How does my computer work?
This week - we use them everyday - at work, at home, to chat to our friends or listen to music - but how do computers actually work, what’s inside them, and what will the computers of tomorrow look like? We’ll be navigating through the past, present and future of computing, and lifting the lid - literally - on a PC to peek inside and see how it works...
Music this week from: https://www.bensound.com
In this episode
Let's meet the panel
with Jeffrey Salmond - Cambridge University, Sophie Wilson - Broadcom, Tim Cutts - Wellcome Sanger Institute, Alan Blackwell - Cambridge University, Noa Zilberman - Cambridge University, Chris Folkerd - UK Fast
Chris Smith and Tim Revell introduced the panel of computer experts who joined us to unpick the bits and bytes of computers. First up, Jeffrey Salmond, a research software engineer in Cambridge University’s IT service, who works with a supercomputer. Chris asked Jeffrey what a supercomputer is...
Jeffrey - A modern supercomputer is pretty much just a collection of normal computers all connected together.
Chris - What’s your electricity bill?
Jeffrey - We use about a megawatt of electricity. I don’t know what that is in pounds...
Chris - Pretty eye watering! And what sorts of problems can you solve with it?
Jeffrey - We can solve some pretty large scale problems like of simulations of big physics problems like galaxies colliding or simulating any kind of physical things right down into subatomic particles.
Chris - So big thinking. Tim?
Tim - Also with us is Sophie Wilson, a computer scientist at Broadcom. You were involved in developing the ARM microprocessor, one of the most significant processors of all time. Why is that Sophie?
Sophie - We designed it back in 1983. In the intervening 35 years, we’ve gone onto to sell 120 billion chips powered by ARM microprocessors.
Tim - What sort of things are they used in?
Sophie - They are used in everything. You’ll know that they’re in your mobile phone but they’re everywhere else as well. They’re contaminating everything you touch!
Chris - I think the share price has probably just plummeted at that point, don’t you think Sophie? More from her later in the programme.
Tim Cutts is the head of scientific computing at the Wellcome Sanger Institute. Now that’s where a big chunk of the human genome was decoded. But Tim, what has DNA got to do with computing?
Tim - In order to study the human genome and its impact on disease and how we can help, we need to gather very large numbers of human genomes and compare them with each other, and that’s an enormous computational problem.
Chris - So it’s really just storage of data; how much information you have to pack away and compare?
Tim - Storage and analysis.
Chris - Big problem. Tim?
Tim - Also with us is Alan Blackwell who works at Cambridge University’s Computer Lab. Alan, how good are computer graphics today?
Alan - They’re a lot better than they were when I started my career! My first graphics project involved the graphics coming out of the back of the computer on pieces of paper.
Tim - Amazing! What can they look like now?
Alan - Of course now, we’re very excited about virtual reality and augmented reality. Things that either make us believe we’re in a different world or make our world look different to the way it is.
Chris - Noa Zilberman is also here. She’s from the Cambridge Computer Lab where she specialises in networks and operating systems. Noa, how much data is the world moving these days and how much information is flowing through computers worldwide?
Noa - Numbers are really crazy. The fastest network devices today can process all the seasons of Game of Thrones in less than a second.
Chris - Is that a good thing? You presumably want to watch it at the same time?
Tim - Ha ha. And Chris Folkerd is the director of enterprise technology at Manchester-based UKFast. Chris, what is UKFast?
Chris F - We’re one of the largest cloud providers in the United Kingdom and we make massive amounts of computer resource available for businesses across the world.
Tim - What can they do with that computer resource?
Chris F- Anything the want really. It gives them the capability to do huge things with big computers that they couldn’t otherwise afford in their offices.
Chris S - Thank you very much. You’ve heard the panel of people that we’re going to be speaking to as we make our way through the world of computing, including it’s past, its present and, hopefully, its future.
04:16 - Building a PC - power supply
Building a PC - power supply
with Nick Batterham - Cambridge University
Naked Scientist Katie Haylor took up the challenge of building a desktop PC with the help of Nick Batterham from Cambridge University's Department of Computer Science and Technology. Step 1 - connect the power supply...
Nick - This is the black box that most people have underneath their desk.
Katie - I can see what looks like a fan on one side, and then in the middle is a big green circuit board with a whole lot of stuff going on.
Nick - Yes, that’s right. The fan on the back of the box is to aid cooling that comes as part of the box. The big green board that you see at the bottom is what we call the Motherboard. It’s a printed circuit board about 30 cms square and it’s on this board that you connect the microprocessor, the RAM, and peripheral cards like a graphics card, for example. The motherboard enables the communication between all those components and it also allows you to connect external components like a hard disc or a CD/ROM via suitable cables.
Katie - We need a power supply, right?
Nick - Thats right.
Katie - In order to do anything we need some power, so where is the power supply?
Nick - This is a power supply.
Katie - It‘s a kind of grey box, again with a fan to make sure things don’t overheat, and then there’s a whole load of cables coming out the back of it.
Nick - Yeah. The power supply takes in the normal mains that everybody has at home converts it to voltage levels that are suitable to drive the electronics; round about 12 volts, 5 volts, and sometimes 3.3 volts as well and, of course, you need grounds too. That’s what all these different colour cables are: the yellow means 12 volt, black as ground, red is 5 volts, orange is 3.3 volts.
