WEBVTT - Sharing the Load 0:00:00.160 --> 0:00:07.200 Brought to you by Toyota. Let's go places. Welcome to 0:00:07.400 --> 0:00:14.800 Forward Thinking. Hey there, and welcome to Forward Thinking, the 0:00:14.920 --> 0:00:17.680 podcast that looks at the future and says, and all 0:00:17.760 --> 0:00:20.319 the world is biscuit shaped. It's just for me to 0:00:20.440 --> 0:00:24.520 feed my face. I'm Jonathan Strickland, I'm Lauren, and I'm 0:00:24.560 --> 0:00:27.840 Joe McCormick. No, Joe. The lyric this week does not 0:00:28.040 --> 0:00:31.560 die into the topic. It was just some words, just 0:00:31.640 --> 0:00:35.520 say in words. Words are good words here. Well, then 0:00:35.600 --> 0:00:38.400 what is the topic, Jonathan? Well, the topic is you know, 0:00:39.280 --> 0:00:41.640 you guys are putting so much pressure on me. There's 0:00:41.720 --> 0:00:44.080 way too much I'm having to carry the whole load 0:00:44.159 --> 0:00:47.239 of explaining what the topic is. How can we help you, Jonathan? 0:00:47.320 --> 0:00:49.760 I think we should all kind of, you know, share 0:00:49.880 --> 0:00:53.760 the responsibility. Okay, let's do that thing, the improv thing 0:00:53.800 --> 0:00:59.040 where each person Okay, so I'll start and then where's 0:00:59.080 --> 0:01:04.160 it going to? From you to to Lauren. Today's topic 0:01:04.480 --> 0:01:11.520 is about distributed computing guys. Yeah, all right, there we 0:01:11.560 --> 0:01:13.560 go that. I think that was probably the most successful 0:01:13.560 --> 0:01:15.560 word of the the time I've ever been part of. And 0:01:15.680 --> 0:01:21.480 nobody brought in like gussy anything about nazis. Yeah, there 0:01:21.520 --> 0:01:23.920 wasn't a head in a box, which is almost always 0:01:23.920 --> 0:01:26.360 what happens in an improv scene. Wait, what did we 0:01:26.400 --> 0:01:32.240 say distributed computing? Yes, yes, so Joe back in the day, 0:01:32.319 --> 0:01:36.240 which was a Tuesday, Uh, there was this issue where 0:01:36.319 --> 0:01:40.080 you would have a big computational problem, really really complex, 0:01:40.720 --> 0:01:44.240 and you essentially had one computer defeat it through and 0:01:44.319 --> 0:01:46.800 you really just had to wait until the computer was 0:01:46.840 --> 0:01:51.720 able to complete that problem, and you were completely reliant 0:01:52.240 --> 0:01:56.120 upon that computer and that computer's limitations. Right, that was it. 0:01:56.200 --> 0:01:58.960 That was that. So if it didn't have enough punch 0:01:59.000 --> 0:02:01.680 card slots, you were just out of luck. Yeah, that's 0:02:01.680 --> 0:02:04.200 pretty much it. Like if you if the program you 0:02:04.240 --> 0:02:08.720 wanted to run had a requirement that was so large 0:02:08.720 --> 0:02:10.679 that you didn't have a box big enough to hold 0:02:10.720 --> 0:02:13.680 all the punch cards. It was too complex for that machine. Yeah, 0:02:13.919 --> 0:02:16.799 which is you know also how stuff like algorithms started 0:02:16.840 --> 0:02:18.760 to be written because people said, oh, hey, if we 0:02:18.800 --> 0:02:22.120 can create a shortcut, that says you know, yeah, this 0:02:22.200 --> 0:02:24.919 is the birth of hackers, right where hackers would say, 0:02:25.200 --> 0:02:28.200 I have an outcome that I need to have happen. 0:02:28.560 --> 0:02:30.239 How do I make that happen? It doesn't have to 0:02:30.280 --> 0:02:33.320 be pretty, It just has to work. Well, you know, 0:02:33.400 --> 0:02:37.120 in science we actually have issues like this where scientists 0:02:37.120 --> 0:02:42.560 researchers are working on uh projects where you get massive, 0:02:42.880 --> 0:02:45.480 truly massive amounts of data and then you have to 0:02:45.520 --> 0:02:48.200 figure out, well, we've got all this information, but we 0:02:48.280 --> 0:02:50.880 can't really do anything meaningful with it. Yeah, you've got 0:02:50.880 --> 0:02:55.040 a problem that's computationally intensive, meaning you you sort of 0:02:55.080 --> 0:02:57.360 know how to solve it. You have a method to 0:02:57.400 --> 0:03:00.520 get there, but you just need the ability to do 0:03:00.680 --> 