1 00:00:00,280 --> 00:00:02,840 Speaker 1: Brought to you by the reinvented two thousand twelve camera. 2 00:00:03,160 --> 00:00:08,920 Speaker 1: It's ready. Are you get in touch with technology? With 3 00:00:09,000 --> 00:00:17,760 Speaker 1: tech Stuff from how stuff dot com. Hello everyone, and 4 00:00:17,800 --> 00:00:20,040 Speaker 1: welcome to tech stuff. My name is Chris Poulette and 5 00:00:20,040 --> 00:00:22,760 Speaker 1: I'm an editor at how stuff works dot com. Sitting 6 00:00:22,840 --> 00:00:27,760 Speaker 1: across from me is senior writer Jonathan. It was a bright, 7 00:00:27,840 --> 00:00:30,880 Speaker 1: cold day in April and the clocks were striking thirteen. 8 00:00:32,560 --> 00:00:35,600 Speaker 1: Take it. You're not doing songs anymore. No more songs, 9 00:00:35,960 --> 00:00:41,000 Speaker 1: not movies. These are the first lines and novels. So 10 00:00:41,040 --> 00:00:44,239 Speaker 1: if you know what novel that came from, let us know. 11 00:00:44,880 --> 00:00:47,839 Speaker 1: That's a novel idea. It is. Uh. There was a 12 00:00:47,880 --> 00:00:51,120 Speaker 1: second quote I almost used that was not a novel quote, 13 00:00:51,240 --> 00:00:54,760 Speaker 1: but I almost use it, which is sixty k ought 14 00:00:54,760 --> 00:00:59,040 Speaker 1: to be enough for anybody? A. Yeah, and that's uh. 15 00:00:59,080 --> 00:01:02,920 Speaker 1: That apparently is not an accurate quotation, but at least 16 00:01:03,280 --> 00:01:06,320 Speaker 1: he says it's not it's it's us. It's a possibly 17 00:01:06,400 --> 00:01:10,759 Speaker 1: apocryphal quote from Mr Billy Gates. I feel like I've 18 00:01:10,760 --> 00:01:13,200 Speaker 1: heard that name. So today we are but I can't remember, 19 00:01:13,240 --> 00:01:14,920 Speaker 1: which is good because today we're going to be talking 20 00:01:14,920 --> 00:01:19,160 Speaker 1: about memory, computer memory specifically. Yeah, and Uh, we had 21 00:01:19,200 --> 00:01:22,319 Speaker 1: a lot of people request over over the length of 22 00:01:22,319 --> 00:01:24,480 Speaker 1: tech stuff. Really the entire time we've been doing this, 23 00:01:24,520 --> 00:01:25,920 Speaker 1: we have a lot of people ask us to do 24 00:01:26,600 --> 00:01:29,360 Speaker 1: a podcast about RAM and to kind of talk about 25 00:01:29,400 --> 00:01:31,880 Speaker 1: what RAM is, why you need it, and what does 26 00:01:31,920 --> 00:01:34,319 Speaker 1: it do and how does it work? Which is funny 27 00:01:34,360 --> 00:01:36,720 Speaker 1: because we kept not doing it because we thought we 28 00:01:36,720 --> 00:01:39,800 Speaker 1: already had it. Turns out not so much. I did 29 00:01:39,800 --> 00:01:42,640 Speaker 1: a search for the word RAM in our archives and 30 00:01:42,760 --> 00:01:47,760 Speaker 1: UH saw a lot of programs, but not RAM. And 31 00:01:47,920 --> 00:01:50,040 Speaker 1: I even search for memory. And the only memory thing 32 00:01:50,040 --> 00:01:53,080 Speaker 1: we've done is we've talked about hard drives, which hard 33 00:01:53,200 --> 00:01:56,520 Speaker 1: The relationship between hard drives and memory is a close one. 34 00:01:56,560 --> 00:01:59,840 Speaker 1: It's an important one. And Uh. In fact, if we 35 00:02:00,080 --> 00:02:03,120 Speaker 1: did not have RAM, if we if we had not 36 00:02:03,200 --> 00:02:06,360 Speaker 1: developed that, and we were relying solely upon the kind 37 00:02:06,360 --> 00:02:09,080 Speaker 1: of memory that you would find in a typical hard drive, 38 00:02:09,880 --> 00:02:13,639 Speaker 1: you know, the traditional hard drive. Uh, computer operations would 39 00:02:13,680 --> 00:02:17,120 Speaker 1: take much longer than what we're accustomed to. Yeah. As 40 00:02:17,160 --> 00:02:19,080 Speaker 1: a matter of fact, I can, I can actually deliver 41 00:02:19,200 --> 00:02:23,520 Speaker 1: a personal commentary on that because my very first machine 42 00:02:23,600 --> 00:02:26,560 Speaker 1: was an Amiga one thousand. Uh. Many people have known 43 00:02:26,600 --> 00:02:29,560 Speaker 1: because I mentioned it several times in the podcast, and 44 00:02:29,919 --> 00:02:32,000 Speaker 1: that first machine that I had didn't have a hard 45 00:02:32,080 --> 00:02:36,440 Speaker 1: drive on it. Um so Commodore's instructions. When you first 46 00:02:36,440 --> 00:02:39,000 Speaker 1: turned the machine on, you would once it it got 47 00:02:39,040 --> 00:02:41,840 Speaker 1: into boot up mode, you would see a copy of 48 00:02:41,880 --> 00:02:45,880 Speaker 1: the Kickstart disc. Kickstart basically loaded the operating system uh 49 00:02:45,960 --> 00:02:50,080 Speaker 1: into RAM, into random access memory, and then once that happened, 50 00:02:50,080 --> 00:02:52,600 Speaker 1: you could launch your workbench, which is the equivalent of 51 00:02:53,639 --> 00:02:56,280 Speaker 1: the desktop in what you would see in Windows Lennox 52 00:02:56,560 --> 00:03:00,560 Speaker 1: or the Mac os today. UM So you know without 53 00:03:00,600 --> 00:03:03,040 Speaker 1: that uh you know, when I got my first hard 54 00:03:03,120 --> 00:03:05,840 Speaker 1: drive computer, which was an Amigia three thousand, UM, it 55 00:03:05,919 --> 00:03:08,040 Speaker 1: had a forty megabyte Yeah, you can laugh at that 56 00:03:08,120 --> 00:03:12,919 Speaker 1: hard drive which would automatically load the Kickstart and get 57 00:03:12,960 --> 00:03:16,000 Speaker 1: everything started up for you. So it worked very much 58 00:03:16,040 --> 00:03:19,880 Speaker 1: like our machines do now. But um you know that 59 00:03:19,880 --> 00:03:22,160 Speaker 1: that was That's one of those things that that the 60 00:03:22,160 --> 00:03:24,680 Speaker 1: hard drive takes care of that you didn't that you 61 00:03:24,800 --> 00:03:28,040 Speaker 1: don't have to do, uh now, is load your operating 62 00:03:28,080 --> 00:03:30,160 Speaker 1: system and all that stuff in there. There's also it's 63 00:03:30,160 --> 00:03:32,880 Speaker 1: also important to note the difference between RAM and ROM. 64 00:03:32,919 --> 00:03:36,800 Speaker 1: I would say read only memory or ROM. UM also 65 00:03:36,880 --> 00:03:40,080 Speaker 1: has a lot of that baked into the chips onto 66 00:03:40,080 --> 00:03:42,520 Speaker 1: your computer. There are some things that are already in 67 00:03:42,600 --> 00:03:45,640 Speaker 1: your computer that are part of the UH UM the 68 00:03:45,680 --> 00:03:50,680 Speaker 1: physical hardware. But and and read only memory UH That 69 00:03:50,800 --> 00:03:54,760 Speaker 1: memory is at access sequentially rather than at random, which 70 00:03:54,760 --> 00:03:57,240 Speaker 1: is how random access memory got its name right. And 71 00:03:57,320 --> 00:04:01,040 Speaker 1: read only memory, as the name implies, you can only 72 00:04:01,360 --> 00:04:04,760 Speaker 1: read from that memory. You can't write to it. So, 73 00:04:04,760 --> 00:04:08,400 Speaker 1: in other words, it's unchanging. It is is static. It 74 00:04:08,440 --> 00:04:10,880 Speaker 1: will always be the way it is, unless you were 75 00:04:10,920 --> 00:04:14,240 Speaker 1: to physically remove the chips and replace them with other 76 00:04:14,360 --> 00:04:17,960 Speaker 1: chips or other circuitry. It's always going to be the 77 00:04:18,000 --> 00:04:21,159 Speaker 1: same way. And there's some devices that only have read 78 00:04:21,200 --> 00:04:24,160 Speaker 1: only memory because that's all they require and it's important 79 00:04:24,200 --> 00:04:27,720 Speaker 1: to have. It's UM. It's a very useful type of memory. 80 00:04:27,800 --> 00:04:31,320 Speaker 1: But when you're working on a project, if you only 81 00:04:31,360 --> 00:04:34,040 Speaker 1: had ROM and not RAM, you would have to burn 82 00:04:34,080 --> 00:04:36,119 Speaker 1: a new ROM every time you wanted to save something 83 00:04:36,120 --> 00:04:39,040 Speaker 1: to this it would be a real pain. So, for example, 84 00:04:39,240 --> 00:04:42,559 Speaker 1: if you were to look at uh the good old 85 00:04:42,839 --> 00:04:45,560 Speaker 1: video game console market, especially if you were looking at 86 00:04:45,560 --> 00:04:51,520 Speaker 1: the old cartridge based consoles, the the games, the cartridges 87 00:04:51,600 --> 00:04:55,080 Speaker 1: you have that you would put plug into your console 88 00:04:55,600 --> 00:04:59,400 Speaker 1: had ROMs on them. That was the game itself was 89 00:04:59,440 --> 00:05:03,400 Speaker 1: a ROM. And that's why if you talk about things 90 00:05:03,440 --> 00:05:07,320 Speaker 1: like the main emulator, and I know that's it's kind 91 00:05:07,320 --> 00:05:10,240 Speaker 1: of like saying a t M machine, but the emulator 92 00:05:10,279 --> 00:05:14,200 Speaker 1: for arcade machines UH that you can run on certain computers. 