Katie - Can we put it in?
Nick - Sure.
06:33 - How much energy does a computer use?
How much energy does a computer use?
with Jeffrey Salmond, Cambridge University
How much energy does a computer use? Chris Smith asked research software engineer Jeffrey Salmond...
Jeffrey - Ours is the biggest UK academic computer so it’s quite large and it‘s about 70th in the world or something like that. So it’s big, but it’s not the biggest.
Chris - When one goes about commissioning or building a computer, how does it work? What do you do to make one?
Jeffrey - Probably the most important bit that makes it a supercomputer, rather than just a computer, is that we have these many computers operating together to solve one problem all at once, which means that they need to have a fast network to connect them together.
Chris - When you say you’ve got them all working together, if it’s one problem how can you distribute the problem among lots of computers in that way?
Jeffrey - That’s a difficult thing. That requires a lot of work both on the hardware level and from the people writing the software to run on these computers.
Chris - Say I want to simulate the Universe, why is it better to have supercomputer like yours to do that than just my desktop PC?
Jeffrey - To simulate something as big as the Universe, you’re going to need a lot of memory. Your desktop might have a few gigabytes of memory, where's our large computer will probably have multiple terabytes of memory and you can use all of that at once.
Chris - But critically, will your computer do Facebook?
Jeffrey - It probably wouldn't actually.
Chris - That was a slightly daft question but what I’m getting at is, is the operating environment that is running on your computer different to what one would be familiar with if you just use Windows or Mac or something?
Jeffrey - It doesn’t run Windows or Mac, but it does run Linux which is a bit more niche. It can be used as a desktop environment just like Windows can.
Chris - How much more efficient is using a supercomputer than using a desktop because one way I could, I suppose, solve a problem is I could just persuade Tim and a few other people in this room to lend me their computers and link them together like you have. We could distribute our problem around the world in that way because people do do that don’t they? IBM does this with the community World Grid, I think it’s called, isn’t it?
Jeffrey - Yes.
Chris - Why have a supercomputer like yours then?
Jeffrey - Some problems: I think the folding at home problem is a famous example that was easily read over a worldwide network of Playstations in this case. But they were able to do that because each unit of work which, in this case, was calculating how a protein folded was easily separated from each other unit of work. You can simulate how protein A folds independently of how protein B folds whereas that’s not true of all simulations.
If, for example, you’re trying to simulate the weather, the weather here in Cambridge is going to be very closely related to the weather in London. If computer A is simulating the area that’s Cambridge and computer B is simulating London, then those two need to be able to communicate together very efficiently.
Chris - How do you keep them safe in the sense that are you a target for people hacking and either trying to steal what you’re processing, or steal your computing time so that they could get your very good computer to solve a big problem for them that might give them a lead in making some bitcoins, for example, that on vogue at the moment, isn’t it?
Jeffrey - The supercomputer would be an excellent resource for getting lots of bitcoins, so we do have to be quite mindful that people would like to do that. Anything in the University is under constant cyber attack by people from around the world. Our facility is no different from anywhere else.
Chris - You don’t get tempted to mine for a few bitcoins yourself?
Jeffrey - Not yet.
Chris - Not that you’re willing to admit on air anyway...
11:06 - Computers from the past
Computers from the past
with Jason Fitzpatrick - Centre for Computing History, Cambridge
For many of us, a high resolution, colourful screen is a key part of any computer - be it a smart phone, laptop, or desktop PC. But this wasn’t always the case. With the help of Jason Fitzpatrick from the Centre for Computing History in Cambridge, Katie Haylor took a trip back in time to meet a few computers from the past...
Jason - My name is Jason Fitzpatrick and I am the CEO here at the Centre for Computing History.
We look at more of the home computing, the way computers started to become part of our lives. And we’ve got a machine back there from 1963 which is called the Elliott 903. It’s a computer that doesn’t have a CPU - no microprocessor.
Katie - To be honest, it doesn’t look, to me, like a computer at all. It’s an enormous big box that looks a bit like a fridge or something and inside there’s racks, and racks, and racks of electronic components. Are they transistors?
Jason - Yes, they are. They’re transistors, yep.
Katie - How does it work; what does it do if it has no processor?
Jason - That’s why it’s on display; this is an interesting story. Most people think a computer has a microprocessor which, obviously, modern ones do. But, what is a microprocessor? It’s simply a semiconductor that has thousands and thousands, millions, in fact billions today, transistors on it all shrunk down into silicon and then they form the processor, the brain of the machine. Actually, if you go backwards, then you could theoretically make a computer just out of the transistors themselves, and that’s what this machine is.
Katie - What are the transistors doing?
Jason - Simply switching on and off. Computers, most people know, work on binary - ones and zeros. In fact, we say ones and zeros, but to a computer it’s not even ones and zeros. It doesn’t understand what a one or a zero is, it understands whether there’s an electrical signal and no electrical signal.
Katie - So off/on?
Jason - Exactly. Off and on. This computer has, I think, about 2½ thousand transistors in it that make up the processor. It’s kind of all a processor, the whole thing and if you shrunk all those transistors down, that would make a microprocessor that we know today.
