to make that work properly so you throw all your colored in sheets of paper away and you redraw the initial sketch make multiple photocopies and start coloring in again now i'm sure today you know you wouldn't do it with photocopies and pieces of paper you'd do it with a diagram you drew on a computer and then you could you probably still want to color it in by hand for the first iteration you know on the computer but um back then in 1983 finding a computer you could do that on usefully was harder than finding a photocopier so
31:07Sophie Wilson: when i hear all this my immediate thought is how did you learn all of this because not that schooling is everything but your your phd was in aerodynamics so i get the sense that you had to pick up all this kind of by doing it where did you learn all of this i i think we
31:27Steve Furber: we made it up I mean we had you know the Berkeley papers to refer to and I think we had there was a book written on the Berkeley risk processes by Katavini it was his PhD thesis I think he's still a professor at a university in Greece and that went into quite a lot of detail as to how the Berkeley risk processes were conceived and put together and i think we just worked from that and made things up i mean yes nobody on the acorn team had had any involvement in designing a processor before for it was our first attempt for all of us but we were quite experienced at designing hardware we had some kind of thought before we start the arm project that there was a bit of mysticism and magic to designing a processor.
32:26Steve Furber: But we designed hardware, high performance memory systems, graphic systems, and so on. And it turned out that designing a processor is actually just another piece of hardware design. It's not fundamentally different from designing the sort of hardware we'd done previously. Nobody taught us. We picked up what we could from books and papers and made the rest up.
32:50Sophie Wilson: OpenAI, Anthropic, and Cursor all use this product to make their lives easier. WorkOS is an API platform that adds enterprise features like SSO, SCIM, and RBAC to your app. These are things that you need to sell to other companies, but aren't the main focus of what you're building. And now they've added more support for AI agents. For instance, Auth4Agents gives each agent its own identity with short-lived scope tokens instead of a long-lived API key. So if something goes wrong, you can revoke one session and everything under it dies. Another feature they have is Airlock, which is an authorization layer.
33:23Sophie Wilson: Every action agent takes is checked against rules that you can write in plain English. So it's not rubber stamping everything and it's not running unsupervised either. And lastly, they have pipes, which connects your agents to over 300 third-party tools without you ever needing to manage a token. So if you're building SaaS or AI agents and selling to enterprises, WorkOS fills all these gaps in a few lines of code. Check them out at workos.com to learn more and get started. And I appreciate them for sponsoring my show. One challenge with building AI products is that the cost of serving customers often scales with usage.
33:57Sophie Wilson: That makes traditional flat per-seat pricing a lot less practical. And that's where Chargebee comes in. Chargebee provides the billing infrastructure to support things like usage-based pricing, prepaid credits, and consumption limits without having to build all of that yourself. That way your team can save time and pricing can evolve alongside your product now instead of being set once per quarter. To learn more, check out chargebee.com and I appreciate them for sponsoring this podcast.
34:49Sophie Wilson: tiny i mean it sounds like there were some technicians and people helping but it was largely just you and sophie wilson i think the culture at acorn at that time was very strong
35:02Steve Furber: we'd done a number of quite challenging things and pulled them off um you know there were things the bbc micro did that nobody had done before one of which was telesoftware this was still before the days of the World Wide Web and to distribute software, the BBC had set up sending data over the unused scan lines in a TV broadcast. The TV broadcast was set up in the days of analog TVs and so there's quite a lot of slack at the top and bottom of the screen and they sent data out and we built a decode of the BBC Micro that would pick up that TV signal and extract the data from it. And all that kind of stuff worked.
35:52Steve Furber: So we did get technically pretty confident that we could do things that we hadn't done before. But I think with the arm, the ultimate success is down to the fact that, yes okay we did we did a reasonable execution okay um but we we kind of thought all the while that the risk idea was so obvious that in a mainstream industry would pick up on it acorns efforts would get trampled underfoot but at least we'd have learned something for choosing a risk processor from one of the big semiconductor houses and it just didn't happen that way so the mainstream industry never really got going it was another 10 years before they began to think well maybe risk is a good idea after all so we were very early into risk and risk brought many advantages
36:59Steve Furber: both simplicity and coming with simplicity was small size so the processor was physically small and low power because it was simple there weren't that many transistors switching and so it all came together in a very nice package the fundamental concepts were inherited from the Berkeley and Stanford risk work we managed not to foul up the implementation so it all came together
37:34Sophie Wilson: You make it sound like risk was obvious. Why were all the CISC people saying CISC was obvious?