93 00:05:14,880 --> 00:05:20,960 Speaker 1: The emulator's job is to to mimic the circuitry that 94 00:05:21,040 --> 00:05:23,720 Speaker 1: you would find within an arcade machine to run a 95 00:05:23,760 --> 00:05:28,680 Speaker 1: specific ROM or game. So ROMs are used in devices, 96 00:05:29,000 --> 00:05:32,559 Speaker 1: and in some cases are are the only thing within 97 00:05:32,600 --> 00:05:35,719 Speaker 1: that device. There might be some other memory there to 98 00:05:35,760 --> 00:05:37,560 Speaker 1: do things that keep track of a high score. That's 99 00:05:37,560 --> 00:05:41,800 Speaker 1: a little different, but but in general, um, you know, 100 00:05:42,120 --> 00:05:44,640 Speaker 1: there are certain devices that will only have ROM. RAM, however, 101 00:05:44,760 --> 00:05:47,279 Speaker 1: is very important for the way we use computers today. 102 00:05:48,200 --> 00:05:51,359 Speaker 1: Think of RAM as it's a it's a temporary storage 103 00:05:52,080 --> 00:05:55,400 Speaker 1: facility for a computer, right. So it's where you can 104 00:05:55,440 --> 00:06:00,680 Speaker 1: temporarily store instructions and data so that your computer processor 105 00:06:01,040 --> 00:06:03,880 Speaker 1: doesn't have to go hunting through your hard drive system 106 00:06:03,920 --> 00:06:08,960 Speaker 1: in order to find the relevant information to execute a command. Um. 107 00:06:09,040 --> 00:06:11,680 Speaker 1: The way I like to think about this is if 108 00:06:11,680 --> 00:06:15,440 Speaker 1: you're a student, imagine that you have a textbook filled 109 00:06:15,440 --> 00:06:18,920 Speaker 1: with facts will say physics. It's a physics textbook, all right, 110 00:06:19,240 --> 00:06:22,120 Speaker 1: and you've got a test coming up, and you've created 111 00:06:22,720 --> 00:06:26,000 Speaker 1: a crib sheet for you to study from, and the 112 00:06:26,040 --> 00:06:29,040 Speaker 1: crib sheet has bulleted points on it about the major 113 00:06:29,120 --> 00:06:31,480 Speaker 1: things you're going to be covering in your next physics test. 114 00:06:32,160 --> 00:06:33,839 Speaker 1: That crip sheet is kind of like RAM in the 115 00:06:33,880 --> 00:06:36,520 Speaker 1: sense that you can make little notes, you can erase stuff, 116 00:06:36,560 --> 00:06:40,800 Speaker 1: you can replace things, and it has a good instruction 117 00:06:40,920 --> 00:06:43,280 Speaker 1: set for you to work from. Now, occasionally you might 118 00:06:43,360 --> 00:06:45,960 Speaker 1: come across a problem. Let's say you're working on some 119 00:06:46,040 --> 00:06:48,400 Speaker 1: homework that's going to prepare you for this test, and 120 00:06:48,440 --> 00:06:50,400 Speaker 1: you've got your crib sheet in front of you and 121 00:06:50,440 --> 00:06:53,440 Speaker 1: you're working on your homework question, and you realize that 122 00:06:53,640 --> 00:06:56,800 Speaker 1: the information that you need is not on the crib sheet. 123 00:06:56,839 --> 00:06:58,719 Speaker 1: It's just doesn't go that deep. So you have to 124 00:06:58,720 --> 00:07:01,280 Speaker 1: go to the text book to refer to the right 125 00:07:01,360 --> 00:07:03,520 Speaker 1: section to learn the stuff you need in order to 126 00:07:03,520 --> 00:07:06,480 Speaker 1: answer that question. That's kind of like your computer. Your 127 00:07:06,480 --> 00:07:09,279 Speaker 1: CPU is going to refer back to the memory to 128 00:07:09,360 --> 00:07:12,360 Speaker 1: see if the information it needs is there, and if 129 00:07:12,400 --> 00:07:16,880 Speaker 1: it's if the information goes beyond that little memory, if 130 00:07:16,920 --> 00:07:19,320 Speaker 1: it's something that has to actually access the hard drive, 131 00:07:19,360 --> 00:07:23,120 Speaker 1: it will go to the hard drive, same sort of idea. Yeah, 132 00:07:23,160 --> 00:07:25,840 Speaker 1: and um, I would just like to note that when 133 00:07:25,840 --> 00:07:29,680 Speaker 1: I said that RUM could only be access sequentially, that's wrong. 134 00:07:29,760 --> 00:07:33,040 Speaker 1: I was actually thinking of serial access memory or SAM. 135 00:07:33,720 --> 00:07:36,520 Speaker 1: I apologize for that. Yeah, I haven't had enough coffee 136 00:07:36,560 --> 00:07:39,760 Speaker 1: this morning apparently, But yeah, cereal access memory is uh, 137 00:07:40,160 --> 00:07:43,880 Speaker 1: is another form of memory that's not used nearly as 138 00:07:43,920 --> 00:07:46,840 Speaker 1: often today as it used to be. But back when 139 00:07:46,920 --> 00:07:50,280 Speaker 1: we had tape drives, Um, you know, you used to 140 00:07:50,320 --> 00:07:52,520 Speaker 1: have to go all the way through the tape until 141 00:07:52,560 --> 00:07:54,440 Speaker 1: you got to the part where it had the information 142 00:07:54,440 --> 00:07:57,480 Speaker 1: you needed, letter than accessing it. It's just the same 143 00:07:57,480 --> 00:08:00,360 Speaker 1: as if he's had a cassette tape, right, had an 144 00:08:00,360 --> 00:08:02,320 Speaker 1: old cassette tape with music on it, and you wanted 145 00:08:02,360 --> 00:08:06,000 Speaker 1: to listen to a specific song. You had to fast 146 00:08:06,040 --> 00:08:08,680 Speaker 1: forward or play through the tape until you got to 147 00:08:08,680 --> 00:08:11,200 Speaker 1: the song you wanted, and then you could listen to it. 148 00:08:11,200 --> 00:08:14,080 Speaker 1: You couldn't just jump right to the song. For our 149 00:08:14,160 --> 00:08:17,120 Speaker 1: younger listeners, this might seem like a completely foreign concept, 150 00:08:17,640 --> 00:08:20,240 Speaker 1: but yes, uh, lots of us used to listen to 151 00:08:20,280 --> 00:08:24,200 Speaker 1: cassette tapes and if you were really lucky you had 152 00:08:24,280 --> 00:08:27,400 Speaker 1: like the eight track tapes where your options were even 153 00:08:27,440 --> 00:08:30,840 Speaker 1: more limited in order to navigate to the next song. Yes, 154 00:08:30,880 --> 00:08:33,959 Speaker 1: but ROM doesn't necessarily work that way, so I apologize 155 00:08:34,000 --> 00:08:37,000 Speaker 1: for that. But random access memory there, there's certain there 156 00:08:37,000 --> 00:08:39,160 Speaker 1: are different kinds of it. One of the most common 157 00:08:39,240 --> 00:08:44,120 Speaker 1: is dynamic RAM. Yeah, that's that's probably the most versions 158 00:08:44,280 --> 00:08:49,760 Speaker 1: of that are probably the most common used in computers today. Yeah, 159 00:08:49,800 --> 00:08:52,720 Speaker 1: and uh. And the way that random access memory, dynamic 160 00:08:52,840 --> 00:08:55,880 Speaker 1: random access memory is is arranged is that you can 161 00:08:55,920 --> 00:09:01,600 Speaker 1: imagine a grid, right, and the the columns there are 162 00:09:01,600 --> 00:09:04,800 Speaker 1: columns in their rows, and where these intersect, you have 163 00:09:05,720 --> 00:09:10,280 Speaker 1: memory cells. Now, a memory cell, the most basic memory 164 00:09:10,320 --> 00:09:14,760 Speaker 1: cell is essentially a transistor and a capacitor, and the 165 00:09:14,800 --> 00:09:17,760 Speaker 1: capacitor can hold a charge. If the capacitor is holding 166 00:09:17,760 --> 00:09:20,360 Speaker 1: a charge, the memory cell is registering as a one. 167 00:09:20,760 --> 00:09:23,359 Speaker 1: If the capacitor is not holding a charge, it's registering 168 00:09:23,400 --> 00:09:27,560 Speaker 1: as a zero. The transistor access a switch that allows 169 00:09:28,080 --> 00:09:31,680 Speaker 1: the various things. It allows the computer to be able 170 00:09:31,679 --> 00:09:35,320 Speaker 1: to read those particular cells and also to recharge those cells. 171 00:09:35,320 --> 00:09:39,040 Speaker 1: Because here's the thing about capacitors, they do drain. Yeah, 172 00:09:39,080 --> 00:09:42,240 Speaker 1: they can hold a charge. There they're sort of like 173 00:09:42,320 --> 00:09:46,120 Speaker 1: a battery, though they are not identical, so don't assume 174 00:09:46,160 --> 00:09:49,600 Speaker 1: that that's the same thing, but they're they fulfill similar functions. 