From here, the transistors in the Elliott, they were packaged into small chips - logic chips - and we had maybe had 100 transistors on a logic chip. But, as we got better and better at making those logic chips, we can get more on there and then we start to have an entire computer, an entire Elliott, on one chip. That then allowed us to do more with that so you could have lots of these chips and make a more powerful machine.
Katie - What have we got here then?
Jason - This is our 80s, we call it 8 byte 80s. And the one I’m going to choose is the Sinclair ZX 81.
Katie - It is tiny. It’s just a black square with a tiny, tiny keyboard on it and then there’s a monitor which looks incredibly old school.
Jason - It’s a television.
Katie - It’s a TV? Oh wow, okay.
Jason - You had 1k of memory. You can’t even send an email these days in less than that.
Katie - Wow!
Jason - It had all of the colours as long as that was black or white. It had no sound and it was brilliant!
14:22 - Building a PC - processor
Building a PC - processor
with Nick Batterham - Cambridge University
Naked Scientist Katie Haylor took up the challenge of building a desktop PC with the help of Nick Batterham from Cambridge University's Department of Computer Science and Technology. Step 2 - find the processor...
Nick - This is the component that does all the work - it’s the brains of the computer. The part that manipulates the data and it does calculations.
Katie - It’s a square; I think there’s some silicon in it, is that right?
Nick - Yeah.
Katie - It looks like it’s encased in; is that metal or plastic?
Nick - It’s a metal case over the top.
Katie - Ah, okay. So you just turn that over and things look a bit more interesting.
Nick - Each one of those tiny little squares that you can see there is made of gold and each one of those is a connection to the microprocessor, so there are hundreds.
Katie - The microprocessor is the bit that’s inside all of that?
Nick - Yes. The actual piece of silicon with the actual microprocessor is actually much smaller than this. That will be a piece in the centre there, probably about the size of my little finger.
Katie - Where does it go? If we walk back over to our box with our power supply and our motherboard, where does it go?
Nick - It goes in this holder here that’s roughly in the middle of the board. You undo that lever there and pull it back and this frame lifts up.
Katie - Ah, okay. And just slots straight in?
Nick - Yeah. The microprocessor, you literally just hold it by the edges and lay it into that frame carefully. It can actually only go one way because there are little notches on each side, what we call keys, that only allow you to put it in the correct way.
Katie - So we’ve just put in the brain of the computer?
Nick - Yeah. Other than we have to put this metal frame back over to hold it in place like so.
16:24 - How does a processor work?
How does a processor work?
with Sophie Wilson FREng FRS, Broadcom
The processor is the so-called “brain” of the computer, but what exactly is it doing? Sophie Wilson developed the instruction set that underpins the processors made by ARM, one of the world’s most significant chip design companies - their technology is in about 95% of smartphones. Before that Sophie helped to design the processors that made the Acorn BBC microcomputer possible, and that introduced a whole generation of people to home computing. First off, Chris Smith asked Sophie to explain exactly what a processor is...
Sophie - When we design electronics, it’s all about putting stuff together to make something happen - a fixed function. In the early days, fixed functions were all you got. If you built a radar set for World War II, then it did a fixed thing and it couldn’t vary it at all unless somebody took a big hammer to it and redesigned it. So a programmable element was needed in order to break the German ciphers. Dr Alan Turing put together the very first programmable cypher engines to crack the Enigma cipher and a Turing Bombe was programmable because you had bits of wire on the back that you put into different orders in order to make it run different programmes. Nowadays, we put different instructions into memory so we have a fixed set of functions inside the processor, and it fetches instructions from memory and does each fixed function, and you change the instructions and it does something completely different.
Chris - Those instructions get in through those small connectors on the underside of the chip that Katie was referring to when she built her computer?
Sophie - Kind of, yes.
Chris - If we were to zoom in with a really powerful microscope on the processor chip, what would we see in there?
Sophie - If you open the chip up, take all the packaging off it, all you’re left with is this coppery coloured ingot of stuff. First you have to etch that away and get rid of it all and then, with a sufficiently good microscope because we make things that are extremely small - critical dimensions on current generation chips are made with deep ultraviolet light so you can’t even resolve this stuff with optical light. But, assuming it’s a sufficiently good microscope - electron microscope or something like that - then you can see lots of layers of connectivity, different types of material. We need to make something capacitive, something connective, something that is a semiconductor, and have all those layers work together. So we build very thin layers of stuff on top of each other to do all this.
Chris - Those are the transistors?
Sophie - Across a silicon chip then we’re making billions of transistors and connecting them together to give the functionality we want. The future of microprocessors is very much the future of transistors and has been for the last 40 years. For some time we’ve had Moore’s Law. Moore’s Law is a law about economics: it says it’s economically feasible to put twice as many transistors onto the same area of silicon every period. The period started off at about a year and then it got lengthened to a year and a half, and now it’s two to three years. Currently, it takes us about 28 times as many scientists to push Moore’s Law forward as it did originally so it’s getting really expensive to do this. We haven’t hit any physical reality limits; we can still do these things, it’s just getting really expensive to do it. So, as I said, we’re using deep ultraviolet light and we want to move to extreme ultraviolet light - 33 nanometre wavelength light.