0:03:03.360 all that work. And if you're going to run it 0:03:03.400 --> 0:03:05.960 through one computer. What if you're trying to do a 0:03:06.000 --> 0:03:08.640 research project where you're sitting here in front of your 0:03:08.639 --> 0:03:11.200 computer and it gives you an estimate it says, okay, 0:03:11.240 --> 0:03:13.600 it will only take forty five years to do all 0:03:13.600 --> 0:03:17.320 the calculations on this data, right. Yeah. Yeah. It's sort 0:03:17.320 --> 0:03:19.680 of the equivalent of saying like, well, I have this 0:03:19.840 --> 0:03:23.840 room full of fun sized candy bars. I know I 0:03:23.880 --> 0:03:26.640 can count them, but I only have you know, ten 0:03:26.680 --> 0:03:30.000 fingers and ten toes. So once I get beyond that, 0:03:30.120 --> 0:03:33.760 it's going to start getting tricky. Well, here's the other 0:03:33.840 --> 0:03:35.960 way of doing this. I just want a room full 0:03:35.960 --> 0:03:38.040 of fun sized candy bars. I'm sorry, I'm gonna come 0:03:38.040 --> 0:03:41.560 back and run with that example interruption, what kind of 0:03:41.600 --> 0:03:45.800 candy bars? Oh, I'm going to say heath crunch bars. 0:03:46.240 --> 0:03:49.800 That's acceptable. I also would have accepted butterfinger. Okay, I 0:03:49.800 --> 0:03:52.839 shouldn't really have peanuts, So that's true. Yeah, you're having 0:03:52.840 --> 0:03:55.480 the issue with the peanuts. So let's say let's say 0:03:55.520 --> 0:03:58.760 that all we have that issue with fun heaths. Okay, 0:03:58.880 --> 0:04:01.560 Lauren needs has got a room full of fun sized 0:04:01.560 --> 0:04:05.000 heath bars, and uh. And if she were going in 0:04:05.040 --> 0:04:07.560 there on her own to count them all, and was 0:04:07.640 --> 0:04:10.120 using her fingers and toes as reference, she would very 0:04:10.200 --> 0:04:12.160 quickly run out of fingers and toes, and then she'd 0:04:12.160 --> 0:04:13.880 have to start trying to remember things. It would take 0:04:13.880 --> 0:04:15.440 her time to get through all of that. I'd have 0:04:15.440 --> 0:04:18.160 to make a little hash marks on paper individually. Right. So, 0:04:18.360 --> 0:04:21.800 if she ended up inviting a bunch of her friends over, 0:04:21.960 --> 0:04:24.640 and she had divided up the floor into a grid 0:04:25.160 --> 0:04:28.560 and assigned each person a part of that floor where 0:04:28.600 --> 0:04:31.279 they are not allowed to eat said candy bars, merely 0:04:31.400 --> 0:04:35.520 count them, and then together you all came up and 0:04:35.560 --> 0:04:37.760 wrote down the numbers you came up with, and then 0:04:37.800 --> 0:04:39.880 added all those numbers. You would then know how many 0:04:39.920 --> 0:04:41.880 candy bars were in that room you had divided the 0:04:41.920 --> 0:04:44.520 problem up. Yeah, take a lot less time that way. 0:04:45.400 --> 0:04:48.360 So this is kind of what distributed computing is all about. 0:04:48.440 --> 0:04:52.520 So you could do the approach of getting a supercomputer 0:04:52.839 --> 0:04:58.040 that has an incredibly fast processor, or maybe several processors, 0:04:58.080 --> 0:05:02.400 but one those are rare too. Because they're rare, their 0:05:02.480 --> 0:05:06.320 time is often spoken for. So your project will probably 0:05:06.400 --> 0:05:09.360 be competing with multiple other projects that they're very expensive 0:05:09.440 --> 0:05:11.880 to use. That's that's number three as well. They are 0:05:12.000 --> 0:05:15.640 very expensive to get that time and so and also 0:05:15.800 --> 0:05:18.600 you know they're going to tackle that problem. They might 0:05:18.640 --> 0:05:20.320 be really fast at it, but they're going to tackle 0:05:20.360 --> 0:05:23.760 that problem sequentially. Okay, but how about instead of one 0:05:23.920 --> 0:05:27.440 really powerful computer, you buy a whole bunch of less 0:05:27.440 --> 0:05:31.400 powerful computers and then you break the task up into 0:05:31.440 --> 0:05:34.560 small chunks like we were talking about. And so you've 0:05:34.600 --> 0:05:37.920 you've got a lot of sort of powerful computers computing 0:05:37.960 --> 0:05:41.160 little bits of your