Brought to you by the reinvented two thousand twelve Camray. It's ready. Are you get in touch with technology? With tech Stuff from how stuff works dot com. Hello again, everyone, and welcome to tech stuff. My name is Chris Polette and I am an editor at how stuff works dot com. Sitting across from me as always a senior writer Jonathan stir Rickland. Wake up in the morning feeling like p didd. I grabbed my glasses. I'm out the door. I'm going to hit this city. I don't want to hit something too. But that's not what I'm thinking about. Yeah, I I despise the source of that. But but at the same time, it was too it was too apropos. I could not pass it up with all the the TikTok related things that you could think of. It was TikTok spoiler. So, guys, we're gonna talk today about a an interesting strategy developed by into l uh in their micro processor micro architecture design work. Right, Yeah, this is this is something that chip heads would you would you call them chip heads people who really care about the processor speed of computers. I call them processor freaks, but with a pH Okay, this is something that they would pay attention to, but probably the general public doesn't know a whole lot about because it's something that goes on somewhat behind the scenes. Although Intel doesn't really make a big secret of of doing it this way. No, No, they've got they've got plenty of information on their own website, completely open to the public that explains this, because I mean, really, it's just it's showing a process, right. It's not giving any proprietary information away, not in the least. It's kind of like saying that you know, a car manufacturing plant uses an assembly line of some sort that that tells you the process or using, but doesn't give you a need detail. True enough, So the uh, it's appropriately named the TikTok strate g because it's sort of like a pendulum. Uh. It moves one way and then the other and then back the other way. Um, but that's not really the pendulum is not really completely a good analogy because it's not just moving back and forth that the process is actually moving forward during this time. Yeah, and we can. Let's let's before we get into the actual details of what TikTok is all about, let's talk about the reason TikTok even needs to exist in the first place, and that would be from Intel's co founder Gordon Moore. Yeah. So, so Gordy, you may remember we've talked about Gordy in the past, and uh, you know somebody from Intel is listening to that. You know. Yeah, we've had we've had some important people email us in the past. Like I'm thinking of Vinton Surf who sent me an email and that just it's hard for me to remember that that important really like people I really legitimately admire and respect and who have had an enormous impact upon in the technology industries. Um, I can hear what I have to say. That just blows my mind because normally I'm just having these conversations in a room and we don't have a microphone in front of me. But anyway, Gordy, uh night. Back in NINETI wrote this paper about cramming more components into a chip. I can't remember. There's something along those lines as the title I'm paraphrasing, but I can. I can look that up for you if you want. You go ahead and look that up while I talk about about this. So we're talking about Moore's law here. So Gordon came up with this observation, and it was an observation. You've got to remember that Moore's law was not some sort of fundamental law of the universe. The observation was that over a certain period of time, and I believe initially it might have been between twelve and eighteen months, it's now closer to twenty four months, but over a certain amount of time, More observed that the number of transistors that one that a company could fit on a single square inch of so con wafer material doubled, so you could fit twice as many transistors on a chip UH within a year or two years um. And that he his observation was that this was a trend that would continue indefinitely until we started to reach some fundamental limits of how small we could make transistors. And at the time, no one was really sure you know how long that would be. And it's the crazy thing is it's held true even today. And you've got to remember, this is an exponential uh pattern, right, I mean it's it's decreasing, the sizes decreasing by half, the number is increasing bye bye, you know, twice as much each time frame, So before too long you get an incredible number of transistors on a silicon chip. The name of the paper. Yeah, And as a matter of fact, Jonathan cited this for his really awesome article on War's Law. Um a couple of years ago. Wow, that that along, are you uh called? It's actually called cramming more components onto integrated circuits. So yeah, that's pretty much right. Yeah, it was pretty close. But you can find that in Electronics. That's the name of the journal. It was April volume thirty eight, number eight. If you want to read it, and it's actually it's not a dry read. You can actually find a link to it on Intel. If you go to Intel and you start looking at Moore's law, there is a link to a PDF of this paper, and I do recommend you read it if you're interested in the original observation. One thing that I thought was really interesting was that Moore was pointing out this isn't just a technological issue. In fact, that was not the main thrust of his paper. It's it's a financial issue because one, you have to find the technology to be able to decrease the size of these transistors, but too you have to make that technology affordable enough to use for it to make sense to use it right if you if you develop the technology to create a up that has UH an incredible number of transistors on it, but it's slow, inefficient, it costs a lot of money to create each chip. You're not you don't have a good business plan because you can't sell those chips to consumers. They would be too expensive. You would never recapture those costs. So you have to be able to one develop the technology and to develop the right procedure so that the technology is efficient and you can actually make money off of it. Speaking of which, um, some people have predicted the demise of Moore's law, of course due to the physical limitations UH for years, but also due to the recent UH financial troubles the world over. People have said, well, you know, there won't be really a need to have faster, faster, faster, faster computers because people can't afford to go by them. So UM, but I haven't really seen it slow down as much as become sort of sort of zag a little bit. And that when and the past years we've had single core processors and you would see a speed a substantial speed boost over the period of a year. Um, you know it would go from one gigga hurts to one point six gigga hurts, and you know then to two point to giga hurts. Well, now we have multi core processors, and they don't seem to move as fast because you know, we're going from uh, you know, three point two to three point six gigga hurts. But then we're also doubling the number of cours on that chip, so they are getting faster. Just doesn't appear to move as fast because of the way it doesn't. At least that's that's my personal observer. Yeah, the the jumps, the jumps, an actual number of cycles per second that a processor is capable of of executing doesn't seem to be jumping at the same rate as it was, you know, ten years ago, right, But the the multi core approach has created a more efficient way to deal with computational problems, and thus ultimately you're computing power has has increased, even though the number of cycles themselves may not have jumped as high as you would have expected. And that's that's part of the whole TikTok philosophy actually, which I guess we can kind of segue into UH. Until really started to adopt this around