Chris - Is this so you can etch the silicon to make these tiny components?
Sophie - This is to make the transistors smaller and thus fit more of them in.
Chris - Because if you use light which is a shorter wavelength, then the size of the component you can make is smaller, that’s why you want to use that particular colour?
Sophie - You want to use the smallest controllable bit of light that you can. Making extreme ultraviolet light in sufficient power, because we want about 200 watts of this light, is very hard. I’ve likened it in the past to the Star Wars particle beam weapon so we have a one megawatt carbon laser producing ordinary light. That goes into a vacuum chamber where we have evaporated some tin droplets. We atomise the tin droplets in the vacuum and that produced lots of sets of ultraviolet radiation so we filter out the ones that we want and take those off to be our extreme ultraviolet light source.
Chris - Are there better materials that we can use in future because, obviously, we are getting to the stage now where we are finding these materials are harder to work with to endow them with more power, so is it that we’re just going to step sideways and start using something completely different? Is there going to be a regime shift if you like and we’ll develop the new generation of processors in an entirely new way with a new material?
Sophie - We’ve been using new materials all the way through that. The types of things we use for insulators have changed. How we put the whole thing together has changed enormously. The connectivity has changed - we used to use aluminium, we use copper. In the future we’re going to use really rare things like ruthenium for the interconnect. We call it Silicon Valley. In the future, if we happen to be using molybdenum disulphide…
Chris - It’s not so catchy!
Sophie - It’s not so catchy. Molybdenum disulphide fen or valley - it’s just not going to take off, is it? People have been looking at the future of transistors. We can make things still on a silicon base but with carbon nanotubes, or we can use this molybdenum disulphide material, which is also a semiconductor, and make things smaller but we still have this lithography problem. The people who made the world's smallest one nanometre transistor, they actually made millions of them using carbon nanotubes that they scattered on a surface and selected out the ones that worked, so that’s not really a basis for future mass production. We’re moving towards seven and five nanometre transistors, and when we get to five we really need this extreme ultraviolet laser to work properly. It doesn’t work properly at the moment.
Chris - Just to finish: when you built the BBC microprocessors that went into those first generation of computers that really made a difference to home computing back in the 80s - in the 70s you were designing those weren’t you? How many transistors were on those chips compared to what we’re routinely knocking out for the average smartphone these days?
Sophie - The BBC machine we used an 8-bit microprocessor - the 6502 - and that has 4,000 transistors in it. The very first ARM has 25,000 transistors in it. Currently, if you by a top end GPU…
Chris - That’s graphics processing?
Sophie - Yes. The top end graphics processor, or a top end Intel microprocessor with about 28 cores on it, you’re looking at buying about 9 billion transistors, they will sting you for 10,000 dollars for the best of them. At least it’s practical.
23:48 - Building a PC - data storage
Building a PC - data storage
with Nick Batterham - Cambridge University
Naked Scientist Katie Haylor took up the challenge of building a desktop PC with the help of Nick Batterham from Cambridge University's Department of Computer Science and Technology. Step 3 - add a hard drive...
Nick - There are two types of storage device: there’s the RAM - the random access memory. This is the memory that will go on the motherboard.
Katie - These are green, almost a tiny ruler? It’s green on the base and then some gold etchings along the side, and it looks like you’ve got some electronic components sitting on this RAM.
Nick - Each one of these sticks is actually called a DIM. The actual memory are these little black chips that are mounted on the surface. And they have them on both sides, so this particular Dym is 2 gigabytes and we have two of those so that means we have 4 gigabytes in this system, total. The processor can communicate with this, retrieve the information it needs or write new information to it much faster than your hard disk, but this type of memory is volatile. When you turn the power off you will lose whatever you stored in it. They go in these sockets here.
Katie - It’s a bit like teeth, they just slot in either side of these groves?
Nick - That’s right.
Katie - It sounds like it’s gone in.
Nick - Yep.
Katie - You said that this was volatile memory in that when you switch off your computer that’s gone. What about non-volatile memory? Is this where the hard drive comes in?
Nick - Yes, that’s right. But it’s construction is completely different.
Katie - You’re holding it right now and it’s a box. It’s got some plastic on the side and then metal in the middle and once you’ve just turned it over I can see some circuitry. Is it possible for us to look inside because I think you mentioned this was a little bit like a record player, right? You’ve got things that spin...
Nick - Don’t take it too literally, but yes, kind of…
Hard disc drives are about the size of a pack of cards. Nick opened one up so we could see what was inside.They contain a stack of small, brown magnetic discs referred to as "platters", that are each a bit like a mini LP.
Sitting above each platter is an arm, like the needle you’d see on a record player.
When the hard disc is connected, the platters spin at high speed. The drive keeps an index of where all of the information is stored on the platters, or where it has free space, so it can rapidly move the arm to the correct location to write or read information magnetically to and from the disc surface. Critically, unlike RAM storage, when the computer is shut down, the information remains on the discs, ready for when you next need it or until you overwrite it with something else...
Nick - You can put the hard disc anywhere you like inside the case. The cases normally come with little compartments that are designed to hold the disc.