task. That's often referred to as 0:05:41.160 --> 0:05:45.279 grid computing. It's uh, grid computing and distributing computing are 0:05:45.320 --> 0:05:49.599 are sometimes interchangeable. It really depends upon who's doing the talking, 0:05:49.920 --> 0:05:52.080 is ultimately what it comes down to. Sure, but but 0:05:52.160 --> 0:05:54.880 what if you don't have the funding to buy a 0:05:54.960 --> 0:05:59.159 grid worth of computers, or what if even a reasonably 0:05:59.279 --> 0:06:01.839 sized grid it of computers isn't going to get the 0:06:01.839 --> 0:06:04.359 problem done faster, or if you don't have space to 0:06:04.440 --> 0:06:07.120 put a grid of computers because it's all taken up 0:06:07.120 --> 0:06:10.360 by fun sized heath bars. Yeah, so clearly this is 0:06:10.400 --> 0:06:14.080 not necessarily the best option either. There could be other 0:06:14.839 --> 0:06:19.760 options out there, right, So problem meat wasted potential. Your 0:06:19.880 --> 0:06:24.240 computer and I mean your computer, you, the listener, and 0:06:24.279 --> 0:06:27.520 the three of us. Actually yea, it was confusing me 0:06:27.520 --> 0:06:30.280 because Joe was clearly pointing at me or your well, 0:06:30.360 --> 0:06:32.640 I was pointing at my microphone, so I was pointing 0:06:32.680 --> 0:06:36.440 at the listener and Knowle's computer and everybody in the office. 0:06:36.440 --> 0:06:40.039 I mean, what if your smartphones and your tablets, etcetera. Yeah, 0:06:40.279 --> 0:06:45.120 things that have processors. We have tons of CPUs around 0:06:45.120 --> 0:06:48.320 the world and that are not Yeah, yeah, that are 0:06:48.520 --> 0:06:52.440 so they're they're capable of doing important processing work. They 0:06:52.520 --> 0:06:57.160 can do math, they can run simulations, they can catalog data, 0:06:57.360 --> 0:07:01.120 they can do all these computational tasks these big supercomputers 0:07:01.120 --> 0:07:04.200 do on a much smaller scale, and they're not helping. 0:07:04.320 --> 0:07:07.280 They're just sitting there when you're not using Yeah, unlike 0:07:07.360 --> 0:07:11.240 unlike our brains, which which genuinely do use the whole 0:07:11.280 --> 0:07:13.760 brain to do stuff, that ten percent rule does not apply. 0:07:13.840 --> 0:07:16.840 As we've spoken about before, your computer is really only 0:07:16.960 --> 0:07:20.840 using a small fraction of its potential processing power at 0:07:20.840 --> 0:07:23.360 any given time, and especially when you're, for example, away 0:07:23.360 --> 0:07:26.600 from home. Right. So here we now reach the idea 0:07:26.640 --> 0:07:31.520 of the popular distributed computing method also known as volunteer computing, 0:07:32.040 --> 0:07:35.080 where there's a project that says, hey, I wonder if 0:07:35.120 --> 0:07:36.920 we can get a bunch of people out in the 0:07:36.960 --> 0:07:40.960 world to donate some of their computer power to help 0:07:41.240 --> 0:07:44.320 us find a solution to our problem right now. Clearly, 0:07:44.360 --> 0:07:49.080 this only really works if the problems you are tackling 0:07:49.240 --> 0:07:52.920 can be divided, right. Not all computer problems are that way. 0:07:53.240 --> 0:07:55.680 So there. We kind of talked about this with quantum 0:07:55.680 --> 0:07:58.720 computers as well, which sort of take this concept and 0:07:58.760 --> 0:08:01.120 boil it down to a single machine. It's the fact 0:08:01.120 --> 0:08:04.679 that the cubits can act as either zeros or ones 0:08:04.760 --> 0:08:08.440 and all values in between technically that allow them to 0:08:08.440 --> 0:08:12.560 to do all the parallel processing simultaneously. At least, that's 0:08:12.600 --> 0:08:15.440 the concept. This is sort of the same thing, except 0:08:15.480 --> 0:08:19.720 instead of the conceptual doing them all simultaneously on one machine, 0:08:20.000 --> 0:08:23.679 you've divided that problem up across a network of machines, 0:08:23.760 --> 0:08:25.920 all of which are working on parts of it. If 0:08:25.920 --> 0:08:29.280 the problem can't be divided, then grid computing or distributed 0:08:29.320 --> 0:08:31.840 computing isn't going to