two thousand seven. Really, was it that long ago? Yeah? Yeah, it was. Um it was right around then when they had started to develop the core technology. That was when the core technology was first starting to be uh UM introduced. And at that time, the the number of the the discreet elements on a chip, we're around the sixty nanometer scale. So we're already talking about on the nano scale, which is yeah, remember a nanometer, And I got a lot of people yelling at me for calling it a nanometer. I'm sorry, I get people yelling at me, no matter what, we're gonna go nanometer this time, and then all the other people can yell at me because I'm sure they were tired of being left out. So a nanometer is one billionth of a meter, so this is incredibly tiny. We're talking about on a scale where even a moat of dust on a silicon wafer will ruin an entire chip because the mode of dust dwarfs the elements that would be printed on that chip. UM. So, sixty five nanometer scale for the core technology, now that was technically a talk that meant that Intel had already developed a chip that could be at sixty five nanometers that would be the size of the transistors essentially on that chip. So the core technology was a new way of arranging those sixty five nanometer transistors in such a way that they were more efficiently used, so that they consumed less power, they had better output, there was a more streamlined flow, so that they were, in a sense an essence, a more powerful chip. Because one thing we also need to remember about Moore's law is today a lot of people in herpret it not as there are twice as many transistors now as there were two years ago, but rather the chip itself is twice as powerful as it was two years ago. This is not exactly the same thing. They're related, but you can get more power out of a chip just by realigning certain elements and making a more efficient workflow. You know, when you start talking about more power, I'm starting to get James doing in the back of my head. I'm giving her all. She's gone. Um so coming to the Jeffreys tubes in your ear. Nice Jeffreys too in your PC, trying to a squeak out that extra Now, if you guys want to know, if you guys want to know more about that, you need to read how warp speed works. We actually have it on the site. Um the so, yeah, the whole basis of tiktalk, right, we have. We've kind of danced around it. But Intel's TikTok strategy is that the TICK is figuring out a way to reduce the size of those transistors, but you bace it upon the previous UH chips micro architecture. All right. So so it's like you've got the plans for a house. Now you're going to build that same house, but you're gonna build it at half that scale. I got it, I got it. So the TALK strategy is finding out the best way to use those smaller components so that it is the most efficient effective transistor arrangement. So in that case, what you do is you look at the plans for that house that you built at half the size of the previous one, and you say, all right, I'm going to rearrange this now so that this house makes sense at this scale. It's I'm not going to change the scale. I'm just going to change the layout of the house. So what you're saying is they they create a blueprint for a chip the next UH and then the next cycle they work on making the components using that blueprint uh more efficient, right, and then and they take the efficiency that they learn on that cycle and build a new architecture on it for the next cycle. And so on one side they're working on making everything more uh you know, reducing the size of it, and the next cycle is all about the actual design of it. Right, So exactly goes size design size design. And this is, by the way, a never ending research process. It's not like you've got people researching how to reduce the size and then they stop, and then they switch to figure out how to make it more efficient. You've got teams working on both of these things simultaneously. And so um, it's interesting. You know we look back and the core technology being the talk at SS Well, the next one was the pen Ryn chip. That was that was the tick. Yeah. Now that one used the same micro architecture as the core processors, but this time they had reduced the size of the elements to the forty five nanometer scale. Now, after Pentrin came one of the chips that I wrote about, Yes, the Haleem, yes Nehalem microprocessor micro architecture. That was the next talk, and the Haleem had introduced a lot of interesting features like multi threading and and uh arranging memory in such a way so that it would uh that the various cores could share memory certain parts of memory very quickly to make it more efficient. That's what we were talking about here. They're actually rearranging the elements that are on the microprocessor chip in such a way that that the data flow is faster just because it makes more sense, right, And it doesn't necessarily it's it's it's an arrangement that would not have necessarily worked at the larger scale because you could not physically find that same configuration with the elements being larger. They had to be that size for you to be able to kind of shift them around. It's almost like one of those puzzles where you have one piece missing and you have to slow the other pieces around until you make the right picture. It's kind of like that. You know you've got you've got this certain amount of space that you are allowed to use, and you have elements of a certain size, and you have to find the right way to fit all those elements together so that it's the most efficient possible. Well, with the larger ones, you just don't have as many configurations. You don't have as much freedom because the elements themselves are bigger. You don't, you can't, you know, there's only so many configurations you can use. So after Nehalem came Westmere, and Westmere was another tick. So it was using the same micro architecture as Nehalem. But now we have gone down to the thirty two nanometer size, right, And here's where another challenge comes in, because when you get down to this size, this this nanometer scale, you're starting to encounter some pretty funky quantum physics problems, quantum mechanics problems. You're talking about electron tunneling. That would problem, that would be a big one. Yeah, because I mean, of course, and we've talked about electron tunneling before as well, so long time listeners will know what we're talking about here. Electrons have this wacky little way of apparently defying the laws of physics as we understand them. Uh. Actually it's not entirely true quantum physics. It makes perfect sense. Classic physics, it makes no sense at all. So on my scale where I you know, if I drop something, it falls and then it hits something and it stops. That makes sense to me, Right, that's the world I grew up in. If I were to drop something and it would pass through the floor beneath me without making a hole and then continue to go down, I'd say, huh, that's strange. But on the quantum world, not so much. Those wacky electrons Tuesdays at eight. Yes, so electrons, if if a barrier is thin enough, and we're talking about a couple of nanometers wide or thick, I should say if if if it's thin enough and electron can tunnel through, and that it passes through that barrier as if the barrier we're not there. It doesn't make a hole. And in a way, it almost is like it's on one side of the barrier at one moment and on the other side of the barrier the next um. But that's one of the problems. And then what Intel has found is they found that by using different materials, by by switching their transistory gates to other kinds of elements, that they were more resistant to electron tunneling. And you don't want electron tunneling, by the way, because leaking electrons means that transistor is pretty much