So these pieces of plastic usually come with the case. You fit them on the edges of your hard disk and that allows you to just slot the disk in somewhere in the case like that.
27:02 - DNA - storing masses of data
DNA - storing masses of data
with Dr Tim Cutts - Wellcome Sanger Institute
It’s one thing to store a PC’s worth of data - records, finances etc., but what about on a much bigger scale? Tim Revell spoke to Tim Cutts, head of scientific computing at the Wellcome Sanger Institute in Cambridge where a large amount of the human genome was sequenced, First up, Tim R asked Tim C how DNA and genomes relate to the subject of data storage...
Tim C - Your genome is actually data. It is the software which your cells use to build you and run you. In order to understand human disease well, we need to sequence genomes, compare them with what people’s medical state might be, and from that we can determine what mistakes might be in the genome which lead to a particular disorder. That’s what the Sanger Institute does.
Tim R - When you say sequencing, that’s reading and understanding this software that is written in our genome?
Tim C - Right. And the technology that’s being used to do that has become enormously faster, very quickly. The original human genome project took around ten years and cost a billion dollars. It was a massive international project. The Sanger Institute now has the capability of sequencing about 61 whole human genomes a day.
Tim R - That’s a lot of software to get through!
Tim C - It is an awful lot of software for us to get through.
Tim R - If you have ever tried to read software, it’s actually quite difficult unless someone’s very nicely written next to it what all the lines of code mean. But with DNA there isn’t notes written next to each line of code so how do you go about understanding what’s written in the DNA?
Tim C - The first thing we have to do is gather a lot of samples because, if we only have one and we compare with what your medical condition might be, we will find that there are lots of places where you are different from someone else. But we don’t know which of those changes actually causes your issue so we have to do it lots of times for many people, and then we get an idea of well, we’ve seen that one before, now we know where we’re going. So that’s where the scale comes from, we have to compare a lot of these things in order to find an answer.
Tim R - What are the challenges in that? There’s a lot of information in a genome and you’ve got a lot of genomes.
Tim C - The first one is that the genome is quite large - it’s about 3 billion letters long. And we also have to sequence it multiple times in order to get a good sense of what each genome looks like, so we end up with about 50 gigabytes of data for each genome.
Tim R - Wow! That’s a lot of information.
Tim C - Then you’re doing 60 of those a day and that starts to build up into quite a large dataset.
Tim R - With that dataset, what do you do? I mean, that’s not just humans reading each line and hoping to find a pattern, how do extract any sort of meaning from that?
Tim C - As we were hearing earlier, we also have a supercomputer to do it. We have to do very similar sorts of calculations. We’re quite lucky, our calculations are mostly that each individual processor can run on a separate problem at the same time - a so-called embarrassingly parallel problem. But that’s essentially what we do and those things are running, just as we heard earlier. We have programmers whose job it is write the code to do that analysis.
Tim R - If you were able to understand it all, what would that tell us about being human or what would that be useful for?
Tim C - The big goal for us at the moment really is to design better precision medicine. That’s where we would really like to get to. So if I can find out how you differ from another person I can then say right, you need a particular kind of medicine. That one won’t work for you but that one will and that’s where we’re really trying to get to at the moment.
Tim R - What do you need to get to that?
Tim C - We need a very very large amount of storage. We currently have 50 petabytes - a petabyte is a thousand terabytes. Many of you will have a roughly a 1 terabyte hard disk in your PC at home, so that’s where the 50,000 home PCs comes from. The systems that we’re using have to be extremely fast. Hard disks are actually quite slow; they can only read data at about 100 megabytes a second. So feeding a supercomputer with data at the right speed also requires, not just for the capacity reasons, but you need to use an awful lot of disks just to get the data into the processors. They’re very hungry and they’re very quick.
Tim R - Tim, the Sanger was a forerunner to much of this big data processing. What problems did you run into?
Tim C - We quite rapidly discovered that we were trying to do things at a scale that the equipment that we were buying wasn’t really designed for. So we had to work very closely with the vendors to improve both their hardware and their software to do what we needed it to do.
Tim R - What sort of things did you need it to do? Solving those problems - were they very technical or did it turn out to be useful later on as well?
Tim C - A lot of them became widespread solutions, particularly the software solutions. For example, when you’re dividing up the work to run on the large supercomputer, that works a bit like a post office queue - “the cashier number one please”. The machine says I’m ready for work and you give it work. But we found that we were giving it so many tasks to do that it just couldn’t cope with the number we were giving it. So we worked very closely with that particular company and they improved the software and that’s in use in supercomputing centres all over the world.
32:57 - Building a PC - images on the screen
Building a PC - images on the screen
with Nick Batterham - Cambridge University
Naked Scientist Katie Haylor took up the challenge of building a desktop PC with the help of Nick Batterham from Cambridge University's Department of Computer Science and Technology. Step 4 - graphics...
Nick - The trend over the last few years has been to integrate things like graphics into the processor themselves. Processors have become far more than just processors. Lots of things like memory management and graphics that were traditionally done on the motherboard have now been integrated into the processor itself. It’s what people like to call “system on chip.”
Katie - If we were going to put a graphics card in, is this what you’re holding right now?
Nick - That’s right. This is a very basic graphics card.
