>>from the Cube Studios in Palo Alto and Boston connecting with thought leaders all around the world. This is a cube conversation. Hi, I'm stupid, man. And welcome to a cube conversation. I'm coming to you from our Boston area studio, and we're gonna be talking about the networking giant. So, uh, joining me is the first time on the program some of the members been on and the cover launch of Pensando so vivid Jane, his CTO and co founder of Pensando Bipin thanks so much for joining us. >>Thank you. It was very nice talking to you. >>All right, so in a big theme we've been talking about for a number of years now is multi cloud. And, you know, I go back and think about you know, that the concept of cloud and even, you know, I've been around long enough You think about the and one of the challenges you look at is well, security is always a challenge. The other things network bandwidth is not infinite. The speed of light has not been solved, though you know, help us understand is you know the first I guess give our audience a little bit of your background. As I said, anybody in the networking world knows less team, though. Tell us, you know, have you been on the journey with them for all of that? Or And you know what brought you and Sandy? >>Yes. Yes. Um, I mean, I've been in the journey with the team since 2000 and six, so it's pretty long, I would say 14 years now, and it's been tremendous. Um uh, at heart, I'm an engineer who takes, you know, Brian brilliant things and taking upon challenges. And I've got multiple startups before this been in a new era, The more startups before that. And of course, you know, they were not experience more independent startups. And, you know, all through the course, I have gained appreciation for, like, you know, starting all the way from silicon to build a distributed systems and a u io all the way up to the fully consumable, you know, system. So I I totally understand the the angle I need to look at this time in a holistic manner. Having contributed to Cisco, UCS of and Nexus products on. Before joining pensando, I was, um I was contributing with my own open source container networking project, which is quite exciting to see How do you evangelize, You know, my own my own core, and that was fun. And that's where I come from, But, uh, but I I'm I'm a software engineer. To start off it started contributing to a six, then started going into the application world with containers trying to pull a container networking with, Ah, we did a server product with Cisco UCS and on and pretty much all over the stack with respect, participation. So that's my background. Um, but it's being exciting to consider what's next for me. And I was largely trying to see >>so, so definitive, actually, if I If I could jump in there, right, you know, I think back the UCS it was, You know, some of those ways I gather virtualization had been around for quite a number of years at that point. But, you know, how do you optimize it you're in. How do you transform infrastructure toe live for those environments, though? You know, UCS, You know, remember, people get back saying, you know, Cisco getting into services like Well, they are. They are because they're changing that compute model really caught that. You know, Cisco led that way. If the urge instructor, so many things you talked about that we'll get to later in the interview open for station. When I look out today, you know infrastructure's paint a lot and cloud obviously, is a huge impact, but also the application. So help us understand kind of the the waves that were writing together And, you know, what was it that you know in Santo decided to build in order to meet what you know, the customers of a require >>Um So I think, you know, going back to the UCS common that you had We started off thinking, for example, what are what were the challenges with respect is scaling out the deployment of servers and we quickly realized that manageability is number one challenge on. And of course, you know when we speak about manageability, it comes down to the underpinnings of what you're building. Are you Are you able to see the entire infrastructure together, or are you still seeing those big pieces? And that's when I think UCS was born to say that Look, we need to bring everything together that could be consumed in a holistic manner. And for that you have to have all those components there are There are somewhat independent to be consumed as a unified thing. And which is why I think it was a unified computing system. UCS. Um and then I think, you know, and Sanders a journey that takes it to probably not just that concept, but in general, the the challenges and the disruptions that we're seeing to the next level. So, I mean, just to summarize, I would say we started off looking at all the disruptions that are happening in the industry. And there are many of those I'm happy to talk about, which means we looked at, uh and then we looked at What are the consumption models that people are largely, you know, finding it very appealing these days because the days in which you're going to write a spirit to do something is still pretty old you want to be able to consume and most this after consumable way, How can we build, you know, how can you build systems that are programmable in the field? Those kind of things? The consumption model reliability software is the friendly factor there, and highly appealing to you guys and all their last one. You know, at least we also we also wanted to be really heard in the game, competitiveness wise. So those were like the the overarching set of things there that we started to think about, like, what descriptions are we going to solve, um, and how the consumption model needs to be for or ah, for the future of infrastructure. And how can we get that key, which is which is far ahead and better than anything that exists out there? So that's where we started to look at. Let's bring something which is bigger B sphere and and something. Even if we have the possibility of feeling it. Let's go ahead