work. You have to have that 0:08:32.000 --> 0:08:35.880 sequential approach. Think of it as if I have a 0:08:35.880 --> 0:08:40.400 a math problem that's completely distinct, then I can solve 0:08:40.480 --> 0:08:43.160 that uh. And if I have a whole series of 0:08:43.200 --> 0:08:45.400 math problems, each of which are distinct, I can solve 0:08:45.440 --> 0:08:48.439 them in whatever order I want. Right. If problem one 0:08:48.480 --> 0:08:50.520 seems like it's too tricky, I can skip the problem 0:08:50.520 --> 0:08:52.719 to and solve that one, then go back to problem one. 0:08:53.120 --> 0:08:55.520 But if I have a series of math problems, each 0:08:55.559 --> 0:08:57.840 of which which is dependent upon the answer of the 0:08:57.880 --> 0:09:01.040 previous problem, that's more of an issue where I need 0:09:01.080 --> 0:09:03.840 to take a more sequential approach. So it all depends 0:09:03.840 --> 0:09:05.680 on the nature of the problem. But assuming that it 0:09:05.760 --> 0:09:08.840 is one that can be divided up, this model is 0:09:09.280 --> 0:09:14.360 a fantastic solution, and it's really amazing how people have 0:09:14.559 --> 0:09:18.360 started to leverage it. Right, and so this is ongoing today. 0:09:18.400 --> 0:09:21.360 But the concept is not at all new it has been. 0:09:21.400 --> 0:09:25.439 The idea has existed for decades, and it's been employed 0:09:25.679 --> 0:09:28.480 in very powerful ways for at least like ten or 0:09:28.480 --> 0:09:31.560 fifteen years now. But I think we should go back 0:09:31.600 --> 0:09:34.040 to the beginning of the idea of distributed or grid 0:09:34.120 --> 0:09:35.920 computing and take a look at how we got where 0:09:35.920 --> 0:09:37.760 we are today. Okay, all right, So if you go 0:09:37.840 --> 0:09:41.120 to the very beginning, we're talking about the basic, major, 0:09:41.240 --> 0:09:45.840 huge mainframe computers that didn't have any connection with any 0:09:45.880 --> 0:09:50.920 other computational device. So they were completely standalone. And if 0:09:50.960 --> 0:09:54.280 you wanted to divide up work, well you might want 0:09:54.280 --> 0:09:56.240 a lot of things, but here's the way life works. 0:09:56.280 --> 0:09:59.439 It's not gonna all pan out for you. So that 0:09:59.520 --> 0:10:02.560 was the big and then you had the the early 0:10:02.640 --> 0:10:06.560 days of networking computers together, the first major one being 0:10:06.640 --> 0:10:09.720 our Pannette. Now that was in the sixties and seventies really, 0:10:10.600 --> 0:10:13.760 So in the sixties you get this team together that 0:10:13.880 --> 0:10:18.160 DARPA had wanted to get together, um, and they started 0:10:18.160 --> 0:10:20.200 trying to figure out ways to let computers talk to 0:10:20.200 --> 0:10:27.000 one another. Now that early communication didn't really facilitate distributed computing. 0:10:27.160 --> 0:10:31.280 You could share work, but you couldn't divide a problem 0:10:31.360 --> 0:10:33.840 up at that point. There was no infrastructure to allow 0:10:33.880 --> 0:10:36.760 that sort of thing to happen yet, So think of 0:10:36.800 --> 0:10:39.760 it as people who are able to communicate with one another, 0:10:39.840 --> 0:10:44.640 but they can't collaborate actively on things. Yet you get 0:10:44.679 --> 0:10:48.319 to the nineteen seventy one you get the first distributed 0:10:48.400 --> 0:10:54.040 computing problem, which was not a true distributed computing challenge. 0:10:54.160 --> 0:10:58.400 It was actually the first computer virus purposeful virus though 0:10:58.400 --> 0:11:00.840 I'm well, I mean, I guess all viruses areful viruses. 0:11:01.160 --> 0:11:05.120 It was an experiment. Really yeah, it's called Creeper. It's 0:11:05.160 --> 0:11:08.880 a self copying, self duplicating piece of code, which you 0:11:08.920 --> 0:11:12.320 can realize if you talk about self duplication, it could 0:11:12.400 --> 0:11:16.080 quickly get out of control and duplicate self in order 0:11:16.120 --> 0:11:18.600 to take up all remaining space. There was also Reaper, 0:11:18.840 --> 0:11:22.880 which was meant to diffuse and disarm and remove Creeper. 