Big Compute - From Supercomputing to Supersonic

Episode Date: February 11, 2021

It’s been about two decades since the Concorde flew passengers across the Atlantic at supersonic speeds, and if it were still in operation today, a ticket would cost you around $20,000.  Some saw the retirement of the Concorde as the end of supersonic commercial air travel, but undercover superhero Blake Scholl of Boom Supersonic plans to break the sound barrier with passenger travel once again by 2030, with dreams of creating a new normal.  In this episode, we hear parts of Blake’s BC20 speech about how his company is able to make this dream a reality through virtually unlimited high performance computing.  We also touch on the on-premises vs. cloud HPC arenas, and revisit the world before conferences went completely online.

One big supercomputing conference in the United States. Whoa, slurred speech. Hi, everybody. Hi, everyone. I'm Jolie Hales. And I'm Ernest DeLeon. And welcome to the Big Compute Podcast. Here we celebrate innovation in a world of virtually unlimited compute, and we do it

one important story at a time. We talk about the stories behind scientists and engineers who are embracing the power of high performance computing to better the lives of all of us. From the products we use every day to the technology of tomorrow, high performance computing plays a direct role in making it all happen, whether people know it or not. Hey, Ernest. What? Remember that long-ago time when people gathered together in person to, like, do anything, really, but to geek out over common interests like going to Comic-Con or CES? I mean, did you ever have a favorite conference

or convention? Absolutely. And there's three that I went to every year. Oh, really? Obviously, except for 2020. I go to DEF CON every year in the summer in Vegas, right? That's a hacking conference. PAX, there's two of them I go to every year. And then the last one is PRGE, which... What's PRGE? PRGE stands for the Portland Retro Gaming Expo. Oh. And it's exactly what it sounds like. Nothing but retro arcade machines, pinballs, and there's like an expo floor with nothing but people buying and trading retro video games. Do you think they offer joust? That was my all-time favorite when I was seven years old. They do. I need to go to this. Yeah. And the great thing about it is there's multiple rows of arcade machines and pinballs,

and they're all on free play. So you just come in there and play. That sounds amazing. No wonder you go to this. Well, for me, there's not one that I go to every year. For a while, it was the D23 Expo. Have you ever heard of that one? No, I haven't. It's the Disney Big Convention. And I've always wanted to go to Comic-Con or CES, but I never actually have. I would love to just people watch at Comic-Con, to be honest with you.

Plus, I'm a nerd at heart, and I'm sure I would get a kick out of a lot of the stuff there. Oh, yeah. But since this is the Big Compute podcast, it's also worth mentioning the many conferences that involve supercomputing or simulation in some way. And there's a ton of these, especially based around certain industries that use simulation. One big conference in the United States that many of our listeners are familiar with probably is the SC conference. SC standing for supercomputing. And they basically describe themselves as, actually I'll quote their website, the International Conference for High-Performance Computing, Networking, Storage, and Analysis.

And they've been going strong pretty much every year since 1988. In fact, Ernest, have you ever, I mean, it sounds like you've never been to an SC conference. Have you heard of the SC conference? I've heard of it. I've never been to it. Most of the stuff I've been to that's related to this is like Usenix and Interop type things, but I've never been to the SC conference. I mean, this year you couldn't have really gone in person, obviously.

SC20 went online like so many others, and I did get to be involved with some SC20 content creation, but that was pretty much the extent of it for me this year. And while conferences are doing the best they can, because obviously this global pandemic basically rendered in-person events defunct for a while. And I will say that for many of us, the experience just doesn't carry the same vibe when they go online. In fact, for you, Ernest, do you have a preference? Do you like attending conferences or conventions in person or do you prefer attending them online or virtually? So I think in my case, it's mostly a preference for in person. And that's mainly because the conferences i attend are mostly gaming related so i'm going with friends and we're you know doing stuff and so i would say obviously i prefer to go

in person for all the conferences that i would actually attend but there's plenty that i would never attend otherwise that i actually got to see online and And the other thing is PAX this year went online, obviously, because, you know, the pandemic and it definitely was not the same. And I lost interest fairly quickly. Gotcha. I think the first day I attended most of it, the second day, maybe half of it, and then didn't even bother coming back for the rest of it. So, yeah, it's unfortunate that online just doesn't carry the same sentiment or the same vibe that in-person does. Yeah. In fact, I was digging into this because I wanted to see what people prefer. And there was a study that I found that was conducted by Censuswide for PromoLeaf. And I'll link to it in the episode notes on bigcompute.org