Katie - It’s a black rectangle with a whole load of...
Nick - This is the heat sink.
Kate - Oh, I wondered what that was a heat sink?
Nick - This is just another heat sink just like the one on the processor. Underneath that would be buried the GPU - the graphics processor unit.
Kate - The heat sink is a load of plastic, metal, a kind of grid?
Nick - Aluminium.
Kate - An aluminium grid and the GPU is hidden inside?
Nick - Yeah, underneath.
Katie - Does it need to go in?
Nick - It can.
Katie - Yeah, let’s do it.
Nick - This part is easy, it just pushes in.
34:18 - How do computer graphics work?
How do computer graphics work?
with Professor Alan Blackwell - Cambridge University
Whether you’re playing games, watching films or simply doing work - how does the computer generate the images you see on screen? Chris Smith spoke to Alan Blackwell from Cambridge University, asking him firstly to cast his mind back to the early days of computer graphics...
Alan - The early computers mostly were calculating equations and they were outputting numbers as text, and mostly they had something like a typewriter connected to them. The text that they were outputting, mechanical hammers would be going up and down just like on a typewriter. And when I started working on computers, if I made a mistake in my programme and wanted to run it again, roles of paper would be rolling out and filling up the office while I worked. So there was a huge saving when the text started to come out on the screen which we called a “glass teletype,” because it didn’t have paper coming out of it.
Chris - Is that why it was called graphics because it’s graphos writing and was literally generating paper output?
Alan - Well yes, although certainly for a long time we talked about text and graphics being different. Graphics was pictures and it was very unusual in the 1960s and 70s to ever see a picture coming out of a computer. If you did, it would be made out of typewriter characters that made up the dots of somebody’s face.
Chris - Who made the leap then to a screen from bits of paper?
Alan - The first person to do that was Ivan Sutherland who, in 1963 at MIT, used displays that previously were being used in the Cold War as radar screens to possibly show incoming missiles. Ivan Sutherland had the idea of drawing directly onto the screen of the computer. The ideas that he came up with in order to do that required a huge amount of hardware because we needed to think about where all the individual lines were going, where the individual pixels were going.
Those sorts of graphics didn’t really become available in your home really until the Apple Macintosh or the II were created, the point at which you had one location and memory for every pixel on the screen. Finally you could start putting a picture together pixel by pixel in a bitmap display.
Chris - In two colours because those computers were green weren’t they?
Alan - They did. The Apple Macintosh, yes, every pixel was either on or off because they could only afford to use one bit of memory for each of those thousands of pixels. If you think of the megapixels, that’s what your camera or your phone would use to take a photograph nowadays, we didn’t have enough memory in the computer to store that many. If you wanted to be not just black and white, but to have different amounts of red, green, and blue for each pixel, you needed three bytes for every pixel.
Chris - Is that where we’re at now then? Is that still how it’s done when you’re representing an image on the screen is there literally an addressing to each pixel, so it knows where it is and it’s got a different colour signature for every pixel?
Alan - That’s right. Effectively, every frame of the picture you see on your computer screen, the computer is making up a red picture, a blue picture, and a green picture and then it’s merging them all together at the same time and putting them together so that you get the impression that you’re seeing colours.
Chris - But there are various cheats and sneaky things that clever people like you can resort to to make it so that it’s not so laborious for the computer, isn’t it? There are sort of ways of compressing images so that you actually save space, save memory, and do things faster?
Alan - That’s absolutely right. We can display the pixels quite fast but we don’t have enough memory to store them. If you’re watching a digital video film, then you’ll be seeing 50 frames per second and every one of those frames has got millions of pixels in it. There’s no way that we could store, even with our terabyte of data we might have on our home computer, in order to fit the movies that we see in a terabyte they have to be compressed. If there’s large amounts of blue sky in your picture, then the computer can say well, there’s lots of blue pixels, the next one is pretty much the same as the last one so just imagine that everything’s the same until I tell you differently. And you can see sometimes when this doesn’t work. For example, if you’re using Skype and you don’t have enough bandwidth to send the picture, you see the pictures start to break up because…
Chris - It looks like shoot minecraft, doesn’t it?
Alan - Exactly. It’s assuming that all those blocks are the same. If it had a little bit more data communication then it would be able to say no, hang on there’s more detail inside of here.
Chris - When they plug in the graphics card or the function is taken over by the processor, it’s doing that sort of compression, it’s doing that addressing of the pixels to the right place on the screen, that’s what’s going on under the hood?
Alan - The graphics card is spending some of its time on compression but most of its time, if you’ve got a really powerful graphics card of the kind that’s used for video games, then it’s spending most of its time calculating the geometry of three-dimensional scenes. It’s trying to say all of these objects that might be in your Minecraft world, for example, or perhaps in your shoot-em-up, if you played Minecraft you will have noticed that things in the far distance it starts filling them and when it’s got a little bit more because it takes a long time to calculate all those three dimensional geometry.
39:24 - What might computers of the future look like?
What might computers of the future look like?
with children from The Perse Prep School, Cambridge
What do young people, so-called "digital natives" - think of computers? Katie Haylor canvassed some the opinions of a few youngsters from The Perse Prep School in Cambridge...
You can watch lots of videos and play on lots of apps.