0:11:23.840 --> 0:11:26.640 Then you in the nineteen eighties you get to the 0:11:26.679 --> 0:11:29.720 birth of the Internet. So this is the true network 0:11:29.760 --> 0:11:32.640 of networks. Urban net is kind of the predecessor to 0:11:32.679 --> 0:11:36.800 the Internet. It's not really the um the earlier version 0:11:36.800 --> 0:11:39.360 of it. Internet itself was a different thing, right, But 0:11:39.440 --> 0:11:41.440 this is when you get to the kind of net 0:11:41.480 --> 0:11:44.880 that Sandra bullet gets caught up right exactly. It was 0:11:45.040 --> 0:11:49.480 very accurately portrayed in that movie. As I recall, Uh, well, 0:11:49.520 --> 0:11:52.680 distributed computing ends up becoming an area of research, even 0:11:52.679 --> 0:11:56.680 though no one has actually launched a distributed computing project 0:11:56.720 --> 0:11:58.760 the way we think of them today. All Right, Well, 0:11:58.800 --> 0:12:03.680 at this time, it was only government officials and university researchers, 0:12:03.720 --> 0:12:06.439 people on that level who had access to to this network, 0:12:06.640 --> 0:12:10.679 right right, You and I, assuming we were not employed 0:12:10.720 --> 0:12:15.280 by a government or military or university, didn't have access 0:12:15.320 --> 0:12:18.600 to it. Uh. The Internet was something that probably most 0:12:18.600 --> 0:12:20.960 of us were largely unaware of at the time. It 0:12:21.000 --> 0:12:24.800 was it was still so um so expensive to obtain 0:12:24.840 --> 0:12:26.720 the kind of equipment that you would need that it was. 0:12:26.800 --> 0:12:29.160 It was really left up to these large organizations. Most 0:12:29.200 --> 0:12:32.160 of us were dealing with local networks like like Bolton 0:12:32.200 --> 0:12:36.040 board systems and stuff that had some connectivity but weren't 0:12:36.120 --> 0:12:40.560 ultimately leading to the larger Internet. So by nineteen eighty 0:12:40.640 --> 0:12:45.320 two there was a Distributed Principles of Distributed Computing symposium, 0:12:45.400 --> 0:12:50.160 and then another one in International Symposium in nineteen five, 0:12:50.320 --> 0:12:54.439 So people were already thinking about the potential for computers 0:12:54.440 --> 0:12:56.880 to do this kind of thing and starting to lay 0:12:56.920 --> 0:12:59.640 the groundwork for the technology that would make it possible. 0:12:59.679 --> 0:13:03.400 By night we get the first Internet based distributing computing 0:13:03.440 --> 0:13:08.040 project at the d e C System Research Center. And 0:13:08.400 --> 0:13:11.200 the way it worked is through email. We get a 0:13:11.240 --> 0:13:14.719 task through email. So you would volunteer to be part 0:13:14.720 --> 0:13:18.760 of this? Yeah, well, I mean there wasn't an automated 0:13:18.800 --> 0:13:22.280 system here yet. Yeah, so you will? You would, you 0:13:22.280 --> 0:13:24.280 would first, you would volunteer. You'd see like, you know, 0:13:24.440 --> 0:13:26.400 you go to the coffee shop. You see a little 0:13:26.400 --> 0:13:29.000 piece of paper with strips on it saying, hey, are 0:13:29.040 --> 0:13:32.360 you willing to lend your computer to help science? Tear 0:13:32.400 --> 0:13:35.520 off a strip and send an email? And uh, and 0:13:35.679 --> 0:13:38.080 most people in the coffee shop and say, what's an email? 0:13:38.440 --> 0:13:40.679 But you knowing what an email is, You tear off 0:13:40.679 --> 0:13:42.520 a strip and you send off an email. They send 0:13:42.559 --> 0:13:45.280 you an email with a task to complete. You run 0:13:45.320 --> 0:13:47.440 it on your computer, complete the task, and you email 0:13:47.480 --> 0:13:50.679 the results back. So it's an It takes takes an 0:13:50.720 --> 0:13:53.319 active role for the volunteer in order for this system 0:13:53.360 --> 0:13:56.160 to work. And the purpose of this project was to 0:13:56.240 --> 0:14:00.880 factor large numbers, which is an important role part of cryptography, 0:14:01.000 --> 0:14:05.720 computer cryptography and UM It was a relatively modest project 0:14:05.800 --> 0:14:10.160 by There were about a hundred volunteers using this and 0:14:10.480 --> 0:14:14.280 it was fueled in part by challenges issued by the 0:14:14.440 --> 0:14:18.760 r S, a security incorporated company. H They wanted to 0:14:18.880 --> 0:14:22.320 do lots of research on factoring of large numbers as 0:14:22.320 --> 0:14:24.880 a security company, and and the fact that this has 0:14:25.000 --> 0:14:27.280 a lot to do with cryptography. It was very important 0:14:27.320 --> 0:14:29.200 to their business in order for them to make sure 0:14:29.240 --> 0:14:33.080 that their systems and other systems remain ahead of hackers. 