175 00:09:49,640 --> 00:09:53,199 Speaker 1: Capacitors usually release their energy in a burst as opposed 176 00:09:53,200 --> 00:09:57,839 Speaker 1: to over a prolonged time. But yeah, the capacitors. The 177 00:09:58,000 --> 00:10:00,040 Speaker 1: the energy drains from the capacitors, so they have to 178 00:10:00,080 --> 00:10:05,600 Speaker 1: be recharged regularly and rapidly in order for them to 179 00:10:05,640 --> 00:10:09,440 Speaker 1: maintain that charge and hold onto what we call a state. Yes, 180 00:10:09,679 --> 00:10:11,880 Speaker 1: the state of that memory cell. So the state is 181 00:10:11,920 --> 00:10:13,760 Speaker 1: either a one or a zero. If it's a one, 182 00:10:14,200 --> 00:10:17,560 Speaker 1: the computer has to continually send energy to that uh 183 00:10:17,720 --> 00:10:20,640 Speaker 1: sell in order for it to maintain a one until 184 00:10:20,679 --> 00:10:22,760 Speaker 1: the memory needs to be written over, in which case 185 00:10:22,760 --> 00:10:24,640 Speaker 1: it might be a one again or it might be 186 00:10:24,679 --> 00:10:26,960 Speaker 1: a zero. It all depends on what the information is. 187 00:10:27,640 --> 00:10:30,000 Speaker 1: And you've got the like I said, you've got columns 188 00:10:30,000 --> 00:10:34,320 Speaker 1: and you've got rows, and uh the way the computer works, 189 00:10:34,400 --> 00:10:37,280 Speaker 1: it has all these different little um components to it 190 00:10:37,360 --> 00:10:42,559 Speaker 1: that will detect what the current state is of all 191 00:10:42,600 --> 00:10:45,200 Speaker 1: those different memory cells in order to be able to 192 00:10:45,720 --> 00:10:48,240 Speaker 1: uh to to pull the right information. And in fact, 193 00:10:48,280 --> 00:10:51,480 Speaker 1: the computer keeps a record of which memory sell it 194 00:10:51,520 --> 00:10:53,320 Speaker 1: needs to go to because you can think of the 195 00:10:53,360 --> 00:10:56,920 Speaker 1: intersection of that column in that row as an address. Yeah, 196 00:10:56,920 --> 00:11:00,400 Speaker 1: if you think about it as a piece of graph paper, Yeah, 197 00:11:00,600 --> 00:11:04,160 Speaker 1: kind of the computer just basically keeps track of, uh, 198 00:11:04,240 --> 00:11:07,559 Speaker 1: you know, where each item is in that memory. Yeah. 199 00:11:07,600 --> 00:11:11,000 Speaker 1: If you think of the columns is like things like A, B, C, D, E, F. No, 200 00:11:11,320 --> 00:11:13,080 Speaker 1: sort of like think of it kind of like a 201 00:11:13,120 --> 00:11:15,719 Speaker 1: game of battleship. That's exactly what I was thinking. Yeah, 202 00:11:15,720 --> 00:11:17,600 Speaker 1: you got that. You've got the columns that are maybe 203 00:11:17,640 --> 00:11:20,920 Speaker 1: A through Z, and then you have one through twenty 204 00:11:21,000 --> 00:11:23,439 Speaker 1: six as the rose, and you want to look at 205 00:11:23,920 --> 00:11:26,840 Speaker 1: A four. Well, then you know exactly where to go 206 00:11:27,480 --> 00:11:29,640 Speaker 1: to to pull up that information. You don't have to 207 00:11:29,679 --> 00:11:32,160 Speaker 1: you don't have to go through the entire sequence of 208 00:11:32,320 --> 00:11:34,920 Speaker 1: memory cells in order to get at that information. That's 209 00:11:35,080 --> 00:11:37,640 Speaker 1: a very simplistic way of saying what is happening with 210 00:11:37,679 --> 00:11:42,440 Speaker 1: this dynamic random access memory. One of the disadvantages here, though, 211 00:11:42,559 --> 00:11:47,319 Speaker 1: is that having to refresh that memory constantly means that 212 00:11:47,440 --> 00:11:53,480 Speaker 1: you're essentially slowing down the memory um, which is you know, 213 00:11:54,320 --> 00:11:56,600 Speaker 1: a problem. It's it's something that that requires a lot 214 00:11:56,600 --> 00:12:00,400 Speaker 1: of energy. It requires, uh that you're constant, constantly refreshing 215 00:12:00,400 --> 00:12:03,720 Speaker 1: it and slows down your memory. Now, UM, having more 216 00:12:03,760 --> 00:12:07,200 Speaker 1: memory in your computer is a good thing. UM. You 217 00:12:07,200 --> 00:12:09,440 Speaker 1: know remember when we talked about thirty two bit and 218 00:12:09,520 --> 00:12:13,840 Speaker 1: sixty four bit systems. Um. You know, your your operating 219 00:12:13,840 --> 00:12:17,000 Speaker 1: system and your computer, depending on how they work together, 220 00:12:17,120 --> 00:12:23,079 Speaker 1: can address a certain amount of computer memory. UM. And 221 00:12:23,280 --> 00:12:26,319 Speaker 1: uh you know with if you have if you are 222 00:12:26,360 --> 00:12:30,640 Speaker 1: not taking advantage of the maximum capacity of memory or 223 00:12:30,679 --> 00:12:34,400 Speaker 1: at least you know, as much as your computer can hold. UM, 224 00:12:34,520 --> 00:12:38,240 Speaker 1: not only is it having to uh fit whatever programs 225 00:12:38,240 --> 00:12:41,040 Speaker 1: you're trying to run on top of the operating system 226 00:12:41,080 --> 00:12:44,720 Speaker 1: in that amount of memory, it's also dealing with uh 227 00:12:44,800 --> 00:12:47,120 Speaker 1: constantly having to refresh that memory. So it can really 228 00:12:47,120 --> 00:12:51,160 Speaker 1: slow your computer down. Going back to the grid really quickly. 229 00:12:51,800 --> 00:12:56,280 Speaker 1: The the columns along this grid are called bit lines, 230 00:12:57,040 --> 00:13:00,360 Speaker 1: the rows are called word lines, and then a the 231 00:13:00,400 --> 00:13:04,760 Speaker 1: intersection is the memory cell address. So uh, the what 232 00:13:05,000 --> 00:13:07,520 Speaker 1: when you are wanting when you want to write information 233 00:13:07,600 --> 00:13:10,000 Speaker 1: or when your computer needs to write information to your 234 00:13:10,120 --> 00:13:12,040 Speaker 1: RAM in order for the CPU to be able to 235 00:13:12,040 --> 00:13:16,400 Speaker 1: have access to it to make things run smoothly. First 236 00:13:17,160 --> 00:13:22,240 Speaker 1: it starts sending electricity through the column area, so through 237 00:13:22,280 --> 00:13:28,640 Speaker 1: the bitline um individual bitline, and then the computer sends 238 00:13:29,360 --> 00:13:34,600 Speaker 1: electricity through the appropriate wordlines the right rose. So let's 239 00:13:34,600 --> 00:13:37,359 Speaker 1: say that you you know that you're you're you're activating 240 00:13:37,440 --> 00:13:41,319 Speaker 1: column D that's the one that's being um that electricity 241 00:13:41,360 --> 00:13:46,160 Speaker 1: is running through right now. And you know that Rose five, twelve, 242 00:13:46,880 --> 00:13:50,319 Speaker 1: and twenty three need to have need to be activated 243 00:13:50,360 --> 00:13:54,240 Speaker 1: because those memories, the memory cells at those addresses at 244 00:13:54,280 --> 00:13:58,040 Speaker 1: the intersection of column d uh need to be active 245 00:13:58,080 --> 00:14:00,800 Speaker 1: in order for the information to be there. The computer 246 00:14:00,840 --> 00:14:05,280 Speaker 1: sends this information, the transistor allows the capacity turns to 247 00:14:05,480 --> 00:14:09,920 Speaker 1: take on that that charge, and then there's a little 248 00:14:10,440 --> 00:14:15,960 Speaker 1: um sensor actually since amplifier as well, that receives the 249 00:14:16,000 --> 00:14:20,680 Speaker 1: signal that says this capacitor has has a state of one, 250 00:14:21,240 --> 00:14:23,560 Speaker 1: and that's what allows the computer no, you know if 251 00:14:23,600 --> 00:14:25,920 Speaker 1: it's a one or zero, and collectively all those ones 252 00:14:25,960 --> 00:14:29,560 Speaker 1: and zeros give it the information it needs. Now, all 253 00:14:29,640 --> 00:14:32,640 Speaker 1: of this happens in a manner of a few nanoseconds, 254 00:14:33,160 --> 00:14:36,640 Speaker 1: So don't think like this is taking ages. It's it's 255 00:14:36,760 --> 00:14:40,400 Speaker 1: it's billions of a second for this stuff. When I'd 256 00:14:40,400 --> 00:14:43,600 Speaker 1: say slow, I would put that in quote it right slow, 257 00:14:43,760 --> 00:14:47,200 Speaker 1: like the way we feel when we put something in 258 00:14:47,240 --> 00:14:49,920 Speaker 1: the microwave for a minute and we're thinking, why isn't 259 00:14:49,960 --> 00:14:54,880 Speaker 1: it done yet? That kind of slow. Yes, it's not slow, 260 00:14:54,920 --> 00:14:56,880 Speaker 1: as in, you put something in the oven and four 261 00:14:56,960 --> 00:15:02,440 Speaker 1: days later you've got turkey. Uh the I put an 262 00:15:02,440 --> 00:15:04,920 Speaker 1: old boot in there. There's a turkey. That's the way 263 00:15:04,960 --> 00:15:08,600 Speaker 1: it worked, isn't it. No? Oh, I need to go 264 00:15:08,680 --> 00:15:11,840 Speaker 1: home after this podcast. But at least I'll have some 265 00:15:11,880 --> 00:15:15,840 Speaker 1: warm boots. Uh. Yeah. So this this is all taking 266 00:15:15,960 --> 00:15:19,800 Speaker 1: just nanoseconds for each individual transaction, melal seconds for the 267 00:15:19,800 --> 00:15:24,320 Speaker 1: whole thing. So, but it's happening repeatedly until that memory 268 00:15:24,360 --> 00:15:26,520 Speaker 1: is getting rewritten. And it's happening. You know, it's changing 269 00:15:26,640 --> 00:15:30,840 Speaker 1: rapidly because that's the nature of memory. If you're running 270 00:15:30,840 --> 00:15:33,760 Speaker 1: a lot of different applications and uh, your memory might 271 00:15:33,840 --> 00:15:37,760 Speaker 1: be filling up pretty quickly with all this information. That's 272 00:15:37,760 --> 00:15:40,800 Speaker 1: why the more applications you run, if you're if you're 273 00:15:40,880 --> 00:15:43,600 Speaker 1: using an older machine and you're running a lot of 274 00:15:43,640 --> 00:15:47,240 Speaker 1: different applications, you might feel like you're everything's kind of sluggish. 