37:41Steve Furber: I think they built up an investment in it. Now in Intel's case, they were probably right to continue with x86 because they had an established software base. And they needed to maintain compatibility with that because that was in the PC market where software compatibility was very important. So for their business, continuing with Kisk was undoubtedly made sense. I mean, they did dabble in risk. Intel did produce one or two rather unsuccessful risk processors. But the x86 kept them going. If you look at an x86 today, then to a large extent, what you see on the front end is an instruction translator that turns the x86 stream into a RISC-like stream and then it all gets executed on a RISC-like core.
38:39Steve Furber: So they haven't ignored it. It's just they use it differently. But mainstream industry, I think, had too much invested in this concept of narrowing the semantic gap between the instruction set architecture and the high-level language. And they saw complex instructions as a good thing. and they didn't recognize that by abandoning those and basically giving more work to the compiler, which is what RISC does, that you could then produce a much more streamlined hardware engine where the benefits of using the silicon, instead of using it for complex instructions, using it for pipelining, that was the first big win.
39:26Steve Furber: the first ARM chip had a three level pipeline which meant it could do fetch, decode, execute and complete one instruction per tick not all the instructions were single tick but most were and yeah it's just a lot of the industry was slow to recognize this and then slow to work out what to do with it.
39:58Sophie Wilson: When you were deciding to build ARM, I understand that you also visited America, what was the difference in the work cultures in computing between the UK and the US in your
40:13Steve Furber: perspective? Our visit to the States, I think was in October 83, was to the Western Design Center in Phoenix, Arizona, where I think it was just Sophie and I went and we were expecting to find the usual gleaming American business office block. And what we found was the Western Design Center was operating out of two bungalows in the Phoenix suburbs. These bungalows had some fairly unusual equipment around them, but they were getting school kids in over the summer to design cell libraries. and our main interest there was they were developing a successor to the 6502 which was the 65C816 if I remember right which had a bit of an address extension so it would address more memory than the 6502 and Acorn did use that in some of their products subsequent to the BBC Micro but it wasn't the big step forward it was an incremental improvement and and we came away from from seeing those bungalows which which which which was sort of much less professional than we were anticipating let's put it that way and and that was one of the things that the courses think well if they can design a processor maybe we can too did acorn ever consider building their own fab for these chips
41:47Sophie Wilson: No. And why is that?
41:50Steve Furber: Building a fab was, even then, very expensive and completely out of proportion to Acorn's business. And in any case, Acorn had this good relationship with VLSI Technology, who had a fab in San Jose, who fabricated all the early ARM chips and the Archimedes, the ARM support chips because ARM was not a one chip development it was a four chip system the processor came with a memory controller chip and a video controller chip and an I.O. controller chip and it was the four chip set that went into the early Acorn Archimedes product and we were perfectly happy with fabricating through VLSI
42:41Sophie Wilson: so this this uh arm chip that was developed it was incredibly performant um superior technology in many regards but i saw that acorn eventually kind of failed after like acorn the company not arm failed eventually why did it fail if the technology was superior acorn had
43:06Steve Furber: pushed the technology out in a joint venture with Apple and Vealus iTechnology in 1990. And there was good reason for this. I mean, Apple had come knocking saying they wanted to use the arm in the Newton, but they would be more comfortable if it was an independent company. And Acorn, Acorn's business kind of stopped growing in the second half of the 80s. so they were quite keen to offload the cost of continuing ARM development. So Apple was effectively pushing on an open door and the company was set up very quickly. And Acorn retained a shareholding in ARM but Acorn itself was a company that was also listed on the stock exchange and it reached the point where the value of ARM shares that Acorn owned was higher than the total value of all the acorn shares and at that point they decided that
44:08Sophie Wilson: it was not viable to continue as they were and so you left and you went to academia and i saw that some of what you were working on was this spinnaker architecture and this idea of neuromorphic computing could you explain what that is
44:29Steve Furber: So around 2000, I began to think that maybe just trying to sell asynchronous technology to industry was not going to succeed. And I got interested in thinking about computers and brains, what's similar, what's different. And how could my group as computer engineers contribute something to sort of understanding the mysteries of the brain? And after quite a long time thinking about this, including some key formative thinking periods while I was on sabbatical with Sun in 2005, we came with a set of ideas that formed the basis of the Spinnaker Project. so use the word neuromorphic neuromorphic goes back to the 1980s and a group led by Carver Mead at Caltech who observed close analogies between the equations that describe the flow of ions in ion channels in biological neurons and the flow of carriers in transistors operating in the sub-threshold region and they developed a number of sensor chips based on this analogy and since then neuromorphic technology has expanded to include a wider range of approaches and Spinnaker is not sub-threshold analogue, it's all digital but it's still to a significant degree brain inspired.