because there's a lot of information that was really interesting in it. And it asked over a thousand people who have attended both kinds of events, so virtual and in person, and it asks them whether they preferred conferences to be in person or virtual. So, Ernest, do you care to guess what the results were? Well, when was the survey taken? Ah, why are you such an engineer? Like you're supposed to be like, well, I think it's this number. But of course, you need all the background information. So that's exactly the reason I'm asking. So the reason I'm asking the time frame here is because I'm certain that in the early on in the pandemic, the number was probably closer to 50 50. But the longer the pandemic dragged out, that number was probably closer to 50-50. But the longer the pandemic dragged out,

that number has probably shifted significantly towards in-person versus online because people were tired of being locked up at home. Yeah, and I had the same thought, but this particular survey that I'm talking about with 1,000 people who were surveyed was conducted on April 9th of 2020. So to your point,

that was in the earlier months of the pandemic at a time when conferences were just starting to go virtual. So just like you, I think it would be interesting to see if these numbers are different now. And I totally imagine that they would be. But the number was, are you ready? Yeah. It was more than 70% at that time preferred in-person conferences. Okay. So if we're guessing that that number is going up because people are getting sick of sitting on their butt at home, then it'd be interesting to see if it's like, what, 85 percent or something now. Now, that's just a guess. I have no idea. Or if maybe people really are enjoying staying at home, you know. I guess maybe when it

comes to these conferences, it probably just depends on the conference and if you're going because you feel obligated or you are obligated by your work versus going because it's interesting to you. For me, there's just something really cool about traveling to a big conference or convention because you're surrounded by thousands of people who have these similar interests. And there's this energy there that, I don't know, it can't really be duplicated over Zoom while you're sitting at home eating cornflakes and wearing second day socks. Absolutely. When you show up at a place like DEF CON or PAX and then you go to just a restaurant or a bar or whatever it is, there's no one there other than people who have the same interest you

do. Yeah. Who are from that convention. Right. And everybody's got their lanyards on or they're wearing their costumes if they're cosplayers. And they're like, you know, Wendy's. Yeah, and they're just sitting together talking about whatever the topic is of that convention. In this episode, I want to take us back to a time before an infectious microorganism that is 1 900th the width of a piece of hair pretty much affected the way 7.8 billion people lived on the planet. And if it's okay, I wanted to share some personal experiences surrounding my supercomputing themed conferences. So bear with me. I think we'll allow it.

Oh, thanks. Thanks, Ernest. So nice of you. So in November of 2019, because I'm relatively new to the tech industry, right? My first conference was in November of 2019, which was just weeks before the coronavirus first popped up in Wuhan. And I had the chance to actually attend SC19 in person, which is the supercomputing conference we referenced earlier. And I remember walking into the large exhibit hall for the first time and just being in awe of seeing these massive displays from these supercomputing behemoths

like NVIDIA, who, you know, I really love NVIDIA. I just put one of their new 3060 Ti graphics cards in my brand new computer build. I'm a big fan. And then there was like HPE Cray was there and these huge booths dedicated to these major tech companies. Pretty much every player in the high performance computing industry goes to the Supercomputing Conference. So at the time, I was there as a representative of Rescale, who, full disclosure, is the primary sponsor of this podcast. And we were focused on multi-cloud HPC, whereas now Rescale is more hybrid. Very cloud still, but also hybrid. But the impression that I got at SC19 was that while cloud HPC services did have a footprint

there, most of the conference was more about showcasing top-notch on-premises HPC hardware. And there was even this little bit of an underlying competitive culture between cloud-based HPC people and the kind of classic on-prem HPC people, as you might imagine. And there were strong opinions about both. I can only imagine. I have obviously been on both sides of that coin and I see that there are benefits to each side. Yeah. But, you know, it's like anything else, right? If you are primarily entrenched in one group, your view of things is kind of formed by that, you know, that group that you're entrenched with. Yeah, it definitely has a lot of influence on you. It kind of formed by that group that you're entrenched with.