0:14:33.440 --> 0:14:35.880 So if it turns out that a group of people 0:14:35.920 --> 0:14:39.760 can quickly factor a certain size prime number, or to 0:14:39.800 --> 0:14:43.160 find the largest primes of a certain number, then they 0:14:43.240 --> 0:14:45.560 wanted to make sure they could go to the next 0:14:45.680 --> 0:14:49.840 level in order to avoid issues with people immediately hacking 0:14:49.880 --> 0:14:53.120 through all sorts of security system Yeah. Yeah, greater encryption, 0:14:53.320 --> 0:14:57.640 for greater protection against people who wanted decrypt YEP. And 0:14:57.680 --> 0:15:02.760 in NT you get distributed dot net, which is really 0:15:02.800 --> 0:15:05.400 the first project to use the Internet to distribute data 0:15:05.440 --> 0:15:08.840 for calculation and collect the results automatically, so it did 0:15:08.960 --> 0:15:14.400 not require the volunteers to receive and send email. It 0:15:14.480 --> 0:15:17.600 had a software package that did all the handling of 0:15:17.640 --> 0:15:21.040 that automatically. Yeah, it's all in the background. So the 0:15:21.160 --> 0:15:24.320 user just had to install software onto his or her 0:15:24.360 --> 0:15:28.280 computer and then start up the software, have an Internet connection, 0:15:28.480 --> 0:15:31.400 and the program would would run itself. Yeah, essentially running 0:15:31.400 --> 0:15:34.560 in the background, taking you know, any unused cycles of 0:15:34.760 --> 0:15:39.880 processor and dedicating it to working on the problem. And 0:15:40.000 --> 0:15:43.640 that has pretty much been the model for distributed computing 0:15:43.720 --> 0:15:46.280 or volunteer computing ever since. You know, I thought you 0:15:46.320 --> 0:15:49.080 were going to say, the first distributed computing project was 0:15:49.120 --> 0:15:52.360 like an x files used net group that was sending 0:15:52.400 --> 0:15:55.359 out task to get different people to decode the messages 0:15:55.480 --> 0:15:59.440 and learn Molder secret. I wish. I'm sure some of 0:15:59.480 --> 0:16:02.360 that was going on. I think, I mean not Molder secret, 0:16:02.400 --> 0:16:05.040 the secret of his his his family has passed. I 0:16:05.080 --> 0:16:08.120 think I think the real secret was that everybody but 0:16:08.320 --> 0:16:13.920 Molder and Scully knew. Everybody everyone in that show knew 0:16:13.960 --> 0:16:18.960 more than the spoiler. Look, I think I think that's 0:16:18.960 --> 0:16:25.480 not a spoiler. That's saving you some time. Okay, okay, 0:16:25.600 --> 0:16:28.920 Well here we are in the present day. Yes, what 0:16:29.120 --> 0:16:33.160 are some of the big distributed computing projects or volunteer 0:16:33.200 --> 0:16:37.760 computing projects out there today? And how are they actually 0:16:37.800 --> 0:16:40.320 making a difference? Like is this just kind of a lark. 0:16:40.440 --> 0:16:42.720 You know, Oh, that's kind of fun, you can participate, 0:16:43.200 --> 0:16:46.920 or does this actually impact science in a meaningful way? Well, 0:16:47.040 --> 0:16:50.160 let me answer that second question first, because it's certainly 0:16:50.280 --> 0:16:52.440 impacts it in a meaningful way. You know, like we 0:16:52.440 --> 0:16:57.000 were saying, access to supercomputers and grid computers, that's something 0:16:57.040 --> 0:16:59.760 that if you're incredibly well funded, might not be an 0:16:59.760 --> 0:17:02.160 issue you. But there are a lot of science projects 0:17:02.200 --> 0:17:06.240 out there that are doing amazing science on very limited budgets. 