275 00:15:47,760 --> 00:15:50,360 Speaker 1: And that's why people will tell you like, oh, well, 276 00:15:50,360 --> 00:15:53,080 Speaker 1: you need to close some of these applications because it's 277 00:15:53,120 --> 00:15:55,200 Speaker 1: taking up space. In the memory, and the CPU is 278 00:15:55,240 --> 00:15:58,160 Speaker 1: having to work harder to get the information it needs 279 00:15:58,520 --> 00:16:03,000 Speaker 1: to act to execute your hands. So, uh, you know 280 00:16:03,120 --> 00:16:06,040 Speaker 1: that that's how that all plays in. That's why people say, oh, 281 00:16:06,160 --> 00:16:07,640 Speaker 1: if you want a computer to go faster, you need 282 00:16:07,720 --> 00:16:10,360 Speaker 1: more memory, because then you can you can actually run 283 00:16:10,440 --> 00:16:13,280 Speaker 1: more applications. That tends to be a very common problem 284 00:16:13,440 --> 00:16:16,080 Speaker 1: that people run into, right that they're like, my computer 285 00:16:16,160 --> 00:16:18,200 Speaker 1: is so slow, and you look at and you're like, well, 286 00:16:18,240 --> 00:16:21,200 Speaker 1: you've got fifteen applications open, and three of them are 287 00:16:21,200 --> 00:16:24,760 Speaker 1: pretty heavy duty, um, you know, or graphics intensive or whatever, 288 00:16:24,960 --> 00:16:28,600 Speaker 1: something that's going to require a lot of processing. That 289 00:16:28,640 --> 00:16:31,880 Speaker 1: would be why it's both processor speed and the amount 290 00:16:31,920 --> 00:16:34,280 Speaker 1: of memory you have. The two are very much important. 291 00:16:34,560 --> 00:16:38,160 Speaker 1: And also when we talk about Moore's law, More's law 292 00:16:38,200 --> 00:16:43,080 Speaker 1: plays into the into memory as well, because dynamic random 293 00:16:43,080 --> 00:16:45,840 Speaker 1: access memory, the nice thing about it is that, well 294 00:16:45,840 --> 00:16:49,200 Speaker 1: two nice things about is that it's relatively inexpensive and 295 00:16:49,360 --> 00:16:52,440 Speaker 1: it doesn't take up a lot of physical space when 296 00:16:52,440 --> 00:16:56,280 Speaker 1: you're designing memory chips. There are other types of random 297 00:16:56,280 --> 00:16:59,880 Speaker 1: access memory, not just dynamic. Their static random access memory. 298 00:17:00,480 --> 00:17:04,880 Speaker 1: And static random access memory uses uh something a logic 299 00:17:05,400 --> 00:17:08,960 Speaker 1: construction called a flip flop, Yes, not a sandal. I 300 00:17:09,080 --> 00:17:12,439 Speaker 1: was gonna say, you're gonna and it comes out as 301 00:17:12,520 --> 00:17:17,320 Speaker 1: chicken already know that doesn't work well. The static random 302 00:17:17,359 --> 00:17:21,480 Speaker 1: access memory, um, yeah, I mean it one of the 303 00:17:21,520 --> 00:17:24,800 Speaker 1: benefits of eas now flip flops. Actually we uh, you 304 00:17:24,960 --> 00:17:30,240 Speaker 1: go back to the Boolean logic um reference. But basically 305 00:17:30,240 --> 00:17:35,760 Speaker 1: a static RAM has the benefit of being a lot 306 00:17:35,840 --> 00:17:39,600 Speaker 1: faster than dynamic RAM. Well, for one thing, what it does, 307 00:17:39,840 --> 00:17:42,399 Speaker 1: once it has a state, it will hold that state 308 00:17:42,520 --> 00:17:44,520 Speaker 1: until you tell it to change, So it doesn't In 309 00:17:44,520 --> 00:17:47,879 Speaker 1: other words, it doesn't it doesn't require to be recharged, 310 00:17:48,000 --> 00:17:52,080 Speaker 1: doesn't have a capacitor that is leaking energy and has 311 00:17:52,119 --> 00:17:55,800 Speaker 1: to be refilled. So once you once you set a 312 00:17:55,800 --> 00:17:57,880 Speaker 1: flip flop to one, it's gonna stay a one till 313 00:17:57,920 --> 00:18:01,080 Speaker 1: you tell it to be a zero. So that sounds great. 314 00:18:01,119 --> 00:18:04,160 Speaker 1: Why don't we use static RAM instead of dynamic RAM 315 00:18:04,240 --> 00:18:07,600 Speaker 1: for our you know, main RAM and our computers. Two reasons. One, 316 00:18:07,720 --> 00:18:11,200 Speaker 1: it takes up more space, so you end up having 317 00:18:11,359 --> 00:18:14,240 Speaker 1: problems like especially with things like mobile devices or or 318 00:18:14,400 --> 00:18:17,880 Speaker 1: laptop computers. You start running into the problem of while 319 00:18:17,920 --> 00:18:20,000 Speaker 1: you can only fit so much into a form factor 320 00:18:20,040 --> 00:18:23,160 Speaker 1: before he gets clunky, right, right, You need more transistors 321 00:18:23,200 --> 00:18:25,840 Speaker 1: for static RAM. Yeah, yeah, four to six for each 322 00:18:25,840 --> 00:18:29,199 Speaker 1: flip flop. So that's and each flip flop is is 323 00:18:29,240 --> 00:18:34,720 Speaker 1: representing one memory cell. So and granted, these transistors that 324 00:18:34,760 --> 00:18:38,040 Speaker 1: we're talking about are on the nano scale at this point, 325 00:18:38,119 --> 00:18:40,760 Speaker 1: you know, we're talking about tiny, tiny, tiny transistors. But 326 00:18:40,800 --> 00:18:43,159 Speaker 1: even so those add up if you need to have 327 00:18:43,240 --> 00:18:46,440 Speaker 1: the amount of memory that you're accustomed to. So they 328 00:18:46,480 --> 00:18:48,760 Speaker 1: are they take up more space, and they're more much 329 00:18:48,800 --> 00:18:52,480 Speaker 1: more expensive. So static RAM is not something you're gonna 330 00:18:52,520 --> 00:18:56,679 Speaker 1: find in every single kind of device, although as you know, 331 00:18:56,720 --> 00:18:59,399 Speaker 1: as the technology has improved, those prices do tend to 332 00:18:59,440 --> 00:19:01,959 Speaker 1: go down, so we do see more and more of that, 333 00:19:02,040 --> 00:19:04,320 Speaker 1: but dynamic RAM is still probably i would say, the 334 00:19:04,359 --> 00:19:10,280 Speaker 1: most popular by far. Um. There there's another potential change 335 00:19:10,359 --> 00:19:15,359 Speaker 1: coming up, a new development that could really uh impact this, 336 00:19:15,440 --> 00:19:17,880 Speaker 1: which we can get into in a little bit. Okay, Yeah, 337 00:19:17,920 --> 00:19:20,240 Speaker 1: I was gonna mention too though, that that static RAM 338 00:19:20,320 --> 00:19:24,200 Speaker 1: can be found in your computer, probably because um, if 339 00:19:24,240 --> 00:19:28,240 Speaker 1: you've seen a list of computer specifications, perhaps when you're 340 00:19:28,240 --> 00:19:31,000 Speaker 1: shopping for a new machine and you see the cash 341 00:19:31,359 --> 00:19:37,280 Speaker 1: referred to, um, your computer's cash is uh, probably static RAM. Yeah, 342 00:19:37,320 --> 00:19:41,480 Speaker 1: a lot of CPUs have this built in. Uh, A 343 00:19:41,480 --> 00:19:44,240 Speaker 1: lot of the ones that use multi threading, that have 344 00:19:45,160 --> 00:19:48,560 Speaker 1: multi core processors. A lot of these CPUs have their 345 00:19:48,600 --> 00:19:52,600 Speaker 1: own sections of memory built And it's not it's not 346 00:19:52,640 --> 00:19:55,320 Speaker 1: your computer's RAM, it's something that's specifically part of the 347 00:19:55,359 --> 00:20:00,400 Speaker 1: CPU chip set that is there to help make make 348 00:20:00,480 --> 00:20:04,400 Speaker 1: those those data transfers even faster, so that it makes 349 00:20:04,440 --> 00:20:10,840 Speaker 1: it very efficient. And for the the most commonly used commands, uh, 350 00:20:10,960 --> 00:20:15,720 Speaker 1: those would be stored within the cash. So in that 351 00:20:15,800 --> 00:20:19,040 Speaker 1: crib sheet example I gave, let's say that you even 352 00:20:19,080 --> 00:20:21,359 Speaker 1: had a little note card next year, a crib sheet 353 00:20:21,440 --> 00:20:24,760 Speaker 1: that had the four formulas you're going to use them 354 00:20:24,800 --> 00:20:28,720 Speaker 1: most frequently in that physics test, and so you've got 355 00:20:28,760 --> 00:20:31,760 Speaker 1: those there because this way, no matter what you know, 356 00:20:31,800 --> 00:20:33,760 Speaker 1: you just have to glance at the at the note 357 00:20:33,760 --> 00:20:35,960 Speaker 1: card and like, that's that's the formula I need. And 358 00:20:36,000 --> 00:20:38,359 Speaker 1: you plug it in and you make it, you make 359 00:20:38,400 --> 00:20:41,840 Speaker 1: it work and whatever. The problem is. Your CPU is 360 00:20:42,000 --> 00:20:47,040 Speaker 1: really really good at executing operations upon data, but it's 361 00:20:47,119 --> 00:20:49,119 Speaker 1: stupid in the sense that as soon as it's as 362 00:20:49,119 --> 00:20:52,320 Speaker 1: soon as it's finished doing that, it's forgotten. There's no, yeah, 363 00:20:52,359 --> 00:20:55,040 Speaker 1: it has no memory of its own other than this 364 00:20:55,040 --> 00:20:58,560 Speaker 1: this cash that we're talking about. A CPU on its 365 00:20:58,400 --> 00:21:02,800 Speaker 1: the very basic CPU has no memory, so it can 366 00:21:02,920 --> 00:21:05,200 Speaker 1: do stuff, but as soon as the task is done, 367 00:21:05,359 --> 00:21:09,160 Speaker 1: it's like a blank slate all over again. That's that's 368 00:21:09,160 --> 00:21:12,600 Speaker 1: why we have to have memory in order to get 369 00:21:12,600 --> 00:21:15,600 Speaker 1: this to work. If if the CPU could somehow remember 370 00:21:16,200 --> 00:21:19,280 Speaker 