Yeah, it definitely has a lot of influence on you. It kind of becomes a part of who you are in a way. And for me at the time, being from a cloud HPC company, and I wonder if actually some of our listeners will remember this, but in order to stand out amidst the ever-prominent hardware giant tech names all around us, my colleague Tanner came up with this idea to bring a special guest with us in hopes of making a memorable impression at this conference. Uh-oh. So, Ernest, I'm not sure what you're up to in 2019,

but have you heard anything about a guy named Clifford? I know of a big red dog named Clifford. No, this Clifford is a lot dumber than that Clifford. Okay. Well, no one's ever accused me of being a genius, but that's about to change. So Clifford was this character that we came up with, and he was this doofy janitor guy. I heard about these supercomputers,

which are just fancy machines that help the engineers get their work done in the building. I mean, I don't use any of them for my job. And he overhears an engineer talk about how supercomputers were going to the cloud. I'm smart enough to know that like if an aerospace engineer wants to shoot his arrows into space, he's going to want to do it from the cloud because it's closer instead of from computers down here on the ground. And he basically sees this business opportunity and decides to start his own hpc recycling business because he figures that hey if everyone's going to start going to

the cloud then they'll obviously need to get rid of their on-premises supercomputing equipment call gone prim we take all of your troubles and we get rid of them for you and he literally thinks it's the clouds in the sky. He thinks that everyone's going up to the clouds. That is great. I didn't know if you would think that was funny or just completely ridiculous. It sounds like such a Dilbert comic.

And it really was, and it was just meant to be so dumb. And it definitely accomplished that goal because it was so dumb. No more extra HPC stuff lying around. We dispose of those. Dispose of those. Dispose of those. That's right. I said it three times so that way you remember it. So Clifford starts this HPC recycling company and he names it gone prem because he can take your on premprem and make it gone-prem. So good.

Call gone-prem, the number one company where we get rid of your old stuff, company. And what better event to jumpstart his business than the SC conference, where he assumes that everyone's just going to have all this on-prem equipment that needs to be recycled if clearly everyone's going to the cloud. on-prem equipment that needs to be recycled if clearly everyone's going to the cloud. That is so amazing. I can imagine the faces of the people who are still selling

on-prem equipment. So we published a few short films about Clifford and gone-prem in these weeks leading up to SC19. And then this is the guy that we bring to this big supercomputing conference. And he's actually a really skilled improv actor who I've worked with a number of times before. And so he shows up at this conference equipped with these terribly designed flyers and like ugly this like giant box truck with his face and his logo wrapped around it that he conveniently illegally parks right out in front of the conference center in downtown Denver and then he runs around trying to pass out flyers and stickers to the masses of people trying to enter the conference many of whom actually recognized him from the short films,

but others had no idea what was going on. That's amazing. That beverage looks delicious. Would you like a delicious flyer there? If you were cycling any computers, I'm your guy. And this was all incredibly hilarious, but a little uncomfortable for me because I just want everybody to take it as the big joke that it's meant to be.

But you have to remember, many of the people attending this conference are, again, there to sell or purchase on-prem hardware. So Clifford's very presence is like kind of poking fun at their world. world and while a lot of people found him to be really entertaining I watched other people like literally run away from him at a full sprint or like look at him in complete disgust and eventually somebody did end up reporting him and Clifford was escorted off the property by security while remaining completely in character I might add good for him yeah it's awesome you're free to hand those out and advertise yourself as long as they are just past these right here will you remember the phone number i'll try my best and a lot of people would come to the rescale booth to get pictures with him and videos with him and we had a lot of like stupid swag and clifford was was meant to be

this like light-hearted and kind of stupid guy that you're not supposed to take him too seriously. And overall, most people didn't and they had a really good time. But for me, again, watching people interact with Clifford or do everything in their power to avoid interacting with Clifford, it really helped me see glimpses of like how closely our emotions can be tied to our technology, like you were saying. So like how willing we are to defend the tech that we believe in and that we use, whether that's attachments to our smartphone brand or a specific video game console, or in our worlds, the supercomputing technology that we believe in. Or cloud HPC versus on-prem. But I don't think that's as polarizing as Android versus

iPhone. And we could have a war here because I know that you and I are on either side of the spectrum and somehow managed to find common ground. I don't know how we do it. I think it's one of those things where we're adults. Are we? Well, sort of. Maybe you are. I've only been here a few minutes and I've already met the vice president. And since I was new and somewhat naive to this world when I went to SC19, I was kind of surprised by it. I really didn't know what to expect. And then when I got there, I was like, oh, my gosh, Clifford is offending a few people.