46:02Steve Furber: The goal of Spinnaker was to build a platform for modelling brain regions and we set ourselves the goal of putting a million ARM processors into a single computer that we could couple to run real-time models of brain regions in biological real time, in other words, the same speed as the biology.
46:24Steve Furber: And the key feature of the machine that's brain-inspired is how we connect to those processes, because the brain is very highly connected. Typical cortical neurons connect to 5 ,000 to 10 ,000 other neurons. So that's the kind of degree of connectivity we had to aim for. and that gives spinnaker a unique communication system it's it's not a general purpose communication system it's not good for everything but it's good at this one thing you mentioned synchronous
46:58Sophie Wilson: asynchronous or i i presume that's equivalent to clock and clockless yes what's the pro and con of
47:05Steve Furber: the two approaches well most most electronic circuits operate off a clock so clock provides a regular beat that keeps all the activity on the chip in synchrony. An asynchronous circuit does not have that global clock. It has local circuits which manage the transmission of data from one unit to another and generally that's done as soon as the data is ready. So some parts of the chip can be running quite quickly and others quite slowly and it's just local management. It's a bit more complex to design asynchronous circuits, particularly as the industry EDA tools don't manage them very well. So that's a drawback of asynchronous design.
47:56Steve Furber: One of the advantages of asynchronous design is you generate far less radio interference and the current spikes are less severe because the activity is not synchronized. So on a synchronous chip, when you hit the clock, lots of things switch straight away, and that gives you big transients in the supply current. In an asynchronous design, that doesn't happen. And it also means that the radio emissions you get are much lower and sort of broader spectrum than with the clock design. but you can also enable things to go at their own speed. You know, one view of a clock is it slows all the faster circuits down to match the speed of the slower circuits so that everybody keeps in step.
48:48Steve Furber: In an asynchronous circuit, you don't need to do that. The faster circuits can go faster.
48:53Sophie Wilson: When I was doing the research for this interview, I saw that, I think this was in 1970, you won an IMO medal representing UK. What was it like competing in the IMO back then and how'd you get into it? So I got into it because the school I attended regularly put pupils in for the National Mathematics Contest, as it was called in the UK.
49:22Steve Furber: and that was a contest which was used to select the British team for the International Maths Olympiad and one year I came in the top I think there were eight pupils were sent to the IMO the year I went the IMO was in Hungary in a place called Kesteli I think if I remember right and the nature of the IMO is loads of school kids roughly end of school age sit down and do exams for a couple of days
50:00Steve Furber: which then get marked and assessed and there are a number of gold medals a number of silver, a number of bronze I got a bronze medal that year but it was interesting I was used to doing a lot of maths at school I mean, my sixth form subjects were double maths and physics. And physics is kind of just another maths, really. So I was used to doing a lot of maths and enjoyed it. And when I went to Cambridge, I went up to read maths.
50:34Later, switched from maths to engineering and aerodynamics.
50:41Steve Furber: but right through school and undergraduate university i was a mathematician when you
50:47Sophie Wilson: look back on your career is there um some particular engineering work you're most proud of
50:53Steve Furber: arm is probably the singular highlight because it's become so globally dominant you know the last figure i heard is that over 350 billion arm powered chips have been shipped by arm's part of the network i mean arm itself doesn't well until recently didn't make any silicon it has now started making some ai silicon i believe but but the fact that arm is is sort of is everywhere on the planet now and whenever you go into a room full of people you know there are more arm processors in the room than there are heads um it is something that that you know i'm pleased to have been there at the beginning and formed the seed of course thousands of people since have worked to make that success that it is are there any book recommendations that you have
51:50Sophie Wilson: that were impactful for you or something that you would recommend to others if you if you wanted
51:57Steve Furber: advice for people wanting to work in computer architecture then of course you have to go to the Hennessy and Patterson book or is it Patterson and Hennessy I can they seem to change their names around at random but they've written a couple of books on computer architecture and computer organization which are the books on the subject with all the experience that you have now if you
52:23Sophie Wilson: could go back to yourself when you just entered the industry and give yourself advice what would you say?
52:29Steve Furber: I think my advice is still the same, that when you start, you know, you go through school, you have subjects you like, subjects you don't. What do you do at university? Is it obvious? For a few people, there's a vocational calling that makes it clear, you know, if you want to be a doctor you better do medicine right if you want to be a vet you need to do veterinary science and so on but most people are are not so specific in what they want to do and my general advice is if you have to make a choice then choose the course that keeps them the most doors open right so try and maximize your future options unless you have a very specific course you want to follow and and look for opportunities as they arise so i was 10 years in the university undergraduate phd research fellowship that was maths and aerodynamics but then the personal computer business was taking off and that was clearly an opportunity I mean today where are the opportunities well I think you'd have to highlight AI as an area which is going to have huge impact it's already started and there are many aspects to it designing better chips for AI at the hardware level but there's all sorts of ethical and philosophical issues at the very high levels and the software in between where people can have an impact.