and they're doing their anything. >>Yeah, and absolutely. There's been so much discussion over the last decade or so about about software's eating the world and what's going on there yet you know, your your team mates. It's a lot of times it's been the chip set. There have been some huge ripples in the industry, you know, major acquisitions by some of the big, disruptive companies out there. Apple made a silicon acquisition, you know, everybody paid and that will have. You can't talk about disruption today without talking about Amazon. And, of course, when Amazon bought Annapurna Labs, you know, those of us looking at the Enterprise and the clouds base was like, Keep an eye on this. And absolutely, it's been something over the last year or so now, where we've seen Amazon roll things out and, of course, a critical component of what Amazon's doing from outposts. So with that as the stage there, you talked about wanting to be interesting leading, you know Amazon, you know, is really sick, and it's setting the bar that everyone is measured against. And when I look at the solution pensando, the kind of best comparable analogy that we've seen is, you know, look at what Nitro chip can do. This is an alternative for all of the other 1000 for customers that might not want to get them from Amazon. Is that a fair comparison? And how would you line up what founder is doing compared to what Amazon has done there? >>Um, so you know, what you've seen in the Amazon announcement really is possible. Amazon is a great benchmark to beat eso No make mistakes. We are very happy to say that, you know, we are We are doing by comfortably so But then, you know, Amazon is more than more than just the just the chips that are that they are building. I mean, what you consume is what they're building and underneath the engines are really part up by by the nicety off all these things that they're very, um, having said that, you know, And Sandra was consisting off both the you know, it's recognized us as a team which has been in traditionally building chips. But yet I think you know, the the Iot or the the previous venture from Mpls Team was somewhat of an eye opening as to how bringing things together is much more value in op, ex and and simplifying things is a huge, huge value compared to just putting performance and those things. So why this is important? That is another aspect which is important in trying to simplify things and make it consumable like software. And Sandra itself has probably, you know, I would say, Ah, good chunk, like about 60% of people in software team and not the, you know, basic harbor t This is not to say that, you know, we, you know, we are under emphasizing one versus the other. Software is a bigger beast when you start trying to build all those programs on a programmable and doing that here and start to roll out those applications on. So that's why I think the emphasis on software is there. Having said that, you know, it's the software that runs the data path pipeline. There's also a layer of software that we're building that can help manage all you know, all the product in a more cohesive manner and unified. >>Okay, that's Ah, thank you for laying that out. You mentioned you've got some background and open for definitely an area where, for a number of years, you know, Amazon has not exactly, uh, open source. Not exactly been a strength for AWS. They have put a lot of effort. They've done some president IRS over the last couple of years. >>And >>how do you see open source fitting into the space? What is I kind of the philosophy of pensando when it comes to open source. And where do you see it playing in the You know, this network piece of the multi cloud. >>Yeah, no, I think it's It's ah, it's a squared, relevant in a way that you know of the cloud native movement on how applications with very Onda normalization of AP eyes across multiple clouds. Israel, We are all seeing the benefits offered. And I think that that trend will continue and which is all driven through open source Ah, you know, community that exist in, you know, in the heart of the word. So personally for me, I think I learned a whole lot of things in the open source community. You know, the importance off evangelizing whatever you're working on, the reason to have convinced other people about contributing into what you're working on on. Frankly, I also learned how difficult it is to make revenues in an open source based part of that strategy. So I think you know that those were the things that I got away from it when I was doing my own open source project of container networking. Um, but at the same time, pensando, uh, you know, we have to make sure that we are 100% aligned with anything that's happening in open source. Never replicated, Um, anything that might be that might be happening in open source instead tried to make people use those things in the best possible way and in the most efficient way and the easiest possible way to use those. So our strategy largely is that, you know, embrace open source which exists are there from an infrastructure point of view, we are collaborating and communicating with less of the users are Hello. I think we're going to standardize most of things we're looking in before community. So our stands largely is that, you know, if we are building a programmable platform than the community is what is gonna driver and we are very much working towards a step by step, of course, trying to get through, you know, a stable state where we could we could not just empower people who are who are taking up the open source efforts which are going on. But at the same time, we can also contribute our program are programs into the open source community and defining the right abstractions into into the community. Um, because we came out of stealth pretty recently, you'll start seeing that and helping those activity as Well, >>excellent. Well, you know the launch of Pensando you had a phenomenal lineup. Not only you know, John Chambers obviously has the relationship with your