Not very many, very few. But there were a couple of people that he really rubbed the wrong way. And I mean, here on the podcast, like when it comes to cloud HPC or on-prem HPC, a lot of our recent stories here on the podcast have demonstrated a bit of both worlds, because I think we're starting to see more overlap these days, right? Like a hybrid or a combo. In fact, while there has been a lot written in the past about cloud HPC adoption not really taking off that quickly, I don't know about you, Ernest, but it seems to be changing a little bit. For example, I got a chance to take a peek at a new study conducted by the team here

at Big Compute where they asked HPC managers a lot of questions around this very subject. And the study found that 73% of HPC managers believe that their workloads will be mostly or entirely in the cloud in the next five years. And I can't help but wonder if the events of 2020 kind of pushed that number upwards as people had to, you know, work remotely. I agree with that. And the reason is because I think a lot of people don't realize where the cloud sits in terms of if you put this thing in layers, right? So to our listeners, it's going to be obvious that everything is on-prem in some context. Even when you're in the cloud, you may be consuming resources via a cloud, but that cloud is maintaining data centers with on-prem hardware. So it's on-prem

no matter what. It's how you're accessing it and how that hardware is configured. And so I think the evolution that's happening or the reason it seems like it has like a long tail and it's not picking up steam as fast is because you have this industry, HPC and supercomputing, which has been around for a very long time and has many, many tools written for it to run in a specific context. The cloud is kind of the evolution of that, but a lot of the tooling and the software packages have not evolved yet to that new model. Some have, but a lot of them haven't. And the other thing is HPC and supercomputing have some very specific architectures, designs, and things they're trying to accomplish

with a given set of hardware. And the cloud is very much trying to be multi-purpose and be able to be used by everybody. So it's one of those things where I think I agree with this 100% that 73% believe that they're going to be mostly or entirely in the cloud in the next five years. If you were to ask again in five years, I would push that number closer to 90, right? But it's an evolution, right? So it takes time for us to get from one point to the next point. And it also, by the way, we had the same exact situation happen when we went from on-prem, I'll call it regular computing, to the cloud, where there were so many system administrators, network administrators, who were just

defiant that this was not going to happen, and they weren't going to let it happen, and they refused to cede control. Part of it was a job security thing. But a lot of them eventually realized that it is better for you to offload so much of that maintenance and the cost and the time to keep all this stuff running and instead focus your tech people on your core business and not managing infrastructure because that's not your core business for most businesses and so i agree i think this is one of those things where that survey is on point and like you mentioned at the end of that 2020 really pushed that number upward because even if someone wasn't using the cloud before they now had to access these supercomputers through the cloud

or through like a vpn a through a VPN or something, right? Which they probably already did some of them, to be honest, but this forced the issues is what I'm saying. And now you have a bunch of people thinking like, well, hey, I was able to do all of my work sitting in my home office or in my kitchen or in my living room. Do I really need to be on-prem? And do I really care where these computers are located? And the answer is no, right? And I think that it's just a matter of time as people start realizing this, that you will eventually see all of this stuff make it into the cloud. And there are a few really cool stories of people who have leveraged this ginormous amount of compute that's available

when you're connected to a virtually unlimited hybrid HPC or mostly cloud kind of world. And that brings me to another conference that's related to supercomputing that I do want to mention here today with a lot of these really cool stories. And I want to talk about one. It's from the last conference that I actually attended in person, which took place on February 11th and 12th of 2020. Literally right before COVID waltzed in. Yeah, literally. I mean, the first case of COVID-19 was confirmed by a lab to be on U.S. soil on January 22nd.

But then California didn't start actually locking down until March 19th. So in February, it was still pretty much business as usual with this big like question mark hanging over everyone's heads. Right. But it was actually our own inaugural Big Compute conference. It is my pleasure to be here with you at Big Compute, which was created to celebrate the possibilities of what can be done with virtually unlimited compute resources we're really getting to that point where we're only limited by our imaginations in what we can do so another way to look at it is the in-person speaker series version of this podcast so there were these presentations that were given in story-based kind of TED Talk styles. And I had the opportunity to be the emcee, which made it possible to rub shoulders with some pretty amazing thought leaders. Ladies and gentlemen, Sam Altman, CEO, OpenAI. It turns out that the most impressive advances that we've had in the field of AI research,

I think, have been more about massive compute than massive data. So BC20 was particularly cloud HPC focused. So sponsors included cloud service providers like AWS, Microsoft Azure, Intel, Google Cloud. And then there were simulation software companies that ran in the cloud like Siemens, Ansys, Convergent Science.