They can be small, big, medium and massive and even without a screen.
A computer can look like anything. It could be small, it could be big, it could be tiny. It could just be a tiny chip. A computer can be a phone.
A computer is something electronic that has an input, and output, a CPU, and some storage and memory.
Katie - What’s the most common thing you use a computer for?
Katie - I thought you were going to say that. How useful are computers?
Very useful as you can use them for storing photos, they can be used for homework. They are an easy way to convey messages and they are also good for gaming, which I quite enjoy.
They are still pretty useful but sometimes they can be a bit annoying.
I think it’s quite useful because on the internet you can just search it up if you’re stuck on something and you really want to find out. But then, sometimes, the internet can be wrong so you have to be careful.
A computer is only as good as the programmer, so they sometimes have glitches and things like that.
Katie - What do you think computers might look like in the future?
The computer might look like a tiny chip which you can put into your clothes or anywhere on you. And then it’s a hologram so it’s really light and you can carry it around and then it appears in front of you and you can just talk to it and it can look stuff up.
They say there’s going to be face recognition and voice recognition, but I think some computers might go to the virtual side.
Maybe in the very very far future there’ll be no school because you can just download information and insert a chip into your head.
42:05 - Building a PC - will it turn on?
Building a PC - will it turn on?
with Nick Batterham - Cambridge University
Naked Scientist Katie Haylor took on the challenge of building a desktop PC with the help of Nick Batterham from Cambridge University's Department of Computer Science and Technology. Question is, will it actually turn on?
Nick - We’ll plug in the power. And then, of course, we’ll need a keyboard and a mouse.
Katie - Can I do the honours?
Nick - Sure.
Katie - I’ve found the “on” switch. I think I know what to do with this…
Nick - There’s the power switch and then there’s another switch on the front…
Katie - Hey... The monitors just come on. The whirring noise, that’s the disks moving round. And then the clicking noise, those are the arms moving across reading the disk.
So we did it?
Nick - I think so.
Katie - Ta da!
42:57 - How do the Internet and World Wide Web work?
How do the Internet and World Wide Web work?
with Dr Noa Zilberman - Cambridge University
Many of us use the internet everyday, but what actually is it, and how does it work? Tim Revell put this to Noa Zilberman from Cambridge University...
Noa - The internet is a global system that connects all computer networks.
Tim - What does that mean practically? The computer network’s quite abstract but everyone knows how to use the internet at the moment so what are they actually doing when they click on the computer and they access the internet?
Noa - You can think of the internet as the postal delivery service for computers. Let’s say that you have a message that you want to send to someone. You’ve got your application, your software, that is running and is writing this message.
Tim - So this is a bit like email?
Noa - It might be an email, it might be that you are trying to watch some online movie. It might be that you are accessing a website like the Naked Scientists and you want to listen to this podcast, so what you need to do first is to write this message. This message is then handed from your application to the operating system. So, as I mentioned earlier, it might be Windows, it might be Linux, it might be a Mac, it doesn’t matter. But this operating system is the one in charge of taking this message and delivering it the hardware, to the component in your computer that knows how to transmit the message into the network.
Tim - What happens next? Where does the message then go?
Noa - Each computer that is connected to the internet has an IP address - an Internet Protocol address - which is just like your home address, so you have your home address and you have the postcode. If you are trying to access the Naked Scientists website, you know what is the name of the website - you know it’s the Naked Scientists but you don’t know what is the IP address.
To this end, what happens is you need to access a certain service that provides this address to you and it is called DNS - the Domain Name Service. You give it a name and it provides an IP address just like looking up a postcode. You know the address of someone but you don’t know what is the postcode.
In the same manner you get the IP address and the software writes its own message and delivers it to the network. Within the network there are multiple network devices that know how to route the message according to the IP address that is on it.
Tim - This is like I then post my letter through the internet and along the way there are little nodes or, in this analogy, you could match them as people who deliver post. And they then just pass the message onto the next person and, eventually, it gets to the Naked Scientists Website or the person I’m trying to email. Is that about right?
Noa - That’s exactly right. You have your own internet service provider, the one you connect to from home. They take your message and they are the first ones to deliver it to the next network, and the next network, until you get to the last network, the one that might be the BBC network. The BBC knows how to take the message and deliver it to the specific computer.
Tim - So this is how a message from this studio in Cambridge can make it all the way across the world. There’s obviously a big difference between sending a small message, just in terms of the size, and if I’m watching something and streaming something from the BBC website there’s just a huge difference in the amount of data. How do you send such a big package; can the postal delivery system deal with that?
Noa - You simply chop it into smaller messages - that’s it. There is what is called a maximum transmission unit that you can send from a computer into the network.
Tim - Going back to the original internet, how did that differ from today? Nowadays, we can send these massive packages by splitting them up, would we have been able to have sent Game of Thrones through the internet 30/40 years ago when these things were starting off?
Noa - You could have sent it but then you would have waited for ages and ages until it would have arrived. If you are thinking back to the beginning of the internet, which was the “uppernet” in 1969. At the beginning there were only four computers connected to that in UCLA, Stanford, UCSB, and University of Utah. The first message that was sent was just a single word “login.” They sent the letter “l” and everything was fine. They sent the letter “o” and everything was fine. They send the letter “g” and it crashed.