useless. Transistors are all about governing the flow of electrons and if you can't stop them, then the transistor is always open essentially. Sorry. I think two on semiconductors, which we've discussed in the past. Two because semiconductors are uh you know, essential to running pretty much all kinds of electronics, including computers, um and it's all about controlling using certain materials to control the flow of electron So you knew, in order to have a computer processor to function as it needs to, it also it needs to be able to control when and where the electrons and the uh inside the actual transistors are going. Yes, So I mean that's it's it's crucial. And if you start having electrons going willy nilly and put it, your processor is just gonna have errors. It's not going to be able to compute things because it can't. You know, the data that's working from the operations that's performing are all going to be affected by that electron leakage. So you have to find a way to reduce that and Intel has been doing that by experimenting with different materials. So we left off at Westmere, which was the tick we talked about going down to thirty tick we talked about. It was the tick we talked about right and the next one you actually wrote about yourself again. Yeah, it turns out I write a lot about the talks. I haven't written about the ticks. But the next talk is, of course, as a time we're recording this podcast, the most recent Intel processor the sandy Bridge processor, and sandy Bridge is again it's at that thirty two nanometer scale, because remember it's going to be on the same scale as the Tick before it, but it's got a different layout. It's no longer based on the new halam Mark micro architecture. It's got its own micro architecture, which includes a section on the chip specifically dedicated to graphics processing, which that was the big thing that set it apart from its predecessors. It also has a very small bowling alley. Alright, I don't even know where you're going with that joke. I'm just gonna I was just imagining I was going with your metaphor earlier in thinking about the building. You know, it's got its own graphics processor and a bowling alley. Okay, I'm gonna I'm gonna call that on a gutter ball right now. Yes, the sandy Bridge micro architecture is is brand new as of the time we're recording this. Yes, so new that there are problems with other chips associated with sandy Bridge, not sandy Bridge itself, we should point out, but we can talk a little bit about that. It's only it's only vaguely related to what we're chatting about in this in this podcast. So the neat thing about the graphics processing, of course, is that this means that if you have a computer with a sandy Bridge processor, especially if you have one of the faster ones, because they'd come in different flavors. You know, there's some that can have there's some that have two cores and can run up to four threads of data. And then there it goes all the way up to I think four cores that can run eight threads of data. Um, it may even go higher than that. I have to look it up again. But the the you know, you get one of the faster ones and you get this graphics processing built onto the chip, it means that you may not need a dedicated graphics processing unit to add to your computer in order to play some of the more advanced video games or to do things like video editing. Um, you you might not need more additional power because you've got everything you need on that one micro chip, which is pretty fascinating. I mean, that chip is tiny, and to think that it does the the equivalent of a dedicated graphics processing card is a phenomenal. Now, granted, I'm sure there are going to be games out there that if you crank them to the highest setting, you're still gonna want your own graphics processing card because it's not it's not able to you know, take over the entire load. I had a feeling when you said that that someone will write in to to tell you that that, uh, you know, that is not the case that you're if you're going to be running a high frame rate first person shooter or you know, something with a lot of detailed games like that, uh, that you're not going to want that. And yes, we're we're aware of that. Yeah. But if you're playing you know, Crush the Castle, yeah, uh well, and and it's funny too. I was thinking about the most recent release of the Mac os ten, which as at this point was snow Leppard and uses the Grand Central technology, which sort of coopts your graphics processor if it if it isn't busy with something. Uh. So it seems like the uh operating system manufacturers and the chip manufacturers are both sort of aware, you know what, we could probably be using you know, one chip to do multiple things, and if you have multiple chips, you can have them sort of you know, pinch hit when required in other areas. So it seems to make the architecture more computer itself architecture, not the the chip architecture more flexible because that way, say you have a Sandy Bridge chip which has the onboard ability to graphics process or process graphics. Sorry. Uh, and you have a GPU as well, it seems that that you would have a lot of ability for your computer to use those computing cycles, you know, in both if it's if the operating system is capable of handling or you know, routing those instructions to different places like that. Yeah, and you've got some GPU manufacturers that are looking into doing CPUs now. So you know, while we're seeing Intel kind of push its way into the graphics processing unit world just by incorporating it into the chips, we're seeing the opposite from the graphics processing world as well. So uh yeah, there's a lot of competition in this space, and that's one of the things. As you make these elements smaller and smaller, you can you can really diversify what they can do. So let's let's look a little bit into the future, all right and look at some of the chips will be coming out over the next few years. So following sandy Bridge will be ivy Bridge, which of course will be another tick. So we're talking about a reduction in size. This chip is going to have elements on the twenty two nanometer scale. That's tiny. This is we're really getting the point where my mind's being blown. Keep in mind that the nanometer scale is approximate. It's about, you know, ten times the size of the atomic scale. So when you get to one nanometer, that's about the size of this is. This is oversimplifying, but ten atoms next to each other. So yeah, so this is a twenty two nanometer scale chip. Uh, and it's built. It will be built on the sandy Bridge micro architecture, so it follows the same plan. But after Ivy Bridge, what what happens, Well, then we're going to get has Well should be the talk. So that's gonna be new micro architecture based on this twenty two nanometer scale. And then following has Well, we get rockwell, which is the next tick, and that's going to be at an insanely small sixteen nanometer scale. And I remember thinking that I couldn't imagine them breaking the forty five nanometer barrier. I didn't think that they were going to get down to thirty two. I just didn't think it was gonna be physically possible, knowing what I knew, which granted, was very little about the physical limitations of of the materials they were using. And then you know, it's not just that you know the gates are have to be thick enough or made out of the right material to prevent electron tunneling. It's how do you actually design technology that can create things that's small and make it efficient enough so you can mass produce it, right, I mean, it's not just that it's one thing to figure out a way of making an element so small that it's that tiny. We've seen companies including IBM, use technology to manipulate single atoms and and create pictures with them, including