And then of course our presenting sponsor of this podcast, Ansys, Convergent Science, and then, of course, our presenting sponsor of this podcast, Rescale, which kind of ties them all together. And that's how I got involved. And speakers consisted of thought leaders like Sam Altman of OpenAI and then innovators from like life sciences, aerospace, automotive, pretty much every field that uses supercomputing. And we actually hope to bring the conference back once this pandemic finally plays itself out. So, I mean, that's kind of an alert to all of our listeners

that we'll keep you posted on when our next conference hits the calendar. In case you'd like to join us, we'd love to see you there. And one particular cool talk that was given at the conference is one I want to spotlight today. And it was done by blake shoal who is ceo of boom supersonic is it weird that i that i kind of want to hear a big boom noise every time i say boom supersonic so it's like boom supersonic it is a little weird but as someone who was once a fan of comic books this was common to write words like boom.

And you just had to imagine the sound in your head. So we were kind of we were conditioned to do this. Awesome. Well, then maybe I'll just throw that in when I'm editing this. Wait, you should say you've got the deep voice. Boom. Supersonic. Oh, that's so good. I think that needs to be a thing. I'm totally going to use that, by the way. Boom. Supersonic.

If you're listening to this, you've probably heard of them, or you're going to want to maybe look them up afterwards because they're pretty awesome. Their popularity has been steadily increasing, and it's really no wonder why. I mean, they're literally creating supersonic airplanes, which is pretty rad. Right. And there's a lot of history there, right? Remember that the Concorde used to be a supersonic passenger aircraft that was eventually decommissioned because of issues, reliability and otherwise. That's like totally the next page of the script. Oh, I didn't read it at all.

Shut up, Ernest. I didn't read it at all. Stop being smart. That's funny. At Boom, we believe that life happens in person and that real FaceTime beats FaceTime. And so our vision is to make the world dramatically more accessible

by removing the barriers to travel, which are principally time, money, and hassle. If we can chip away at those, we can build a world where more people can go more places more often, which is going to be a better planet for all of us to live on. Supersonic basically means faster than the speed of sound. Or faster than Mach 1, which is approximately 768 miles per hour, like in average conditions at sea level.

But Boom Supersonic isn't just aiming for 768 miles per hour. They are working toward creating a commercial aircraft that will fly around 75-ish passengers at Mach 2.2, or 1,429 miles per hour, which kind of smashes the speed of sound. And since typical flights these days fly around 550 miles per hour, you can see how impressive 1,429 miles per hour is in comparison. Yeah, it would get me home in around an hour, I think. I think as the crow flies, where I'm at to my home is around 1,400 miles. So flying home.

It's like a perfect. Yeah. Imagine like, oh, I need to go to work in the city this week. So I'm just going to fly in in the morning and then fly home at night. That's amazing. Yeah, that'd be like your commute would take less time than most people's commute. In the car. Yes.

In California. Well, yeah, because this is California. This is just one other way that supercomputing is in the car. Yes. In California. Well, yeah, because this is California. This is just one other way that supercomputing is changing the world. And one way out of so many ways that people don't even know about, right? So Blake and his team are definitely undercover superheroes, although with

all the media attention that they've been getting lately, they're pretty much being unmasked. We have been following developments at Boom Supersonic for the last several years boom supersonics will reveal the prototype of its supersonic jet that promises to bring back faster than sound passenger travel we'll see what happens after they go through the test flights and they start manufacturing this supersonic jet now it's my understanding that supersonic flight is not completely new. Wasn't there, you know, an aircraft that was once used for this that had reliability issues? You mean the Concorde you mentioned earlier?