1: on its own, then you'd have other issues like, well, 371 00:21:19,320 --> 00:21:21,800 Speaker 1: now you needed to do something new, So how do 372 00:21:21,840 --> 00:21:24,840 Speaker 1: you write over what you had before? Do you just 373 00:21:24,960 --> 00:21:26,840 Speaker 1: add to it? If you add to it, how long 374 00:21:26,880 --> 00:21:29,040 Speaker 1: until you reach capacity? And you can't do anything with 375 00:21:29,040 --> 00:21:31,320 Speaker 1: that CPU other than the stuff that you've already done. 376 00:21:31,960 --> 00:21:34,480 Speaker 1: So you know, this is why the whole idea of 377 00:21:34,480 --> 00:21:37,719 Speaker 1: the random actis memory that could be rewritten very quickly 378 00:21:38,080 --> 00:21:42,280 Speaker 1: was so important, because otherwise you limit the functions that 379 00:21:42,400 --> 00:21:44,840 Speaker 1: your computer is capable of doing. You know, there was 380 00:21:45,200 --> 00:21:48,000 Speaker 1: this computer is great at adding and subtracting and dividing, 381 00:21:48,119 --> 00:21:51,359 Speaker 1: and after that you can't do anything else because that's 382 00:21:52,240 --> 00:21:56,919 Speaker 1: I was about to install Pacman, but darn it, I 383 00:21:57,000 --> 00:22:00,560 Speaker 1: already took up all of its space with these three functions. Well, yeah, 384 00:22:00,600 --> 00:22:03,280 Speaker 1: so you've got uh and and we're we're sort of 385 00:22:04,080 --> 00:22:06,680 Speaker 1: filling out the whole computer. So you've got your your CPU, 386 00:22:06,840 --> 00:22:09,240 Speaker 1: and you've got a CASH to help it remember stuff 387 00:22:09,240 --> 00:22:12,840 Speaker 1: that it needs to do basic operations. And then you've 388 00:22:12,840 --> 00:22:15,680 Speaker 1: got your your memory, your RAM, your dynamic RAM that 389 00:22:15,840 --> 00:22:18,919 Speaker 1: that's over here managing the stuff that you've got going on, 390 00:22:19,040 --> 00:22:24,320 Speaker 1: your your word pressing, your word uh processor uh stuff, 391 00:22:24,359 --> 00:22:27,280 Speaker 1: and your your graphics program, the stuff that you have 392 00:22:28,200 --> 00:22:31,840 Speaker 1: your browser, your your email program. But you also have 393 00:22:32,240 --> 00:22:35,720 Speaker 1: uh in your modern computer, you've got your graphics processor 394 00:22:35,880 --> 00:22:39,080 Speaker 1: chip and in a lot of cases, UM, and I'm 395 00:22:39,160 --> 00:22:41,240 Speaker 1: I'm just hedging my bets here that somebody has some 396 00:22:41,280 --> 00:22:44,560 Speaker 1: weird computer that doesn't have this also has its own 397 00:22:44,680 --> 00:22:49,879 Speaker 1: RAM UM to help it pro specifically process graphics. UM. 398 00:22:50,040 --> 00:22:52,760 Speaker 1: So that RAM in general is off limits to the 399 00:22:52,760 --> 00:22:56,000 Speaker 1: rest of the machine because it's saying no, no, no no. 400 00:22:56,200 --> 00:23:00,280 Speaker 1: This memory is specifically to help us render graphic on 401 00:23:00,320 --> 00:23:04,399 Speaker 1: the screen so that the user can uh see everything 402 00:23:04,560 --> 00:23:08,320 Speaker 1: that he or she wants to see from the other programs. 403 00:23:08,320 --> 00:23:11,159 Speaker 1: So it's not handling programs, it's handling graphics. We have 404 00:23:11,320 --> 00:23:14,560 Speaker 1: we have seen some processors recently that are able to 405 00:23:14,600 --> 00:23:18,320 Speaker 1: tap into the graphics processing units as well. And be 406 00:23:18,400 --> 00:23:24,360 Speaker 1: able to uh to utilize those two process particularly difficult 407 00:23:24,359 --> 00:23:27,840 Speaker 1: problems or powerful, you know, time consuming problems to try 408 00:23:27,880 --> 00:23:31,560 Speaker 1: and reduce the amount of time it takes to get 409 00:23:31,560 --> 00:23:36,000 Speaker 1: through that application. So and in fact, we're seeing we're 410 00:23:36,000 --> 00:23:40,880 Speaker 1: seeing both sides, right. We're seeing UH CPU manufacturers get 411 00:23:40,920 --> 00:23:46,919 Speaker 1: into adding in elements that specifically tackle graphics processing, and 412 00:23:46,960 --> 00:23:53,160 Speaker 1: we've seen graphics processing unit manufacturers get into handling more 413 00:23:53,240 --> 00:23:58,960 Speaker 1: basic processing UH functions. So the two worlds have been 414 00:23:58,960 --> 00:24:02,720 Speaker 1: colliding for probably us well for for quite a quite 415 00:24:02,720 --> 00:24:05,800 Speaker 1: a while, but really visibly for the last two years. Yeah, 416 00:24:05,880 --> 00:24:09,639 Speaker 1: I'm thinking specifically of Apple's Grand Central Technology, one of 417 00:24:09,640 --> 00:24:12,400 Speaker 1: those things in snow Leopard that people didn't really care about, 418 00:24:12,480 --> 00:24:15,959 Speaker 1: but it was actually supposed to improve the operating system, 419 00:24:16,000 --> 00:24:19,040 Speaker 1: but it was mainly thinking of Intel Sandy Bridge, which 420 00:24:19,119 --> 00:24:22,960 Speaker 1: had its own graphics processing element added into it. And 421 00:24:23,000 --> 00:24:26,120 Speaker 1: the thing is that, uh so that so the rule 422 00:24:26,160 --> 00:24:28,159 Speaker 1: that we were just talking about is is going to 423 00:24:28,200 --> 00:24:33,520 Speaker 1: be shifting as time goes on, and UH processor manufacturers 424 00:24:33,520 --> 00:24:37,480 Speaker 1: of all kinds are more sophisticated, the operating systems become 425 00:24:37,480 --> 00:24:41,120 Speaker 1: more sophisticated and able to take advantage of these changes. UM. 426 00:24:41,119 --> 00:24:43,080 Speaker 1: But that's kind of the way it works out. And 427 00:24:43,080 --> 00:24:46,159 Speaker 1: I just wanted to illustrate the fact that RAM can 428 00:24:46,200 --> 00:24:49,360 Speaker 1: be used to support a number of computer functions. You'll 429 00:24:49,359 --> 00:24:52,040 Speaker 1: also see it in you know, all kinds of other 430 00:24:52,080 --> 00:24:58,080 Speaker 1: devices that use memory, cameras, um cars, all kinds of 431 00:24:58,080 --> 00:25:01,639 Speaker 1: technologies that use comput you are processing that you may 432 00:25:01,720 --> 00:25:04,840 Speaker 1: or may not necessarily think of as having computers inside, 433 00:25:04,840 --> 00:25:08,800 Speaker 1: but you know they have some form of RAM in there. Now. 434 00:25:08,840 --> 00:25:13,000 Speaker 1: Of course, RAM has gotten more sophisticated itself over time too. 435 00:25:13,040 --> 00:25:15,320 Speaker 1: And you do you want to talk about some of 436 00:25:15,320 --> 00:25:17,080 Speaker 1: the older types or do you want to talk about 437 00:25:17,119 --> 00:25:21,639 Speaker 1: the improvements you were just about to mention, Well, um, 438 00:25:21,680 --> 00:25:23,840 Speaker 1: I have something leading up into the improvements. If you have, 439 00:25:24,040 --> 00:25:26,720 Speaker 1: if you have information about older types of memory, I'd 440 00:25:27,119 --> 00:25:29,480 Speaker 1: more than happy to hear it. I personally did not 441 00:25:29,880 --> 00:25:32,119 Speaker 1: research that, so I have none of that information in 442 00:25:32,119 --> 00:25:35,080 Speaker 1: front of me. Okay, all right, well, um, I have 443 00:25:35,240 --> 00:25:37,120 Speaker 1: some of it. And and really this could probably get 444 00:25:37,160 --> 00:25:40,399 Speaker 1: kind of dry, um, but basically, you know, as as 445 00:25:40,480 --> 00:25:43,000 Speaker 1: time has gone on, you've been able to see you 446 00:25:43,040 --> 00:25:46,560 Speaker 1: were talking about Moore's law, which of course says that 447 00:25:46,600 --> 00:25:50,639 Speaker 1: the number of transistors on a processor chip will double 448 00:25:50,720 --> 00:25:57,000 Speaker 1: in well, originally it was two years now half or wait, 449 00:25:57,040 --> 00:26:00,520 Speaker 1: I'm sorry, that's backwards. Yeah, it tends to go back 450 00:26:00,560 --> 00:26:03,720 Speaker 1: and forth between twelve months to twenty four months and 451 00:26:03,880 --> 00:26:07,159 Speaker 1: eighteen to twenty four tends to be the most frequently 452 00:26:07,320 --> 00:26:11,560 Speaker 1: cited figures. So depending on any given year, you'll hear, oh, well, 453 00:26:12,280 --> 00:26:14,320 Speaker 1: it's one of the things that the Moore's law gets 454 00:26:14,440 --> 00:26:17,640 Speaker 1: gets validated in retrospect, right, because you have to look 455 00:26:17,720 --> 00:26:20,040 Speaker 1: back two years ago and look and see how many 456 00:26:20,080 --> 00:26:23,680 Speaker 1: transistors were found on a CPU, or like we're staying 457 00:26:23,680 --> 00:26:26,919 Speaker 1: here a memory circuit. That also can apply. If you 458 00:26:26,960 --> 00:26:29,959 Speaker 1: can fit twice as many transistors in the memory circuit, 459 00:26:30,320 --> 00:26:36,360 Speaker 1: then that's another example of Moore's law holding true. M Um, 460 00:26:36,400 --> 00:26:41,240 Speaker 1: but yeah, basically, as far as the memory chips have gone, 461 00:26:41,600 --> 00:26:46,680 Speaker 1: there's been a wave of advances over the last couple 462 00:26:46,680 --> 00:26:50,200 Speaker 1: of decades in which more and more processors are are added. 