the IBM logo. Right, that's a great one, right where they've used an electron microscope and they use the very tip of it to pull individual atoms and spell out IBM Um, there's a great picture of it online. Just do a Google search and you'll find it. But the you know, the fact that you can do this, that's not me. That doesn't mean that it's efficient or that you could do it on a mask. Lees So it's phenomenal to me. The note did they find the technology to to build things at the scale, but do it in an efficient way where you can actually make chips. I'm just you know, it's it's it's very impressive, and it's I'm just wondering how long Mr Moore's Law will continue to be a law. I mean, they're they're trying their hardness. Yeah, And it's it's funny because you said that people have been predicting the end of Moore's law. People have been predicting the end of Moore's Law since like the eighties. Well, and as you point out in your article, it would have gone by the wayside if they weren't actively trying to make it happen. Now that the companies it's become, it's almost like a self fulfilling prophecy, right, Uh, No one wants to admit that Moore's Law is has reached its end. Everyone wants to be able to keep pushing that innovation. For one thing, it is a motivator to innovate, and we want innovation. If we are we become unmodi vata, demotivated whatever you want to call it, to innovate, then we just stagnate. You know, we're gonna be like, well, we've gotten as far as we can go and that's it. No, No, it's better to sit there and say no, no, there's got to be a better way to make this even faster. Uh. And that way we keep moving forward, we progress, we advance, and um, that's kind of what Moore's laws helped us do. It's really pushed us to innovate so that we can keep up with this observation. And uh yeah, we'll probably reach a day at some point where at least the approach we're using now will no longer be feasible. In order to maintain More's law, we may have to have a complete shift in what it means to to build a computer, right, and may mean that we go through quantum computers which are still unproven, or we may have biological computers that uh that that utilized DNA as a computing technology. You know, once to get a taste at DNA. Yeah, but I do think that until really got onto something when they when they developed the strategy though, because it seems like by concentrating on either the size or the architecture and building around that, it gives them something to a point from which they can start and they can build a new chip without having to necessarily building everything from scratch. I think it probably cuts down I'm saying probably. I don't know. I'm an outsider here, you know, but uh, I would imagine it. It cuts down on the amount of time they have to spend preparing, uh, you know, a design for the new chip, because they have an idea of where they want to start. Um, it cuts down on the possibility of mistakes, which at this point, at this scale, a mistake would be a huge hit to reputation. I mean, yes, Intel is the giant chip manufacturer. They're They're storied in their past. Um, they have been sued for for monopoly. Yeah, they are definitely the dominant player in the market. And we will, I'm sure get someone who wants us to do the A M. D story or we have had people asked us to do A and D. And we will. We just we figured this would you know, when you're talking about micro processors, to not start with until seems ridiculous, just because it is such a huge player in that market. Yes it is. And that's the thing, even at its size. Uh. The the the semi scandal was sandy Bridge um was already starting to have an effect on intelent. You could see in the way that that the company reacted to the problem that it discovered that probably you know, they pulled those chips and stopped making the ones that they were making with that architecture. Yeah, do you want to just really quickly, Yeah, that problem had to do with other processor chips, not the not the actual sandy Bridge chip, but other hips on the motherboard that Intel was shipping out that would support the sandy Bridge chip. And uh, the problem was discovered that over time, uh, and we're talking about a fairly short time frame, the the performance of those chips would degrade fairly rapidly. And that you know, for most people it wouldn't really be a huge deal because most people are not really pushing their machine to its limits. But for the people who were pushing their machines too, as far as they're gonna go, Like the video gamers and the media editors out there, they would potentially notice a decrease in performance much more quickly than you would have anticipate for a typical computer. And so that meant that a lot of manufacturers and a lot of you know, a lot of computer retailers began to hold off on incorporating sandy Bridge motherboards into their systems until this was addressed, until these chips had been fixed and new motherboards were being shipped out. So it was kind of a black eye for Intel, But ultimately it was a problem not with the actual sandy Bridge microprocessor. UM but I'm sorry, go ahead, I'm sorry. I was just gonna say though that that that sort of illustrates my point though that um, this will help I think that this will help Intel cut down on the possibility that there will be um architecture problems with these chips. Because they have a place from which to start, they can go ahead and get moving on it. Obviously, with the roadmap set out years in advance, the company already has an idea of where it's going, so it can be it can be working on the next chip even before this chip is released. Actually, yeah, they're working on like the next three chips. By the time a chip has come out, you can get your it's it's a guarantee that they're working on at least the next two, if not three generations. And that's just impressive that they that the company is is that efficient and programmed out that it knows what it's doing and it can move ahead with confidence. And in case you're curious as to what strategy they used before TikTok, uh, it was that they were concentrating on reducing the size of their transistors every year. So each year they were trying to to double the number of transistors on a chip, but they were only looking at the micro architecture every two to four to sometimes six years, so they were only adjusting the efficiency of the chips, uh, you know, sporadically, while whereas they were reducing the size year over year over year. And that's when they realized that, well, this is not really sustainable if we want to truly stay twice as power, keep a chip twice as powerful two years out. Uh So they readjusted their strategy and that's when they adopted TikTok. So it seems to be working for them. So good job Intel. I'm sure other companies use similar strategies. Uh, this was just one that has actually become fairly famous, at least in the technology world, so we wanted to to tackle it. Oh, that kind of wraps up this discussion about the TikTok strategy. So if you have any questions, or you want to suggest your own topic of favorite topic, if it's A and D, or perhaps it has nothing to do with chips at all. You just want to hear us talk about video game music more, let us know tunes, Yes, you can let us know on Twitter or Facebook are handled. There is text stuff HSW or you can send us an email. That address is tech stuff at how stuff works dot com and Chris and I will talk you again really soon for more on this and thousands of other topics. Is it how stuff works dot com. To learn more about the podcast, click on the podcast icon in the upper right corner of our homepage. The How Stuff Works iPhone app has arrived. Download it today on iTunes, brought to you by the reinvented two thousand twelve camera. It's ready, are you