That was very diplomatic and kind of you to bring it up in that way, even though you already knew that was coming. Yeah. Thank you. Yes. you already knew that was coming yeah thank you yes so before i talk about the concord so the first airplane to actually fly at supersonic speeds was a bell x1 rocket powered research plane as you probably know it was piloted by chuck yeager and he does it the first human to crack the sound barrier this flight marks the first milestone in the supersonic chapter in the history of aviation and breaking the sound barrier was a big deal but it didn't mean that supersonic travel was

possible on a commercial level right until the concord you should say the concord like you say boom supersonic in your radio low voice. The Concord. Yes! Although the development of the Concord didn't exactly go as planned. And I'll tell you what that means after the break. Just going to leave us hanging like that. Every time. From supersonic jets to personalized medicine, industry leaders are turning to Rescale to power science and engineering breakthroughs. Rescale is a full-stack automation solution for hybrid cloud that helps IT and HPC leaders deliver intelligent computing as a service and enables the enterprise transformation to digital R&D. As a proud sponsor of the Big Compute podcast, Rescale would especially like

to say thank you to all the scientists and engineers out there who are working to make a difference for all of us. Rescale, intelligent computing for digital R&D. Learn more at rescale.com slash bcpodcast. so we were talking about the first supersonic commercial aircraft the concord i love that so the concord was a supersonic jet that was actually built as a joint venture between the French and British governments in the 1960s. And it was sort of a way to show that Western technology was better than Soviet technology at the time. And it took its first flight in 1969 and then its first supersonic transatlantic flight in 1973. And then it started regular passenger service in 1976, which continued all the way through 2003, which I actually did not realize it was that recent that it stopped flying. Yeah, I remember seeing an article about them decommissioning it finally.

Just after one o'clock, Concorde's final landing. And as far as speed goes, it had a maximum speed of Mach 2.04 or 1,354 miles per hour. And it seated around 100 passengers, I believe. And while the Concorde was pretty amazing, obviously, it was a gas guzzler. And when you consider inflation, a round trip ticket for a flight from New York to London on the Concorde today would cost you around, get this, $20,000. That is a lot for a standard passenger aircraft. And this is crazy, okay? So you mentioned that it had some troubles, right, the Concorde. You're completely right. Apparently when the project was proposed, it originally estimated that the Concorde is going to cost around $70 million to

develop, right? But then it actually ended up costing $1.3 billion, which is almost 1,800% more expensive than originally estimated. A year late, millions of pounds over the estimated cost and still a very big question mark. These were Concorde's so late and expensive because it was developed before computational simulation on this kind of a scale was anywhere close to practical. So it had to be tested in physical wind tunnels where every single iteration, so every little change in design, cost literally millions of dollars and took months. So as you can imagine, there were a lot of delays. But now with high performance computing, a lot of that development can be done quickly through computational simulation.

Right. Now, there are all kinds of phenomenal simulation softwares that can closely duplicate real life elemental testing like physics or materials, temperature, fluids, vibration, pretty much everything you need to test for while developing just about any product out there, including supersonic airplanes. And when you combine the ability to run these simulations with high-performance computing that can power all of this research in the snap of a finger, depending on how many cores you use, it's no wonder so many amazing products have been developed in the last couple decades. And that's what's allowing technology like Boom Supersonics aircraft design to progress at incredible speeds without spending millions of dollars per iteration. We've changed virtually everything about how we design and build aircraft. From an aerodynamic perspective, we've gone from developing in wind tunnels, where every iteration takes months and costs millions of dollars, to being able to do things in computer simulation, where you can test more iterations and arrive at a more refined, more efficient design. We have new materials. We've gone from principally aluminum to carbon

fiber composites, which means you can build a strong, lightweight structure that can better withstand the stresses and temperatures of high-speed flight. Propulsion has completely changed. As you may know, if you're an airplane geek, Concorde was the only passenger airliner ever to fly around with afterburners. And if you're an airplane nerd, like I am, afterburners are cool. They're rip-roaring loud. There's a flame coming out the back of the engine. You can't miss them when they fly over. But if you're an airline or a passenger, you maybe don't love them because they're loud.

They bother people on the ground. The flame is kind of scary. And most important, they're incredibly fuel inefficient. And so today we have totally new kinds of engines called turbo fans that are quieter and more efficient. And commercial supersonic travel is especially important if you're someone who travels a lot, because it can literally cut the length of your trip in half, which means that an international round trip for a business meeting,

once we're able to have those again, might be able to take place within a single day, giving you much more time to spend with your family. And to me, that's why this kind of technology is so important. Yep. That's what it's all about. We've gone from being able to design on drafting paper to being able to do all kinds of design in CAD and then simulation, allowing us to test our designs faster, to iterate faster and arrive at a more efficient aircraft. So at Boom, we're putting all that together to build a new, more efficient, most affordable ever supersonic airliner.