463 00:26:50,480 --> 00:26:53,399 Speaker 1: The way that their accesses has changed. I remember with 464 00:26:53,480 --> 00:26:56,600 Speaker 1: my Amiga three thousand they used a very unusual type 465 00:26:56,600 --> 00:26:59,199 Speaker 1: of memory called zips, in which the pins that you 466 00:26:59,280 --> 00:27:02,800 Speaker 1: use to plug them in were basically a zig zag. 467 00:27:02,880 --> 00:27:04,240 Speaker 1: There was a pin on one side, then there was 468 00:27:04,280 --> 00:27:05,600 Speaker 1: one on the other side, there was one on the 469 00:27:05,600 --> 00:27:08,160 Speaker 1: other side, you know, and flipped back and forth between them. 470 00:27:08,240 --> 00:27:11,560 Speaker 1: Only a very few computers used that type of technology. UM. 471 00:27:11,600 --> 00:27:15,440 Speaker 1: When I got a Mac, it used sims UM, which 472 00:27:15,480 --> 00:27:18,879 Speaker 1: is a single inline memory module. UM. You can actually 473 00:27:18,880 --> 00:27:21,200 Speaker 1: find quite a bit about the different types of memory 474 00:27:21,240 --> 00:27:24,080 Speaker 1: on We referred to it in our how ram works 475 00:27:24,160 --> 00:27:26,600 Speaker 1: article on how stuff works dot com, but it's on 476 00:27:26,720 --> 00:27:29,840 Speaker 1: Kingston's website and it's UM. You know, it talks about 477 00:27:29,880 --> 00:27:33,320 Speaker 1: the different types. But the single inline modules were an 478 00:27:33,320 --> 00:27:35,760 Speaker 1: improvement over that the older technology, and then they came 479 00:27:35,800 --> 00:27:39,840 Speaker 1: out with a dual inline memory modules UM, and they 480 00:27:39,840 --> 00:27:43,760 Speaker 1: basically it's a little itty bitty card UM. It's long, UM, 481 00:27:43,800 --> 00:27:47,479 Speaker 1: but it has a series of chips soldered into it UM. 482 00:27:47,520 --> 00:27:49,720 Speaker 1: And those are the memory chips, right. And the old 483 00:27:49,840 --> 00:27:54,320 Speaker 1: days you actually had to install a memory chip directly 484 00:27:54,359 --> 00:27:57,080 Speaker 1: into the motherboard. Yeah, this is the This sort of 485 00:27:57,080 --> 00:28:00,359 Speaker 1: predates the more I would say, the nine needs in 486 00:28:00,400 --> 00:28:04,440 Speaker 1: two thousands computers. This is like the old four right, 487 00:28:04,480 --> 00:28:06,439 Speaker 1: So if you want to upgrade your computer, it actually 488 00:28:06,440 --> 00:28:10,680 Speaker 1: meant opening up your computer, disconnecting the motherboard, and then 489 00:28:11,119 --> 00:28:14,560 Speaker 1: possibly UM, depending on how the memory chip was designed, 490 00:28:14,560 --> 00:28:17,000 Speaker 1: you might even have to do some soldering. But but 491 00:28:17,320 --> 00:28:19,680 Speaker 1: you know, install a new memory chip so that your 492 00:28:19,720 --> 00:28:25,640 Speaker 1: computer would have more memory. Eventually, improvements included, uh designing 493 00:28:25,680 --> 00:28:30,680 Speaker 1: something called a memory bank where you had a port 494 00:28:30,880 --> 00:28:34,080 Speaker 1: essentially that you could plug in a card that had 495 00:28:34,520 --> 00:28:37,800 Speaker 1: a certain number of memory chips of a certain capacity, 496 00:28:38,120 --> 00:28:42,960 Speaker 1: and then as technology improved, you could replace that card 497 00:28:43,280 --> 00:28:46,240 Speaker 1: with a card that had a greater capacity. Now, keep 498 00:28:46,240 --> 00:28:50,840 Speaker 1: in mind that your computer CPU would determine how much 499 00:28:50,880 --> 00:28:53,680 Speaker 1: memory your computer could actually use. There would you would 500 00:28:53,680 --> 00:28:56,760 Speaker 1: reach a point where it wouldn't matter if you could 501 00:28:56,800 --> 00:28:59,200 Speaker 1: buy a card with more memory, your CPU wouldn't be 502 00:28:59,240 --> 00:29:02,240 Speaker 1: able to access it. Yeah, it had had limitation on that, 503 00:29:02,360 --> 00:29:05,160 Speaker 1: So there were you know, you that's why if you 504 00:29:05,200 --> 00:29:08,880 Speaker 1: were to look at computer specs and see like, you know, 505 00:29:09,000 --> 00:29:13,000 Speaker 1: upgradeable up to whatever, that's the reason why is that 506 00:29:13,040 --> 00:29:16,640 Speaker 1: the CPU itself has that limitation and so um, you 507 00:29:16,680 --> 00:29:19,520 Speaker 1: know something. You know, in America at least, we have 508 00:29:19,600 --> 00:29:23,800 Speaker 1: this philosophy of more is better. But there's a certain 509 00:29:23,800 --> 00:29:27,320 Speaker 1: point where, depending on the machine you're using, more isn't 510 00:29:27,320 --> 00:29:29,560 Speaker 1: going to do you any good because your computer simply 511 00:29:29,680 --> 00:29:32,760 Speaker 1: cannot use it. Yeah, and that's actually sort of the 512 00:29:32,760 --> 00:29:37,640 Speaker 1: source of Jonathan's earlier quote, UM, I just the idea 513 00:29:37,720 --> 00:29:40,400 Speaker 1: behind it is that you know, there's only so much 514 00:29:40,440 --> 00:29:43,840 Speaker 1: you can use. UM DEM's actually had chips on both 515 00:29:43,840 --> 00:29:47,720 Speaker 1: sides of that UH circuit board, and we're able to 516 00:29:47,840 --> 00:29:52,160 Speaker 1: handle more memory and more quickly. And you know, from 517 00:29:52,200 --> 00:29:56,000 Speaker 1: there we've moved UM move forward. I won't get into 518 00:29:56,080 --> 00:29:59,280 Speaker 1: to all of it, but we really got into the 519 00:29:59,360 --> 00:30:01,720 Speaker 1: more advance it's types of memory in the two thousands 520 00:30:01,760 --> 00:30:08,640 Speaker 1: when we got into UM UH the UM dynamic RAM 521 00:30:08,680 --> 00:30:11,520 Speaker 1: and that that made things a lot more And basically 522 00:30:12,240 --> 00:30:14,600 Speaker 1: what they've done is, over the period of time, made 523 00:30:14,720 --> 00:30:18,800 Speaker 1: the transfer of information more efficient. They've increased the number 524 00:30:18,840 --> 00:30:21,800 Speaker 1: of transistors and the amount of information that could be 525 00:30:21,800 --> 00:30:25,480 Speaker 1: stored on a single UH card with the RAM in it. 526 00:30:26,040 --> 00:30:29,800 Speaker 1: And it's just it's just done. Some made some insignificant 527 00:30:29,800 --> 00:30:34,480 Speaker 1: improvements over the past few years. Right. And and memory 528 00:30:34,560 --> 00:30:38,960 Speaker 1: relies on something called a memory controller. Yes, that's part 529 00:30:39,000 --> 00:30:42,880 Speaker 1: of what maintains like it determines UH when to write 530 00:30:42,920 --> 00:30:45,840 Speaker 1: two memory cells. It also helps read the memory cells. 531 00:30:45,680 --> 00:30:48,520 Speaker 1: It's it's kind of like a manager, right, But it 532 00:30:48,600 --> 00:30:52,760 Speaker 1: also has to check the memory whenever it's getting information 533 00:30:52,800 --> 00:30:55,680 Speaker 1: back from memory, has to check it for errors. And 534 00:30:56,000 --> 00:30:59,680 Speaker 1: depending on what kind of system you're using, you might 535 00:30:59,720 --> 00:31:02,040 Speaker 1: have a memory chip with just with a built in 536 00:31:02,320 --> 00:31:07,840 Speaker 1: error checking technology which is called a parody check, so 537 00:31:08,000 --> 00:31:11,240 Speaker 1: checking for parody to make sure that the information it's 538 00:31:11,240 --> 00:31:14,920 Speaker 1: it's delivering is accurate. Um. There are a lot of 539 00:31:14,920 --> 00:31:19,560 Speaker 1: different ways of doing this, but one is So we 540 00:31:19,640 --> 00:31:23,560 Speaker 1: talked about information in in the computer world in terms 541 00:31:23,560 --> 00:31:28,600 Speaker 1: of bits and bytes, right, and a bite is eight bits, 542 00:31:29,360 --> 00:31:33,840 Speaker 1: which kind of represent a unit of information of useful 543 00:31:33,920 --> 00:31:37,400 Speaker 1: information because each bit is itself a unit of information, 544 00:31:37,400 --> 00:31:39,120 Speaker 1: but in order for it to be useful for a computer, 545 00:31:39,200 --> 00:31:43,600 Speaker 1: we we group them in groups of eight uh. Standard. 546 00:31:43,640 --> 00:31:47,040 Speaker 1: Now that wasn't when computers first were developed. There were 547 00:31:47,080 --> 00:31:51,000 Speaker 1: several different competing Um. I guess you could calm standards 548 00:31:51,000 --> 00:31:53,680 Speaker 1: because they were standard amongst a certain group of computers. 