Brought to you by the reinvented two thousand twelve Camray. It's ready. Are you get in touch with technology? With tech Stuff from how stuff works dot com. Hello again, everyone, and welcome to tech stuff. My name is Chris Polette and I am an editor at how stuff works dot com. Sitting across from me as always a senior writer Jonathan stir Rickland. Wake up in the morning feeling like p didd. I grabbed my glasses. I'm out the door. I'm going to hit this city. I don't want to hit something too. But that's not what I'm thinking about. Yeah, I I despise the source of that. But but at the same time, it was too it was too apropos. I could not pass it up with all the the TikTok related things that you could think of. It was TikTok spoiler. So, guys, we're gonna talk today about a an interesting strategy developed by into l uh in their micro processor micro architecture design work. Right, Yeah, this is this is something that chip heads would you would you call them chip heads people who really care about the processor speed of computers. I call them processor freaks, but with a pH Okay, this is something that they would pay attention to, but probably the general public doesn't know a whole lot about because it's something that goes on somewhat behind the scenes. Although Intel doesn't really make a big secret of of doing it this way. No, No, they've got they've got plenty of information on their own website, completely open to the public that explains this, because I mean, really, it's just it's showing a process, right. It's not giving any proprietary information away, not in the least. It's kind of like saying that you know, a car manufacturing plant uses an assembly line of some sort that that tells you the process or using, but doesn't give you a need detail. True enough, So the uh, it's appropriately named the TikTok strate g because it's sort of like a pendulum. Uh. It moves one way and then the other and then back the other way. Um, but that's not really the pendulum is not really completely a good analogy because it's not just moving back and forth that the process is actually moving forward during this time. Yeah, and we can. Let's let's before we get into the actual details of what TikTok is all about, let's talk about the reason TikTok even needs to exist in the first place, and that would be from Intel's co founder Gordon Moore. Yeah. So, so Gordy, you may remember we've talked about Gordy in the past, and uh, you know somebody from Intel is listening to that. You know. Yeah, we've had we've had some important people email us in the past. Like I'm thinking of Vinton Surf who sent me an email and that just it's hard for me to remember that that important really like people I really legitimately admire and respect and who have had an enormous impact upon in the technology industries. Um, I can hear what I have to say. That just blows my mind because normally I'm just having these conversations in a room and we don't have a microphone in front of me. But anyway, Gordy, uh night. Back in NINETI wrote this paper about cramming more components into a chip. I can't remember. There's something along those lines as the title I'm paraphrasing, but I can. I can look that up for you if you want. You go ahead and look that up while I talk about about this. So we're talking about Moore's law here. So Gordon came up with this observation, and it was an observation. You've got to remember that Moore's law was not some sort of fundamental law of the universe. The observation was that over a certain period of time, and I believe initially it might have been between twelve and eighteen months, it's now closer to twenty four months, but over a certain amount of time, More observed that the number of transistors that one that a company could fit on a single square inch of so con wafer material doubled, so you could fit twice as many transistors on a chip UH within a year or two years um. And that he his observation was that this was a trend that would continue indefinitely until we started to reach some fundamental limits of how small we could make transistors. And at the time, no one was really sure you know how long that would be. And it's the crazy thing is it's held true even today. And you've got to remember, this is an exponential uh pattern, right, I mean it's it's decreasing, the sizes decreasing by half, the number is increasing bye bye, you know, twice as much each time frame, So before too long you get an incredible number of transistors on a silicon chip. The name of the paper. Yeah, And as a matter of fact, Jonathan cited this for his really awesome article on War's Law. Um a couple of years ago. Wow, that that along, are you uh called? It's actually called cramming more components onto integrated circuits. So yeah, that's pretty much right. Yeah, it was pretty close. But you can find that in Electronics. That's the name of the journal. It was April volume thirty eight, number eight. If you want to read it, and it's actually it's not a dry read. You can actually find a link to it on Intel. If you go to Intel and you start looking at Moore's law, there is a link to a PDF of this paper, and I do recommend you read it if you're interested in the original observation. One thing that I thought was really interesting was that Moore was pointing out this isn't just a technological issue. In fact, that was not the main thrust of his paper. It's it's a financial issue because one, you have to find the technology to be able to decrease the size of these transistors, but too you have to make that technology affordable enough to use for it to make sense to use it right if you if you develop the technology to create a up that has UH an incredible number of transistors on it, but it's slow, inefficient, it costs a lot of money to create each chip. You're not you don't have a good business plan because you can't sell those chips to consumers. They would be too expensive. You would never recapture those costs. So you have to be able to one develop the technology and to develop the right procedure so that the technology is efficient and you can actually make money off of it. Speaking of which, um, some people have predicted the demise of Moore's law, of course due to the physical limitations UH for years, but also due to the recent UH financial troubles the world over. People have said, well, you know, there won't be really a need to have faster, faster, faster, faster computers because people can't afford to go by them. So UM, but I haven't really seen it slow down as much as become sort of sort of zag a little bit. And that when and the past years we've had single core processors and you would see a speed a substantial speed boost over the period of a year. Um, you know it would go from one gigga hurts to one point six gigga hurts, and you know then to two point to giga hurts. Well, now we have multi core processors, and they don't seem to move as fast because you know, we're going from uh, you know, three point two to three point six gigga hurts. But then we're also doubling the number of cours on that chip, so they are getting faster. Just doesn't appear to move as fast because of the way it doesn't. At least that's that's my personal observer. Yeah, the the jumps, the jumps, an actual number of cycles per second that a processor is capable of of executing doesn't seem to be jumping at the same rate as it was, you know, ten years ago, right, But the the multi core approach has created a more efficient way to deal with computational problems, and thus ultimately you're computing power has has increased, even though the number of cycles themselves may not have jumped as high as you would have expected. And that's that's part of the whole TikTok philosophy actually, which I guess we can kind of segue into UH. Until really started to adopt this