Tim - Well that seems like it wasn’t quite as good then as it is today?
Noa - Yes. The internet today is about 10 thousand times to 100 thousand times faster than the network then and, obviously, more reliable.
Tim - Looking forwards, what can we imagine from the internet in 10, 20 or even 30 years time?
Noa - Thinking about 10, 20 and 30 years time is crazy long in terms of the internet. We can already see new technologies coming in like the Internet of Things (IoT), where almost everything is connected. You already heard probably about your fridge letting you know when you ran out of milk. But you can also see more technological trends such as the integration of computing and storage and networks together. Things that you use to do on the computer are now moving to the network and visa versa. But you can also assume that everything will be much faster, though we can’t be much faster than the speed of light.
48:58 - What is cloud computing?
What is cloud computing?
with Dr Chris Folkerd - UKFast
When talking about computers, the internet, and data storage, we really can’t fail to mention “the cloud”. Storing data out in the ether of the cloud is becoming much more more popular, but what actually is it? Chris Smith spoke to Chris Folkerd from UKFast. First up, Chris S asked Chris F what is meant by "the cloud"...
Chris F - “The cloud,” in its simplest form, is really just a way of utilising someone else's resources on their computers across the internet. Things like “icloud” and “dropbox” enable you to access someone else’s storage on their computers. Some of the more infrastructure based systems where you’re accessing physical servers, cloud computing for example, you’re accessing someone’s web pages, someone’s services across the internet on a big shared pool of resource.
Chris S - Is this more efficient then? Because, basically, what you’ve got running in the cloud are a massive sea of computers, or a cloud of computers all connected together providing processing power and you, for the time you need it, get that chunk of computers to do your job for you, send the results back so that you get what you need, but you haven’t had to invest the energy and the infrastructure in running all of that, you just get the results?
Chris - Yeah, exactly that. The cloud is very beneficial in terms of efficiency because you’re only using it when you need to. So if you’re running a large simulation you don’t have to pay for the infrastructure, you can run the simulation then you’re finished. Businesses find it quite useful because if they’re busy over Christmas, they can immediately start using more resource over the Christmas period and then give that back without paying for any resource that they need.
You also get access to a lot more technologies on the cloud because someone else has already invested in that and you can access that immediately rather than having to go through the process of acquiring it all, working how it all works, and then setting it all up.
Chris S - What are the practicalities then for someone who wants to have a website or something, rather than having a physical computer these days? Could they just have a website that doesn’t really exist apart from in the cloud? It’s just a thing which is there because someone else’s computer is running their website for them?
Chris F - Absolutely! It’s very very common these days, and it’s one of the most common use cases we see at UKFast. You can be as simple as buying a slice of a server for just your website, which works out much cheaper than having the physical infrastructure. And you can just, within a few minutes, go onto a portal and say I’d like space for a website, get access to a control panel, upload your files and off you go. It makes computer provision really quick.
Chris S - Is that what drove this in the first place? Because it seemed to suddenly appear out of nowhere this cloud. There were clear skies and then suddenly everyone’s talking about the cloud. So where did it come from in the first place?
Chris F - It’s got its origins in a couple of technologies that have come around. The internet is the principle one, without that we wouldn’t be able to talk to people’s machines and it’s critical to the way the cloud’s developed. Especially on the computing front, there’s also technology called “virtualisation.” That started emerging in the 90s and it lets you slice up a computer into different chunks. Computers aren't using all of their resources in one go. So, if you can provision that out in small slices, more people can use the same machine and it makes it a lot cheaper.
From there really it just span out; things were cheaper so people could launch websites a lot quicker than having their own infrastructure in place. Then more people came to those websites, more functionality built out from there and, as it does with popular technology, it just scaled from that point onwards.
Chris S - What about security, Chris? Because, if, say I’m running my website in a cloud along side a whole bunch of other people so it’s all sharing one big computer, how do I make sure that my data that’s going through my website, say I’m taking people’s credit card numbers or something, can’t be say stolen by Tim’s website sitting next door to mine in the cloud?
Chris F - It’s one of the biggest questions we get and the honest answer is that there are a lot of security precautions that are put in place. Hosting with the cloud is very very secure because we have the expertise of working with all of these devices all of the time. There’s a lot of very secure barriers that prevent you from accessing other people’s resource, be it compute, storage or networking, and it makes it very difficult for anyone to bridge between those.
Chris S - Can you just, in the last 60 seconds or so Chris, just look over the horizon, to stay with our sky analogy, and tell us what you think the future of this is, where’s it all going?
Chris F - From a consumer perspective it’s the growth of IoT or the cloud services that back that up.
Chris S - This is “internet things” isn’t it?
Chris F - “Internet of things” yes. Will give people a lot more of a tailored service to the devices they’re putting into their home. From a business perspective it’s shortening the time it takes to go to market because you can access all of these services very quickly and they’re called “microservices” - small bits of technology that you can rapidly add into your product portfolio. We’re seeing things being released in months now rather than years, and that will get quicker and quicker until you’re seeing functionality being released in the week or days time frame and really accelerate people’s ability to adopt new technologies.