0:17:06.480 --> 0:17:08.840 And so for this kind of model to come along 0:17:09.359 --> 0:17:13.040 for specific types of problems, particularly science projects where you're 0:17:13.040 --> 0:17:16.040 generating huge amounts of data and then you have to 0:17:16.080 --> 0:17:19.679 analyze it, it's an incredibly useful tool. And it also 0:17:20.040 --> 0:17:22.640 not only is it meaningful in that sense, it's meaningful 0:17:22.640 --> 0:17:25.400 in the sense it gets people involved in science, even 0:17:25.440 --> 0:17:28.480 in a passive way. You start to learn more about 0:17:28.600 --> 0:17:31.120 what your computer is being used for one the purpose 0:17:31.200 --> 0:17:34.920 of that scientific project is, and that encourages scientific literacy, 0:17:34.960 --> 0:17:37.920 which I think is incredibly valuable. Yeah, so it's partially outrage. 0:17:37.960 --> 0:17:41.040 It's it's not just getting stuff done. It's also saying, hey, 0:17:41.119 --> 0:17:43.520 you can be a part of this, and also look 0:17:43.520 --> 0:17:45.959 at this cool thing that we're learning about Yeah, like, 0:17:46.160 --> 0:17:48.880 you know, the universe is mysterious. You want to help 0:17:48.920 --> 0:17:51.400 but be less mysterious. Yeah, you know, it's kind of 0:17:51.640 --> 0:17:53.800 kind of the way it boils down. And a lot 0:17:53.840 --> 0:17:57.679 of these projects are all folded under the umbrella of 0:17:58.080 --> 0:18:01.960 the Berkeley Open Infrastructure for Network Computing, which has a 0:18:02.000 --> 0:18:05.040 great acronym. You want to say it, Joe, you know, 0:18:05.119 --> 0:18:12.840 you want to say it bow wink, blink blink. It 0:18:12.880 --> 0:18:15.960 doesn't actually it's not. The full thing isn't blink with 0:18:16.000 --> 0:18:18.720 a C, but it is blink that has a C 0:18:18.880 --> 0:18:21.440 at the end of it. Um. But it's just fun 0:18:21.480 --> 0:18:23.720 to say, and so I'll probably try and say it 0:18:23.760 --> 0:18:26.280 as frequently as I possibly can. Well, this is sort 0:18:26.320 --> 0:18:30.120 of an umbrella program. Yeah. Yeah. It actually started as 0:18:30.160 --> 0:18:32.800 a specific platform for one of the programs will talk 0:18:32.840 --> 0:18:35.800 about in the second But what happened was it was 0:18:35.880 --> 0:18:40.000 such a useful approach that got adopted for other programs 0:18:40.000 --> 0:18:43.360 and now it serves as this umbrella where you can 0:18:43.400 --> 0:18:47.120 go to the Blink website and see all sorts of 0:18:47.160 --> 0:18:51.040 different projects listed underneath. Yeah, there's a few of these 0:18:51.119 --> 0:18:54.359 kind of infrastructures out there, and and this one is 0:18:54.400 --> 0:18:57.200 really cool because it's definitely run by by Berkeley, who 0:18:57.200 --> 0:19:00.680 are good people and and don't really have much of 0:19:00.359 --> 0:19:04.560 a profit factor in it. This is more by night. 0:19:05.560 --> 0:19:09.120 It's it's definitely more about enabling people to do science 0:19:09.200 --> 0:19:13.240 right and less about we've made this incredible platform that 0:19:13.320 --> 0:19:16.200 you can use for one low price of five million 0:19:16.240 --> 0:19:20.399 dollars or whatever. UH. So it's it's really cool. I 0:19:20.800 --> 0:19:23.920 blogged onto it the day that we're recording this podcast 0:19:23.960 --> 0:19:27.399 November four, two thousand and fourteen, and saw that there 0:19:27.400 --> 0:19:31.920 were about forty projects listed under Blink. I know that 0:19:31.960 --> 0:19:35.240 there that changes. There are times when there are many 0:19:35.320 --> 0:19:38.640 more uh and some of them actually were offline when 0:19:38.680 --> 0:19:42.320 I looked into them, probably for actually maintenance for for 0:19:42.359 --> 0:19:46.400 several of them, because you're talking about a fairly complex system. Ultimately, 0:19:47.320 --> 0:19:50.040 the way Blink works is that you've got a master 0:19:50.200 --> 0:19:54.280 system that kind of determines what the job is, sends 0:19:54.359 --> 0:19:59.280 the various tasks out to the volunteer computers, uh, accepts 0:19:59.320 --> 0:20:03.240 the incoming tasks from computers that have completed