549 00:31:53,720 --> 00:31:56,000 Speaker 1: But we kind of selled on this whole eight bit 550 00:31:56,160 --> 00:32:00,360 Speaker 1: is a byte model and with parity, they there's an 551 00:32:00,520 --> 00:32:04,800 Speaker 1: extra bit added on to the end and uh that 552 00:32:04,840 --> 00:32:09,680 Speaker 1: bit is um it's kind of a marker, right, Yeah, 553 00:32:09,680 --> 00:32:12,560 Speaker 1: it's basically used for error checking. Yeah. So if if 554 00:32:12,600 --> 00:32:17,280 Speaker 1: the uh, for example, it looks at how many of 555 00:32:17,400 --> 00:32:22,040 Speaker 1: the bits within that bite are ones versus zeros. So 556 00:32:22,160 --> 00:32:25,000 Speaker 1: if all of the if there are an odd number 557 00:32:25,040 --> 00:32:28,600 Speaker 1: of ones in that byte, remember it's eight bits, there's 558 00:32:28,600 --> 00:32:31,520 Speaker 1: an odd number, the parity bit is set to one. 559 00:32:32,040 --> 00:32:34,000 Speaker 1: If it's an even number, the parody bit is set 560 00:32:34,040 --> 00:32:38,400 Speaker 1: to zero. So then when the data is being processed, 561 00:32:38,880 --> 00:32:42,120 Speaker 1: the totals added up again and it's checked against the 562 00:32:42,120 --> 00:32:48,240 Speaker 1: parody bit. Now, if that matches, the assumption is that 563 00:32:48,360 --> 00:32:52,280 Speaker 1: the that byte is correct, it's accurate, and everything's cool. 564 00:32:52,560 --> 00:32:56,200 Speaker 1: If it comes up as a conflict, then that's a 565 00:32:56,240 --> 00:33:00,560 Speaker 1: message to say, dump this information because something has gone wrong. Now, 566 00:33:00,760 --> 00:33:03,400 Speaker 1: the parody bit does not tell you what the information is. 567 00:33:03,440 --> 00:33:05,880 Speaker 1: It just is a shorthand way of saying, all right, 568 00:33:06,200 --> 00:33:10,800 Speaker 1: are there an even number of ones in this byte? Yes, well, 569 00:33:10,800 --> 00:33:13,280 Speaker 1: then something's gone wrong. It doesn't tell you what the 570 00:33:13,320 --> 00:33:17,200 Speaker 1: information is or why it's wrong. It just says that's 571 00:33:17,200 --> 00:33:19,560 Speaker 1: not what I got when I added it up, right, 572 00:33:20,680 --> 00:33:24,640 Speaker 1: So uh. And then there's that that's called even parody. 573 00:33:24,680 --> 00:33:27,240 Speaker 1: That's that particular model. That's just one way of doing it. 574 00:33:27,240 --> 00:33:29,520 Speaker 1: There's also odd parody, which is kind of the same idea, 575 00:33:29,520 --> 00:33:31,840 Speaker 1: except you know, if it's an odd number of ones, 576 00:33:31,880 --> 00:33:33,920 Speaker 1: then it's considered a zero of it's an even number 577 00:33:33,960 --> 00:33:38,920 Speaker 1: of ones, it's considered a one. But uh, there's also 578 00:33:39,080 --> 00:33:45,120 Speaker 1: the error correction code method, which goes a little bit further. 579 00:33:45,160 --> 00:33:47,360 Speaker 1: This is this is so you've got parody that tells 580 00:33:47,360 --> 00:33:50,320 Speaker 1: you there's a problem. Error correction is to try and 581 00:33:50,360 --> 00:33:52,920 Speaker 1: step in when there's a problem and fix it. Um. 582 00:33:53,040 --> 00:33:57,280 Speaker 1: It uses additional bits to monitor the information that the 583 00:33:57,320 --> 00:34:01,720 Speaker 1: actual information that's in the byte, so it's looking at 584 00:34:02,600 --> 00:34:07,360 Speaker 1: the information itself, not just a summary UM. And it 585 00:34:07,600 --> 00:34:13,560 Speaker 1: uses pretty complicated algorithms to try and head off any problems. 586 00:34:13,600 --> 00:34:16,279 Speaker 1: So there, you know, this has to be built in 587 00:34:16,320 --> 00:34:19,839 Speaker 1: because occasionally things go wrong. Sometimes something doesn't trip when 588 00:34:19,840 --> 00:34:23,719 Speaker 1: it's supposed to trip, and uh, your CPU doesn't necessarily 589 00:34:23,760 --> 00:34:26,759 Speaker 1: know that. You know, CPU is just working on what's 590 00:34:26,800 --> 00:34:29,760 Speaker 1: given to it. So again, since the CPU can't remember 591 00:34:29,760 --> 00:34:33,359 Speaker 1: what it did last in its last nanosecond, it's just saying, 592 00:34:33,360 --> 00:34:37,080 Speaker 1: all right, I gotta execute this particular operation against this 593 00:34:37,200 --> 00:34:41,799 Speaker 1: particular set of information. It doesn't know or care if 594 00:34:41,840 --> 00:34:46,120 Speaker 1: it's the correct operation or information set. So you have 595 00:34:46,200 --> 00:34:49,280 Speaker 1: to have that error correction in. There's in some places. 596 00:34:49,760 --> 00:34:54,200 Speaker 1: It's not always in the memory controller chip. Sometimes it's 597 00:34:54,239 --> 00:34:56,799 Speaker 1: part of the CPU. It's it all depends on the 598 00:34:56,960 --> 00:35:01,480 Speaker 1: architecture of the computer system itself. Yeah. Now, um, it's 599 00:35:01,480 --> 00:35:07,160 Speaker 1: also important to note, um uh that as memory uh 600 00:35:07,239 --> 00:35:10,680 Speaker 1: improvements have changed, the way of of doing this has changed. 601 00:35:10,680 --> 00:35:14,319 Speaker 1: And of course that probably the the type of RAM 602 00:35:14,360 --> 00:35:15,840 Speaker 1: that you have in your computer, if you've got a 603 00:35:15,880 --> 00:35:19,399 Speaker 1: more recent UH computer, is the aversion of the double 604 00:35:19,480 --> 00:35:24,200 Speaker 1: data rate synchronous d RAM dynamic RAM or U d 605 00:35:24,320 --> 00:35:26,640 Speaker 1: d R and you know d d R two d 606 00:35:26,719 --> 00:35:30,440 Speaker 1: d R three um s d RAM. But that's uh, 607 00:35:30,520 --> 00:35:33,759 Speaker 1: you know, that's changing. As you were saying, their improvements 608 00:35:33,800 --> 00:35:35,960 Speaker 1: being made. I know, one of the types of memory 609 00:35:36,000 --> 00:35:38,879 Speaker 1: that people have been talking about is magnetic RAM, which 610 00:35:38,960 --> 00:35:41,800 Speaker 1: is supposed to basically give you an instant on some 611 00:35:42,160 --> 00:35:45,440 Speaker 1: uh situation when you turn your computer on, because uh 612 00:35:45,480 --> 00:35:47,840 Speaker 1: it can store the information and pull it up immediately 613 00:35:47,880 --> 00:35:49,359 Speaker 1: and you don't have to worry about a long boot 614 00:35:49,440 --> 00:35:54,399 Speaker 1: up sequence as the RAM is getting uh populated with information, right. Yeah. 615 00:35:54,880 --> 00:35:58,120 Speaker 1: The idea here is to have something some sort of 616 00:35:58,200 --> 00:36:02,719 Speaker 1: system in place that can maintain a state without the 617 00:36:02,719 --> 00:36:06,840 Speaker 1: need for uh the electrical impulse to go through and 618 00:36:06,880 --> 00:36:12,239 Speaker 1: boot it up. Right. So another potential solution, although this 619 00:36:12,280 --> 00:36:17,560 Speaker 1: is one that is still being developed is the memorister. Yes, memoristers. 620 00:36:17,760 --> 00:36:21,640 Speaker 1: These are interesting things. Uh, it's kind of difficult. It's 621 00:36:21,840 --> 00:36:25,840 Speaker 1: really complicated to to get into detail. But from a 622 00:36:25,880 --> 00:36:33,359 Speaker 1: bird's eye perspective, a memorister is an electrical component, all right. 623 00:36:33,480 --> 00:36:37,360 Speaker 1: And if you run current through a memorister in one direction, 624 00:36:37,480 --> 00:36:42,399 Speaker 1: the electrical resistance increases. If you run current through the 625 00:36:42,440 --> 00:36:47,600 Speaker 1: opposite way, the resistance decreases. Now, once the current stops 626 00:36:48,000 --> 00:36:54,279 Speaker 1: moving through, the memorister holds onto whatever the last resistance was. 627 00:36:54,360 --> 00:36:56,120 Speaker 1: So if you ran it through the first way, then 628 00:36:56,160 --> 00:36:59,640 Speaker 1: the resistance has been is stays at its increased level. 629 00:37:00,160 --> 00:37:03,040 Speaker 1: If you if you last ran it through the opposite way, 630 00:37:03,080 --> 00:37:05,560 Speaker 1: then it's going to be at its decreased level. Well, 631 00:37:05,600 --> 00:37:09,000 Speaker 1: that's that's a two bit system, right. You could assign 632 00:37:09,080 --> 00:37:10,600 Speaker 1: one of those a one and the other one of 633 00:37:10,760 --> 00:37:15,960 Speaker 1: zero and once you ran through that once, uh, it 634 00:37:15,960 --> 00:37:19,279 Speaker 1: would make it would hold on to that information. And 635 00:37:19,520 --> 00:37:24,160 Speaker 1: it takes up much less space than the typical memory 636 00:37:24,239 --> 00:37:29,839 Speaker 1: transistors do, so it's smaller and it will hold on 637 00:37:29,960 --> 00:37:34,319 Speaker 1: to whatever the state is until you tell it that 638 00:37:34,440 --> 00:37:36,480 Speaker 1: you know you want to change by by and you 639 00:37:36,560 --> 00:37:39,319 Speaker 1: tell it by running the electricity through it one way 640 00:37:39,480 --> 00:37:42,520 Speaker 1: or versus the other. Does the computer have to remain 641 00:37:42,600 --> 00:37:45,200 Speaker 1: plugged in for this to work. No, once you've once 642 00:37:45,239 --> 00:37:48,120 Speaker 1: you've done it, once you've run the current through, you 643 00:37:48,160 --> 00:37:53,080 Speaker 1: can turn the current off and the memorister retains that resistance. 