54:23Steve Furber: And that's just in the computing domain. I mean, there's lots of exciting things happening in the life sciences as well, which are quite a different subject area and one I know much less about.
54:37Sophie Wilson: Awesome. Well, thank you so much for your time, Professor. I really appreciate it. Okay, you're welcome. Hey, thank you for watching this podcast. If you liked it and you want to see the show grow, please support with a comment or a like. Also, if you have any recommendations for people you want me to bring on, please drop a comment. Guests like Barbara Liskov, Mike Stonebreaker, Mark Brooker, these were all people that I brought on because someone left a comment. On another note, aside from the podcast, I'm working on building the ergonomic keyboard that I wish existed. Here's a glance at the prototype.
55:09Sophie Wilson: It's a split keyboard.
55:11Steve Furber: So there's two sides. This is in the case.
55:14Sophie Wilson: But yeah, we launched on Kickstarter. and we hit our goal within eight hours of launching. I really appreciate it if you were one of the people who grabbed one of the early units. We're now working on the long journey of building the tooling now. And so if you still want to pick one up, I've left the late pledges open on Kickstarter. So you can grab one there. I'll put a link in the description. Thank you again for watching the podcast and I'll see you in the next episode.
In 1984, two first-time chip designers, Steve Furber and Sophie Wilson, created what would become the most popular processor in the world (ARM). I interviewed Steve about how they did it with such a small team that had no formal training.
We also covered a bunch of questions about hardware design and his answers were so clear. I learned a lot and hope you enjoy the episode!
• My ergonomic keyboard project I mentioned, you can follow along here: https://read.compose.llc/
• The Kickstarter page for it: https://www.kickstarter.com/projects/ryanlpeterman/compose-simple-ergonomics-beautifully-done
Podcast links:
• YouTube: https://www.youtube.com/watch?v=3K9L0dRRzOs
• Apple: https://podcasts.apple.com/us/podcast/the-peterman-pod/id1777363835
• Transcript: https://www.developing.dev/p/e075-steve-furber
Thank you to this episode's sponsors for supporting my work:
• WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at https://workos.com/
• Chargebee: billing and monetization infrastructure for the AI economy, so your pricing can evolve alongside your product, check them out at https://www.chargebee.com/
Timestamps:
(00:00) Intro
(00:27) Building his first computer
(05:28) BBC Micro
(10:28) Designing the ARM processor
(17:15) Why their design was better
(23:38) Emulators and interpreters
(25:58) Instruction sets and microarchitecture
(31:08) How they learned chip design
(34:27) Why they were so successful
(39:57) America vs UK
(42:40) Why Acorn failed
(44:10) Neuromorphic computing
(48:52) Winning an IMO medal
(50:45) His most proud engineering
(51:46) Top technical book recommendation
(52:29) Advice for young people
(54:42) Outro
Where to find Steve:
• Personal website: https://personalpages.manchester.ac.uk/staff/steve.furber/
• University of Manchester research profile: https://research.manchester.ac.uk/en/persons/steve.furber/
• X: https://x.com/FurberSteve
• LinkedIn: https://www.linkedin.com/in/stevebfurber/
• GitHub: https://github.com/sfurber
• ORCID: https://orcid.org/0000-0002-6524-3367
• Google Scholar: https://scholar.google.com/citations?user=jLnsiBEAAAAJ
• Wikipedia: https://en.wikipedia.org/wiki/Steve_Furber
Where to find Ryan:
• Newsletter: https://www.developing.dev/
• X/Twitter: https://x.com/ryanlpeterman
• LinkedIn: https://www.linkedin.com/in/ryanlpeterman/
• Threads: https://www.threads.com/@ryanlpeterman
• Instagram: https://www.instagram.com/ryanlpeterman
• TikTok: https://www.tiktok.com/@ryanlpeterman
Referenced in this episode:
• Reduced Instruction Set Computer Architectures for VLSI: https://mitpress.mit.edu/9780262111034/reduced-instruction-set-computer-architectures-for-vlsi/
• Computer Architecture: A Quantitative Approach: https://shop.elsevier.com/books/computer-architecture/hennessy/978-0-443-15406-5
• Computer Organization and Design: The Hardware/Software Interface: https://shop.elsevier.com/books/computer-organization-and-design/patterson/978-0-08-050257-1