And I feel very lucky to have fallen in love with this problem at a time where you can actually do something about it. Not only has the technology advanced since Concorde, but the market has also grown. Since Concorde retired in 2001, there's actually been a doubling in international air travel. And what that means is there are 65 million passengers per year flying on routes in business class where we can offer them nearly a doubling in speed. That turns into a $200 billion opportunity for Boom, which means despite the capital intensity of this effort, there's a great return for investors there, and we're actually able to build a business. So at the intersection of proven technology, proven market, supersonic travel is truly inevitable. It's only a matter of time. So to safely create a commercial supersonic jet, Blake and his team at Boom Supersonic have developed a smaller version

of the aircraft to test first. And that aircraft, which was physically rolled out just a few months ago, is called XB-1. And can I just say, this is a total side note, but from a filmmaker's perspective, their XB-1 rollout video was incredibly well produced. It was like the kind of video that I watch and think, dang, I wish I had made this. So if you haven't seen it and you're listening to us now, it's worth going online, taking a look. BoomSupersonic.com plug for these awesome people. But anyway, the airplane is even cooler than the video. Now, how do we know this is all going to work?

Well, it's about testing both digitally and in physical hardware. One of the first things we built was a flight simulator. And this takes not just wind tunnel data, but a tremendous amount of output from simulation. We've done about 66 million core hours of computing, mainly through Rescale. Shameless sponsor plug. Since we started the design effort on XB1. And if you ask yourself what that would look like in wind tunnel testing, it would be financially and time-wise just absolutely impractical.

We've been able to test hundreds of iterations of aircraft designs, which you just could not do with wind tunnels. We've gone to the wind tunnel just three times for XB1 to get calibration data, to confirm that we're calibrated in CFD, and then to get a final sign-off of the exact design that we're shipping. We've also done engine testing. So XB-1 uses off-the-shelf General Electric engines, and we've been able to take them down to the U.S. Air Force Academy

just about 45 minutes south of our office and get them running to full power. And we're really proud that we're able to do this on sustainable biofuels. So supersonic aviation is not just going to save you time. It's also going to be good for the planet. And while XB-1 looks frigging awesome, it's just a step toward Boom's primary goal, which is to create the 75-ish seat commercial supersonic jet they're calling Overture.

When you look back in history, it's easy to underappreciate how much aviation has done for the planet. Isn't it interesting that we haven't had a world war since the dawn of the jet age? When you reduce travel times, people go more places more often. There was a six-fold increase, for example, in travel in the first 10 years of the jet age to places like Hawaii that were previously inaccessible and we think that Overture will kick off a similar similar growth in air travel and similar increasing of

accessibility of earth we want to live in a world where our children have not just read about places like Cape Town and Tokyo and Mumbai and a textbook that have actually been there. Imagine what it's like when everyone has experienced the wonderful people, places, and cultures our planet has to offer. And Overture is the first in the series of aircraft. We're going to continue to build them larger, more efficient, quieter, and more environmentally friendly. And I think in our lifetimes, we will see a world where every flight over about a thousand miles is supersonic.

And Blake believes that flights on Overture will be available in the year 2030, which might feel kind of far away, but that's actually pretty soon considering the task ahead of them. And if you take a look at the Overture renders, not only are Blake and his team raising the bar in like flight technology,

but they're raising the bar on the whole flight experience. To be honest, parts of flying, especially if you're in economy, can feel like a little bit of a demoralizing experience because you give up all control and you give up personal space at the same time. And then you're just hoping that your personal belongings don't end up going to Guam or something without you. And then more and more seats these days are being packed into smaller spaces so there's less leg room. And then nowadays you also have to have like a 26 hour flight to get any kind of meal on board a flight in economy.

It's just so much different than it was when I was a kid. Absolutely. Even six hours or four hours in a cramped situation can be pretty bad. It can be rough and feel a little demoralizing, I think. I mean, of course I say that. And honestly, I should probably check myself and stop whining if I really take a step back, because I mean, even if the entire experience of flying economy is somewhat unideal, I have to remember that I'm literally boarding a giant metal machine that flies through the sky. And then it gets me to the destination I need to go to in this incredible timing. I mean, I'm sure that my pioneer ancestors who trekked across the country

in ox-pulled wagons would probably be happy to trade a bumpy ride behind the butt of a couple animals for like an armrest free middle seat of a modern airplane. I don't know if that's true. You don't think so? You'd rather ride behind an ox butt? I don't know if I'd rather ride behind an ox butt, but I just don't see those people being comfortable on an airplane regardless of the situation. They probably think it was some kind of like evil magic or something, you know, like a metal bird.