whatever work 0:20:03.320 --> 0:20:06.480 you've given them, and then assimilates that into a meaningful 0:20:06.560 --> 0:20:09.240 way for researchers to look at. So all of this 0:20:09.400 --> 0:20:13.200 is going on behind the scenes. And meanwhile the volunteers 0:20:13.200 --> 0:20:17.959 computers are doing actual scientific work without really, you know, 0:20:18.119 --> 0:20:20.880 without necessarily you being aware of it. Some of them 0:20:20.880 --> 0:20:24.560 come with fun like screen savers, so you can kind 0:20:24.600 --> 0:20:28.160 of watch a graphical representation of what's going on with your, 0:20:28.600 --> 0:20:30.080 you know, the work you're doing. One of the ones 0:20:30.119 --> 0:20:33.280 we'll talk about has one of those. That's pretty cool. Well, 0:20:33.359 --> 0:20:37.480 let's get to the examples. Sure, so here's a fun one, 0:20:37.520 --> 0:20:42.199 steady at home. The search for extraterrestrial intelligence. Wait a minute, 0:20:42.400 --> 0:20:46.560 how can I search for extraterrestrial intelligence without a radio telescope. 0:20:46.720 --> 0:20:51.000 Well here's how, Joe. You can take data that was 0:20:51.040 --> 0:20:54.520 gathered by other radio telescopes and use your computers processor 0:20:54.880 --> 0:20:57.600 to analyze that information and look for anything that might 0:20:57.640 --> 0:21:00.400 be meaningful. Right, Because the thing is is that when 0:21:00.480 --> 0:21:03.320 you know these telescopes are searching space, there's no like 0:21:03.640 --> 0:21:07.680 big red light that starts flashing when when something, oh, alien, 0:21:07.760 --> 0:21:10.040 it's right there, it's right there. We just found the 0:21:10.119 --> 0:21:13.840 Venusian elvis. No, I guess what we end up with 0:21:13.960 --> 0:21:16.159 is a lot of numbers, a whole lot of numbers 0:21:16.160 --> 0:21:18.440 that need to be crunched, and so your computer can 0:21:18.440 --> 0:21:20.879 crunch part of them. And so it wouldn't have a 0:21:20.880 --> 0:21:24.000 red light, but your computer might be the one that says, hey, 0:21:24.200 --> 0:21:27.080 here is an anomaly in the data. Right, wonder what 0:21:27.160 --> 0:21:30.480 that means? Right, And that's it really is, looking for 0:21:30.520 --> 0:21:33.800 those kind of anomalies and trying to flag them so 0:21:33.840 --> 0:21:36.560 that other people can take a closer look and see 0:21:36.600 --> 0:21:39.280 if there's actually any signal inside the noise. Because as 0:21:39.280 --> 0:21:41.680 we know, there's lots of stuff out there in the 0:21:41.760 --> 0:21:45.240 universe that generates radio signals. So just because you pick 0:21:45.320 --> 0:21:47.760 up yeah, yeah, you might get up stuff from a pulsar, 0:21:47.840 --> 0:21:50.080 which is already super cool. The fact that you know 0:21:50.160 --> 0:21:54.280 your your computer is working on data generated by an 0:21:55.119 --> 0:21:59.360 extrasolar body that could be light years across from us. 0:21:59.400 --> 0:22:02.720 But obviously that's not the same as Venusian Elvis, which 0:22:02.760 --> 0:22:05.199 is what our real goal is here for CET. But 0:22:06.280 --> 0:22:08.880 that's the thing is that with all that kind of information, 0:22:08.880 --> 0:22:10.240 it's the same sort of thing that if you were 0:22:10.280 --> 0:22:14.479 to have a massive telescope look deep into space and 0:22:14.560 --> 0:22:19.520 slowly do uh pans across the night sky looking at 0:22:19.680 --> 0:22:23.560 every single teeny tiny bit of that space to look 0:22:23.600 --> 0:22:27.040 for meaningful things, would take forever. Same sort of thing. Um, 0:22:27.040 --> 0:22:30.399 it's really dividing up this massive task among lots of 0:22:30.400 --> 0:22:34.240 different computers to make it more manageable, because otherwise you 0:22:34.240 --> 0:22:37.640 would just keep gathering data and it would pile up, 0:22:37.920 --> 0:22:40.080 and you know, you would always be playing catch up 0:22:40.200 --> 0:22:43.639 and always falling further and further behind. So that's the 0:22:43.680 --> 0:22:46.919 purpose of SETI at home. Then you have other projects too, 0:22:47.119 --> 0:22:49.879