around two thousand seven. Really, was it that long ago? Yeah? Yeah, it was. Um it was right around then when they had started to develop the core technology. That was when the core technology was first starting to be uh UM introduced. And at that time, the the number of the the discreet elements on a chip, we're around the sixty nanometer scale. So we're already talking about on the nano scale, which is yeah, remember a nanometer, And I got a lot of people yelling at me for calling it a nanometer. I'm sorry, I get people yelling at me, no matter what, we're gonna go nanometer this time, and then all the other people can yell at me because I'm sure they were tired of being left out. So a nanometer is one billionth of a meter, so this is incredibly tiny. We're talking about on a scale where even a moat of dust on a silicon wafer will ruin an entire chip because the mode of dust dwarfs the elements that would be printed on that chip. UM. So, sixty five nanometer scale for the core technology, now that was technically a talk that meant that Intel had already developed a chip that could be at sixty five nanometers that would be the size of the transistors essentially on that chip. So the core technology was a new way of arranging those sixty five nanometer transistors in such a way that they were more efficiently used, so that they consumed less power, they had better output, there was a more streamlined flow, so that they were, in a sense an essence, a more powerful chip. Because one thing we also need to remember about Moore's law is today a lot of people in herpret it not as there are twice as many transistors now as there were two years ago, but rather the chip itself is twice as powerful as it was two years ago. This is not exactly the same thing. They're related, but you can get more power out of a chip just by realigning certain elements and making a more efficient workflow. You know, when you start talking about more power, I'm starting to get James doing in the back of my head. I'm giving her all. She's gone. Um so coming to the Jeffreys tubes in your ear. Nice Jeffreys too in your PC, trying to a squeak out that extra Now, if you guys want to know, if you guys want to know more about that, you need to read how warp speed works. We actually have it on the site. Um the so, yeah, the whole basis of tiktalk, right, we have. We've kind of danced around it. But Intel's TikTok strategy is that the TICK is figuring out a way to reduce the size of those transistors, but you bace it upon the previous UH chips micro architecture. All right. So so it's like you've got the plans for a house. Now you're going to build that same house, but you're gonna build it at half that scale. I got it, I got it. So the TALK strategy is finding out the best way to use those smaller components so that it is the most efficient effective transistor arrangement. So in that case, what you do is you look at the plans for that house that you built at half the size of the previous one, and you say, all right, I'm going to rearrange this now so that this house makes sense at this scale. It's I'm not going to change the scale. I'm just going to change the layout of the house. So what you're saying is they they create a blueprint for a chip the next UH and then the next cycle they work on making the components using that blueprint uh more efficient, right, and then and they take the efficiency that they learn on that cycle and build a new architecture on it for the next cycle. And so on one side they're working on making everything more uh you know, reducing the size of it, and the next cycle is all about the actual design of it. Right, So exactly goes size design size design. And this is, by the way, a never ending research process. It's not like you've got people researching how to reduce the size and then they stop, and then they switch to figure out how to make it more efficient. You've got teams working on both of these things simultaneously. And so um, it's interesting. You know we look back and the core technology being the talk at SS Well, the next one was the pen Ryn chip. That was that was the tick. Yeah. Now that one used the same micro architecture as the core processors, but this time they had reduced the size of the elements to the forty five nanometer scale. Now, after Pentrin came one of the chips that I wrote about, Yes, the Haleem, yes Nehalem microprocessor micro architecture. That was the next talk, and the Haleem had introduced a lot of interesting features like multi threading and and uh arranging memory in such a way so that it would uh that the various cores could share memory certain parts of memory very quickly to make it more efficient. That's what we were talking about here. They're actually rearranging the elements that are on the microprocessor chip in such a way that that the data flow is faster just because it makes more sense, right, And it doesn't necessarily it's it's it's an arrangement that would not have necessarily worked at the larger scale because you could not physically find that same configuration with the elements being larger. They had to be that size for you to be able to kind of shift them around. It's almost like one of those puzzles where you have one piece missing and you have to slow the other pieces around until you make the right picture. It's kind of like that. You know you've got you've got this certain amount of space that you are allowed to use, and you have elements of a certain size, and you have to find the right way to fit all those elements together so that it's the most efficient possible. Well, with the larger ones, you just don't have as many configurations. You don't have as much freedom because the elements themselves are bigger. You don't, you can't, you know, there's only so many configurations you can use. So after Nehalem came Westmere, and Westmere was another tick. So it was using the same micro architecture as Nehalem. But now we have gone down to the thirty two nanometer size, right, And here's where another challenge comes in, because when you get down to this size, this this nanometer scale, you're starting to encounter some pretty funky quantum physics problems, quantum mechanics problems. You're talking about electron tunneling. That would problem, that would be a big one. Yeah, because I mean, of course, and we've talked about electron tunneling before as well, so long time listeners will know what we're talking about here. Electrons have this wacky little way of apparently defying the laws of physics as we understand them. Uh. Actually it's not entirely true quantum physics. It makes perfect sense. Classic physics, it makes no sense at all. So on my scale where I you know, if I drop something, it falls and then it hits something and it stops. That makes sense to me, Right, that's the world I grew up in. If I were to drop something and it would pass through the floor beneath me without making a hole and then continue to go down, I'd say, huh, that's strange. But on the quantum world, not so much. Those wacky electrons Tuesdays at eight. Yes, so electrons, if if a barrier is thin enough, and we're talking about a couple of nanometers wide or thick, I should say if if if it's thin enough and electron can tunnel through, and that it passes through that barrier as if the barrier we're not there. It doesn't make a hole. And in a way, it almost is like it's on one side of the barrier at one moment and on the other side of the barrier the next um. But that's one of the problems. And then what Intel has found is they found that by using different materials, by by switching their transistory gates to other kinds of elements, that they were more resistant to electron tunneling. And you don't want electron tunneling, by the way, because leaking electrons means that transistor is pretty much