You know what I mean? Like it's that kind of, because they have no idea, no concept of what this is, right? There's a no compromises passenger experience on board Overture as well. So we're starting from a blank sheet of paper, re-envisioning not just the airplane, but also what it will be like from the moment you walk onto the aircraft, the moment you step off. So we're building a nice, comfortable seat, plenty of room to spread out, relax, do work. And my personal favorite feature is a cup holder that's nowhere close to where you put your laptop.

So if you look at Overture's renders, each passenger seat has its own personal space. So there's like no fighting over armrests and everybody gets the window and everybody has leg room. And I'm sure that a ticket will probably cost more than a seat on Southwest, but maybe Boom Supersonic will be able to change how flight is done for the masses too, like over the long run. I've got my fingers crossed that maybe Boom Supersonic will become the supersonic version of Boeing or something, you know, and that this technology will just continue to spread over the earth until it becomes the new normal. Yeah, I mean, it's all about the economics, right? So if they're fitting 75 people in this aircraft and Southwest is fitting, you know, 130 ish, a hundred and I

forget exactly the number, but almost three times that, you know, pound for pound, the cost would be roughly two and a half to three times a Southwest seat. But if boom can go significantly faster than a Southwest plane using less fuel. You could do more flights. You can do more flights at less cost. And then maybe you can get it down to like maybe one and a half or two times the cost of the Southwest seat. And then to go beyond that, the 75 seater is really kind of their first passenger airplane, right?

So maybe it could expand in size even beyond that. So I think there's just a lot of opportunity for Boom Supersonic to really do something cool here. And so it seems the world now is really watching Boom Supersonic so that we can see how this goes, right? 2030, that airplane might be in the sky. And so far, things have been going really well. And I think they're going to do what they set out to do. And that could really change the world. Wholeheartedly agree. I also have seen the renders and to me, everything looks great.

Right. The only question is going to be the cost per seat in a commercial flight context. And I think that using innovative technology to lower the cost of development, lower the overall cost of manufacturing of the aircraft, get the best possible fuel economy out of it, will make that number more and more attractive to airlines to offer as like a commercial, you know, a commercial service. So I'm really hoping they succeed for my own benefit, not even for. I know for selfish reasons. I'm like, yeah, I'm like, they're going to change the world, meaning I might be able to get to Europe in a few hours. Could you imagine getting to London in like an hour? Oh, that'd be awesome. The technology is going to definitely change the world.

But man, if they hit the right economic balance, they will change an entire industry. And I've got to say, as far as thought leadership goes, the energy in the room when Blake was talking at the Big Compute conference was really exciting. And you could really feel this cool vibe in the room. And that was something that I do miss from being in person at these conferences. So I'm really looking forward to seeing that again. But it was just cool to see how people were hanging on his every word. Maybe he can give us an update at the next one and, you know, a seat on one of the inaugural flights. Oh, yes. Please, Blake. Maybe not the first flight.

Go on like the second. The second one. So for our listeners, Blake Scholl's full talk is available on bigcompute.org if anyone wants to watch it, along with some links that we'll post to topics that we've mentioned on our episode notes page. So some of those ridiculous Clifford videos we'll also include there. And kind of interesting, the Big Compute podcast actually did a 20-minute interview with Boom Supersonic, actually interviewed co-founder Josh Kroll way back at episode three. So before Ernest and I had any knowledge that this podcast even existed, Boom Supersonic was a guest on this podcast.

So really interesting interview worth listening to if you want to hear more about the background of this awesome company. We've got a lot of great content coming up on the podcast and website, including some talk on the SolarWinds hack. We've also got some heartwarming stories about how supercomputing is literally saving children's lives. I'm so excited for that one. It is the coolest story. And of course, if you want to help spread the word about the Big Compute Podcast, you can write us a review or tell a friend or do both. Our community is quickly growing and it's really cool to be a part of that. Thank you to everyone out there. That's going to do it for this episode of the Big Compute Podcast.

Until next time. Stay safe. Thank you.