644 00:37:54,000 --> 00:37:56,000 Speaker 1: So the only thing that has to happen is the 645 00:37:56,040 --> 00:37:58,960 Speaker 1: computer has to be able to detect what the resistance 646 00:37:59,120 --> 00:38:02,040 Speaker 1: is of that memory rister. So once it detects what 647 00:38:02,200 --> 00:38:05,600 Speaker 1: the state is, then you've got that information already there. 648 00:38:05,880 --> 00:38:08,440 Speaker 1: So it could be used in various kinds of processors 649 00:38:08,440 --> 00:38:11,160 Speaker 1: as well as memory. And because it's smaller, you could 650 00:38:11,200 --> 00:38:15,600 Speaker 1: at least potentially cram far more memory into a smaller 651 00:38:15,640 --> 00:38:20,320 Speaker 1: space than what is capable using right now through transistors. 652 00:38:20,360 --> 00:38:23,520 Speaker 1: So this is this is a potential way to keep 653 00:38:23,600 --> 00:38:27,719 Speaker 1: Moore's law going. In fact, if the developments were to 654 00:38:27,840 --> 00:38:31,200 Speaker 1: progress at a at a good clip, we could almost 655 00:38:31,280 --> 00:38:35,680 Speaker 1: leap frog quite a bit because the potential is that 656 00:38:35,800 --> 00:38:40,680 Speaker 1: it would revolutionize UH processing and memory all in a 657 00:38:40,800 --> 00:38:45,120 Speaker 1: in a a fell swoop, a swell foop. Yeah. Now 658 00:38:45,160 --> 00:38:47,520 Speaker 1: I'm not sure that the board would agree. I'm sure 659 00:38:47,560 --> 00:38:53,160 Speaker 1: that they say that anything involving resistance, Yeah, but yeah, 660 00:38:53,160 --> 00:38:58,200 Speaker 1: it's it's an interesting idea, and it's something that's was 661 00:38:58,239 --> 00:39:02,000 Speaker 1: first proposed back in nineteen seven. Any one and UH 662 00:39:02,120 --> 00:39:06,680 Speaker 1: and HP Labs has been working on it diligently. UM 663 00:39:06,760 --> 00:39:08,600 Speaker 1: and in fact, in two thousand and eight announced that 664 00:39:08,640 --> 00:39:14,440 Speaker 1: it was developing switching mem risters. So these are these 665 00:39:14,440 --> 00:39:16,279 Speaker 1: are the sort of technologies that I think are going 666 00:39:16,360 --> 00:39:19,760 Speaker 1: to become far more important in the near future. Because 667 00:39:20,560 --> 00:39:23,400 Speaker 1: again we've talked about this before about how the world 668 00:39:23,480 --> 00:39:27,600 Speaker 1: is moving to mobile devices literally in some cases, but 669 00:39:27,719 --> 00:39:30,719 Speaker 1: that mobile devices are becoming increasingly important. Well, with a 670 00:39:30,760 --> 00:39:33,120 Speaker 1: mobile device, you have a much more limited amount of 671 00:39:33,120 --> 00:39:36,200 Speaker 1: space that you have to work within, and so something 672 00:39:36,280 --> 00:39:39,920 Speaker 1: like a memrister, which could at least, at least in theory, 673 00:39:40,120 --> 00:39:43,680 Speaker 1: pack much larger punch and a much smaller package. It 674 00:39:43,719 --> 00:39:49,279 Speaker 1: could create the super super duper smartphones that we all want. 675 00:39:50,000 --> 00:39:56,080 Speaker 1: Super smartphones are already on the horizon. Okay, well secret 676 00:39:56,080 --> 00:40:00,799 Speaker 1: identities too, So so RAM is pretty ubiquitous. I mean, 677 00:40:00,800 --> 00:40:04,680 Speaker 1: it's in just about anything that that computes UM. And 678 00:40:05,040 --> 00:40:08,600 Speaker 1: you know, the technology has been fairly standard for for 679 00:40:08,719 --> 00:40:12,799 Speaker 1: several years now, um, you know, with minor improvements over 680 00:40:12,840 --> 00:40:16,000 Speaker 1: the past decade or so, but um, you know, with 681 00:40:16,000 --> 00:40:22,280 Speaker 1: with Uh, computer scientists working on improvements, uh, completely different technologies. 682 00:40:22,560 --> 00:40:25,040 Speaker 1: Hopefully they'll be able to improve that because it's it's 683 00:40:25,080 --> 00:40:29,200 Speaker 1: critical to basically any type of computing that you want 684 00:40:29,360 --> 00:40:34,040 Speaker 1: or need to do. Um, So it's uh, it's very basic. 685 00:40:34,120 --> 00:40:37,040 Speaker 1: I'm glad we we looked at it because it's, uh, 686 00:40:37,320 --> 00:40:40,560 Speaker 1: it's vastly important to our our daily world these days. 687 00:40:40,600 --> 00:40:44,000 Speaker 1: It's definitely one of the basic building blocks of of 688 00:40:44,040 --> 00:40:46,360 Speaker 1: the computing age. I mean, you know you talk about 689 00:40:47,000 --> 00:40:50,640 Speaker 1: it's not as it's not as basic as say a transistor, right, 690 00:40:50,760 --> 00:40:52,319 Speaker 1: it's like a level up, so it's kind of on 691 00:40:52,360 --> 00:40:55,720 Speaker 1: the molecule scale as opposed to the atomic scale. Right. 692 00:40:55,719 --> 00:40:59,200 Speaker 1: It relies on transistors, so it's it's a little more 693 00:40:59,239 --> 00:41:02,680 Speaker 1: complex than the basic basic building blocks. But without it, 694 00:41:03,200 --> 00:41:05,759 Speaker 1: computing would not be nearly as useful as it is 695 00:41:06,800 --> 00:41:10,400 Speaker 1: because it would take far more time to process operations. 696 00:41:10,840 --> 00:41:14,400 Speaker 1: And even again, even if you have the fastest CPU, 697 00:41:14,520 --> 00:41:17,560 Speaker 1: if it can't access memory, then all it's going to 698 00:41:17,600 --> 00:41:20,640 Speaker 1: do is just be very quick when it needs to 699 00:41:20,640 --> 00:41:24,239 Speaker 1: to find information on the hard drive, and then it's 700 00:41:24,280 --> 00:41:27,120 Speaker 1: all dependent upon how fast the hard drive can deliver 701 00:41:27,160 --> 00:41:31,320 Speaker 1: the information to the CPU. The memory allows the CPU 702 00:41:31,360 --> 00:41:34,839 Speaker 1: to skip that step and it just makes things much faster. Now, 703 00:41:35,040 --> 00:41:38,880 Speaker 1: another potential memrister thing I should say is that if 704 00:41:38,880 --> 00:41:41,680 Speaker 1: you designed a hard drive out of memristers, you could, 705 00:41:41,800 --> 00:41:47,319 Speaker 1: in theory have your hard drive act as memory. It 706 00:41:47,320 --> 00:41:50,160 Speaker 1: would be it would it could in theory behave in 707 00:41:50,200 --> 00:41:54,600 Speaker 1: a very similar fashion, which means you could potentially just 708 00:41:54,680 --> 00:41:57,600 Speaker 1: incorporate RAM directly as part of what the hard drive does, 709 00:41:57,920 --> 00:42:00,839 Speaker 1: and then you wouldn't need RAM anymore, which also means 710 00:42:00,840 --> 00:42:03,560 Speaker 1: that you can load stuff up at at uh in 711 00:42:03,600 --> 00:42:07,240 Speaker 1: the blink of an eye, and that would be phenomenal. Uh. Again, 712 00:42:07,280 --> 00:42:11,080 Speaker 1: that's a potential uh that we may come to see 713 00:42:11,080 --> 00:42:13,359 Speaker 1: one day. It's not something that you're gonna see on 714 00:42:13,400 --> 00:42:16,520 Speaker 1: the market. I don't know else. I haven't gone to 715 00:42:16,560 --> 00:42:21,359 Speaker 1: ce S yet, so maybe hey, look at m rister machine. 716 00:42:21,640 --> 00:42:25,040 Speaker 1: Can I take it? Yeah? No, that's the tildy key 717 00:42:25,040 --> 00:42:29,719 Speaker 1: work alright then, Yeah, let's wrap this up. Guys. If 718 00:42:29,760 --> 00:42:33,520 Speaker 1: you have any questions about any particular subject you would 719 00:42:33,560 --> 00:42:36,640 Speaker 1: like us to talk about. You have suggestions for topics, 720 00:42:36,960 --> 00:42:39,360 Speaker 1: let us know. You can tell us on Facebook or Twitter. 721 00:42:39,480 --> 00:42:42,640 Speaker 1: Are handle There is tech stuff hs W and stay 722 00:42:42,680 --> 00:42:46,680 Speaker 1: tuned to text stuff because our email is changing. We 723 00:42:46,719 --> 00:42:48,520 Speaker 1: don't have it yet, so I can't give it to you. 724 00:42:48,600 --> 00:42:51,080 Speaker 1: But tech Stuff at how stuff Works dot Com will 725 00:42:51,080 --> 00:42:54,879 Speaker 1: only work for a short limited time, so keep your 726 00:42:54,960 --> 00:42:57,560 Speaker 1: ears tuned. In a future episode of tech Stuff we 727 00:42:57,600 --> 00:43:00,600 Speaker 1: will give you our new address. I hope you guys 728 00:43:00,680 --> 00:43:02,640 Speaker 1: enjoyed the show, and Chris and I will talk to 729 00:43:02,680 --> 00:43:07,239 Speaker 1: you again when we remember. Be sure to check out 730 00:43:07,280 --> 00:43:10,440 Speaker 1: our new video podcast, Stuff from the Future. Join how 731 00:43:10,520 --> 00:43:13,040 Speaker 1: Stuff Work staff as we explore the most promising and 732 00:43:13,080 --> 00:43:17,759 Speaker 1: perplexing possibilities of tomorrow. The hou Stuff Works iPhone app 733 00:43:17,800 --> 00:43:25,440 Speaker 1: has arrived. Download it today on iTunes, brought to you 734 00:43:25,480 --> 00:43:28,839 Speaker 1: by the reinvented two thousand twelve camera. It's ready, are 735 00:43:28,920 --> 00:43:29,080 Speaker 1: you