useless. Transistors are all about governing the flow of electrons and if you can't stop them, then the transistor is always open essentially. Sorry. I think two on semiconductors, which we've discussed in the past. Two because semiconductors are uh you know, essential to running pretty much all kinds of electronics, including computers, um and it's all about controlling using certain materials to control the flow of electron So you knew, in order to have a computer processor to function as it needs to, it also it needs to be able to control when and where the electrons and the uh inside the actual transistors are going. Yes, So I mean that's it's it's crucial. And if you start having electrons going willy nilly and put it, your processor is just gonna have errors. It's not going to be able to compute things because it can't. You know, the data that's working from the operations that's performing are all going to be affected by that electron leakage. So you have to find a way to reduce that and Intel has been doing that by experimenting with different materials. So we left off at Westmere, which was the tick we talked about going down to thirty tick we talked about. It was the tick we talked about right and the next one you actually wrote about yourself again. Yeah, it turns out I write a lot about the talks. I haven't written about the ticks. But the next talk is, of course, as a time we're recording this podcast, the most recent Intel processor the sandy Bridge processor, and sandy Bridge is again it's at that thirty two nanometer scale, because remember it's going to be on the same scale as the Tick before it, but it's got a different layout. It's no longer based on the new halam Mark micro architecture. It's got its own micro architecture, which includes a section on the chip specifically dedicated to graphics processing, which that was the big thing that set it apart from its predecessors. It also has a very small bowling alley. Alright, I don't even know where you're going with that joke. I'm just gonna I was just imagining I was going with your metaphor earlier in thinking about the building. You know, it's got its own graphics processor and a bowling alley. Okay, I'm gonna I'm gonna call that on a gutter ball right now. Yes, the sandy Bridge micro architecture is is brand new as of the time we're recording this. Yes, so new that there are problems with other chips associated with sandy Bridge, not sandy Bridge itself, we should point out, but we can talk a little bit about that. It's only it's only vaguely related to what we're chatting about in this in this podcast. So the neat thing about the graphics processing, of course, is that this means that if you have a computer with a sandy Bridge processor, especially if you have one of the faster ones, because they'd come in different flavors. You know, there's some that can have there's some that have two cores and can run up to four threads of data. And then there it goes all the way up to I think four cores that can run eight threads of data. Um, it may even go higher than that. I have to look it up again. But the the you know, you get one of the faster ones and you get this graphics processing built onto the chip, it means that you may not need a dedicated graphics processing unit to add to your computer in order to play some of the more advanced video games or to do things like video editing. Um, you you might not need more additional power because you've got everything you need on that one micro chip, which is pretty fascinating. I mean, that chip is tiny, and to think that it does the the equivalent of a dedicated graphics processing card is a phenomenal. Now, granted, I'm sure there are going to be games out there that if you crank them to the highest setting, you're still gonna want your own graphics processing card because it's not it's not able to you know, take over the entire load. I had a feeling when you said that that someone will write in to to tell you that that, uh, you know, that is not the case that you're if you're going to be running a high frame rate first person shooter or you know, something with a lot of detailed games like that, uh, that you're not going to want that. And yes, we're we're aware of that. Yeah. But if you're playing you know, Crush the Castle, yeah, uh well, and and it's funny too. I was thinking about the most recent release of the Mac os ten, which as at this point was snow Leppard and uses the Grand Central technology, which sort of coopts your graphics processor if it if it isn't busy with something. Uh. So it seems like the uh operating system manufacturers and the chip manufacturers are both sort of aware, you know what, we could probably be using you know, one chip to do multiple things, and if you have multiple chips, you can have them sort of you know, pinch hit when required in other areas. So it seems to make the architecture more computer itself architecture, not the the chip architecture more flexible because that way, say you have a Sandy Bridge chip which has the onboard ability to graphics process or process graphics. Sorry. Uh, and you have a GPU as well, it seems that that you would have a lot of ability for your computer to use those computing cycles, you know, in both if it's if the operating system is capable of handling or you know, routing those instructions to different places like that. Yeah, and you've got some GPU manufacturers that are looking into doing CPUs now. So you know, while we're seeing Intel kind of push its way into the graphics processing unit world just by incorporating it into the chips, we're seeing the opposite from the graphics processing world as well. So uh yeah, there's a lot of competition in this space, and that's one of the things. As you make these elements smaller and smaller, you can you can really diversify what they can do. So let's let's look a little bit into the future, all right and look at some of the chips will be coming out over the next few years. So following sandy Bridge will be ivy Bridge, which of course will be another tick. So we're talking about a reduction in size. This chip is going to have elements on the twenty two nanometer scale. That's tiny. This is we're really getting the point where my mind's being blown. Keep in mind that the nanometer scale is approximate. It's about, you know, ten times the size of the atomic scale. So when you get to one nanometer, that's about the size of this is. This is oversimplifying, but ten atoms next to each other. So yeah, so this is a twenty two nanometer scale chip. Uh, and it's built. It will be built on the sandy Bridge micro architecture, so it follows the same plan. But after Ivy Bridge, what what happens, Well, then we're going to get has Well should be the talk. So that's gonna be new micro architecture based on this twenty two nanometer scale. And then following has Well, we get rockwell, which is the next tick, and that's going to be at an insanely small sixteen nanometer scale. And I remember thinking that I couldn't imagine them breaking the forty five nanometer barrier. I didn't think that they were going to get down to thirty two. I just didn't think it was gonna be physically possible, knowing what I knew, which granted, was very little about the physical limitations of of the materials they were using. And then you know, it's not just that you know the gates are have to be thick enough or made out of the right material to prevent electron tunneling. It's how do you actually design technology that can create things that's small and make it efficient enough so you can mass produce it, right, I mean, it's not just that it's one thing to figure out a way of making an element so small that it's that tiny. We've seen companies including IBM, use technology to manipulate single atoms and and create pictures with them, including the IBM logo. Right, that's a great one, right where they've used an electron microscope and they use the very tip of it to pull individual atoms and spell out IBM Um, there's a great picture of it online. Just do a Google search and you'll find it. But the you know, the fact that you can do this, that's not me. That doesn't mean that it's efficient or that you could do it on a mask. Lees So it's phenomenal to me. The note did they find the technology to to build things at the scale, but do it in an efficient way where you can actually make chips. I'm just you know, it's it's it's very impressive, and it's I'm just wondering how long Mr Moore's Law will continue to be a law. I mean, they're they're trying their hardness. Yeah, And it's it's funny because you said that people have been predicting the end of Moore's law. People have been predicting the end of Moore's Law since like the eighties. Well, and as you point out in your article, it would have gone by the wayside if they weren't actively trying to make it happen. Now that the companies it's become, it's almost like a self fulfilling prophecy, right, Uh, No one wants to admit that Moore's Law is has reached its end. Everyone wants to be able to keep pushing that innovation. For one thing, it is a motivator to innovate, and we want innovation. If we are we become unmodi vata, demotivated whatever you want to call it, to innovate, then we just stagnate. You know, we're gonna be like, well, we've gotten as far as we can go and that's it. No, No, it's better to sit there and say no, no, there's got to be a better way to make this even faster. Uh. And that way we keep moving forward, we progress, we advance, and um, that's kind of what Moore's laws helped us do. It's really pushed us to innovate so that we can keep up with this observation. And uh yeah, we'll probably reach a day at some point where at least the approach we're using now will no longer be feasible. In order to maintain More's law, we may have to have a complete shift in what it means to to build a computer, right, and may mean that we go through quantum computers which are still unproven, or we may have biological computers that uh that that utilized DNA as a computing technology. You know, once to get a taste at DNA. Yeah, but I do think that until really got onto something when they when they developed the strategy though, because it seems like by concentrating on either the size or the architecture and building around that, it gives them something to a point from which they can start and they can build a new chip without having to necessarily building everything from scratch. I think it probably cuts down I'm saying probably. I don't know. I'm an outsider here, you know, but uh, I would imagine it. It cuts down on the amount of time they have to spend preparing, uh, you know, a design for the new chip, because they have an idea of where they want to start. Um, it cuts down on the possibility of mistakes, which at this point, at this scale, a mistake would be a huge hit to reputation. I mean, yes, Intel is the giant chip manufacturer. They're They're storied in their past. Um, they have been sued for for monopoly. Yeah, they are definitely the dominant player in the market. And we will, I'm sure get someone who wants us to do the A M. D story or we have had people asked us to do A and D. And we will. We just we figured this would you know, when you're talking about micro processors, to not start with until seems ridiculous, just because it is such a huge player in that market. Yes it is. And that's the thing, even at its size. Uh. The the the semi scandal was sandy Bridge um was already starting to have an effect on intelent. You could see in the way that that the company reacted to the problem that it discovered that probably you know, they pulled those chips and stopped making the ones that they were making with that architecture. Yeah, do you want to just really quickly, Yeah, that problem had to do with other processor chips, not the not the actual sandy Bridge chip, but other hips on the motherboard that Intel was shipping out that would support the sandy Bridge chip. And uh, the problem was discovered that over time, uh, and we're talking about a fairly short time frame, the the performance of those chips would degrade fairly rapidly. And that you know, for most people it wouldn't really be a huge deal because most people are not really pushing their machine to its limits. But for the people who were pushing their machines too, as far as they're gonna go, Like the video gamers and the media editors out there, they would potentially notice a decrease in performance much more quickly than you would have anticipate for a typical computer. And so that meant that a lot of manufacturers and a lot of you know, a lot of computer retailers began to hold off on incorporating sandy Bridge motherboards into their systems until this was addressed, until these chips had been fixed and new motherboards were being shipped out. So it was kind of a black eye for Intel, But ultimately it was a problem not with the actual sandy Bridge microprocessor. UM but I'm sorry, go ahead, I'm sorry. I was just gonna say though that that that sort of illustrates my point though that um, this will help I think that this will help Intel cut down on the possibility that there will be um architecture problems with these chips. Because they have a place from which to start, they can go ahead and get moving on it. Obviously, with the roadmap set out years in advance, the company already has an idea of where it's going, so it can be it can be working on the next chip even before this chip is released. Actually, yeah, they're working on like the next three chips. By the time a chip has come out, you can get your it's it's a guarantee that they're working on at least the next two, if not three generations. And that's just impressive that they that the company is is that efficient and programmed out that it knows what it's doing and it can move ahead with confidence. And in case you're curious as to what strategy they used before TikTok, uh, it was that they were concentrating on reducing the size of their transistors every year. So each year they were trying to to double the number of transistors on a chip, but they were only looking at the micro architecture every two to four to sometimes six years, so they were only adjusting the efficiency of the chips, uh, you know, sporadically, while whereas they were reducing the size year over year over year. And that's when they realized that, well, this is not really sustainable if we want to truly stay twice as power, keep a chip twice as powerful two years out. Uh So they readjusted their strategy and that's when they adopted TikTok. So it seems to be working for them. So good job Intel. I'm sure other companies use similar strategies. Uh, this was just one that has actually become fairly famous, at least in the technology world, so we wanted to to tackle it. Oh, that kind of wraps up this discussion about the TikTok strategy. So if you have any questions, or you want to suggest your own topic of favorite topic, if it's A and D, or perhaps it has nothing to do with chips at all. You just want to hear us talk about video game music more, let us know tunes, Yes, you can let us know on Twitter or Facebook are handled. There is text stuff HSW or you can send us an email. That address is tech stuff at how stuff works dot com and Chris and I will talk you again really soon for more on this and thousands of other topics. Is it how stuff works dot com. To learn more about the podcast, click on the podcast icon in the upper right corner of our homepage. The How Stuff Works iPhone app has arrived. Download it today on iTunes, brought to you by the reinvented two thousand twelve camera. It's ready, are you