theme, but you know, oh, am partners of Hewlett Packard, Enterprise and IBM, as well as the Marquis of Goldman Sachs. Things look a little bit different in the first half of 2020 and then they didn't end of 29 teams. So, you know, curious, You know that the global pandemic, the rippling financial implications, you know, what does that mean? The pensando. How has that impacted conversations that you're having with your >>Well, one thing I know at a broader level, let me cover, um, where things are heading. And in that sense, you know, I see that network and the infrastructure in general cloud infrastructure networking it's going to become. And we have realized it's this during during during recent early 20 twenties that that is going to be very important to have the have a new underpinning infrastructure that is not just working efficiently, securely, but is, you know, highly cost effective and very high performance, you know, ranging from people who are trying to connect from home to people who are trying to use videoconferencing and people who are going to be more and more use cloud based services even to order simple of the data being, you know, going to source for so network will become essential, you know, essential element for four things as we go forward. And we do see that being embraced by our customers and and things where we were trying to communicate that, you know, look, you will need performance and cost benefits are becoming more and more real Now. It's like, oh, things that we were having things in the pipeline for us. We need to work on that now. And the reason is because the things that we anticipated the demand increase, which is gonna happen over the fear of years, is happening literally in a few months. And so that is what we see. We are definitely, you know, very well poised to take advantage of their of their demand for sure. But also the fact that you know it needs to be done super efficiently. And so I think we are. You know, we are right. Well, I would say, you know, situated to be able to take advantage of start. >>Yeah, absolutely. You know, one thing you can't control as a company is you know what the global situation is when you come out of stealth and, you know, move through some of those early phases, you know, you've been part of You said a number of startups you've been part of been in give us a little bit of the inside baseball of, you know, being part of Rondo. You know, any stories on a little some of the ups and downs on the multi year journey to get where you are today? >>Definitely. I think. You know, um, minutes aren't good. They are largely an execution play. Relatively independent startup is is going to be about you know, how we cracked the overall market market fit and, ah, on execution, Of course, on deal with maybe in a competition in a different way, of course, like maybe big companies are our great partners. At the same time, you have to navigate that. So the overall the overall landscape in Spain and forces forces not is it's quite different. We can be much more border than we are independent company In trying to disrupt almost anything because we don't have any point of view to define per se. We do exactly, You know, what could be the most disruptive way, too, to potentially benefit the users on day? That's a big, you know, big change. I would say, um, we are being but paranoid as well at the same time, impractical to look at. You know how how we could navigate this situation in a very practical may. And the journey off, often independent startup is, you know, personally, for me, this is this is my fourth in different and start and best off. Off off, all independent. Once, I would stay largely because the kind of tradition that we're getting being an independent company is so huge. I'm just concerned about those things. But what We're really trying to trying to ensure that, you know, we can't get our stuff, but I want you and we started. >>Excellent. Guess what? One of the other things about being a startup is You know what you know adjustments You need to make along the way. So I'm curious. As you know, you've gone to some of your early customers. Any feedback or adjustments in some of the use cases or, you know, things that you've learned along the way that you can share. >>Um, fundamentally, at a base level, we haven't shifted from what we started off. We look at disruptions on on how consumption models are going to be changing, how speeds and feeds are gonna become important because, you know, because most law is going to be almost operating, how we how we deliver things into and containers are going to be a primary, you know, vehicle to deliver and build applications. So we recognize those disruptions, and we haven't changed, But normally from those disruptions that we wanted people after her. Uh, but at the same time, I think, you know, as we went and socialize our ideas and on architecture and designs with customers, we realized that that they are giving us lots more feedback on work all we could do and ah, and starting to become like we could take on different segments of market and not just one. So why stick ourselves to the data center power? Why not work on something on edge, blur wine or wine are real solutions for five G where latency and and performance is super crucial. Why don't take up on, you know, branch that use cases. So there are many things that are opening up. Um, and largely the you know, the shift. Or I would say the the inclination of what we should change versus not is happening with respect to where our customers are driving us. And and it is very important to make sure that you know the users of our lives Articulating all of the shift happens as opposed to, uh, you know, as opposed to anything else. We listen to them like super, super carefully, uh, and at the same time trying to make sure that we not only meet their means for you there their demands. So, um, definitely, you know, from the from the overall landscape of things, we are starting to get a lot more than what we are capture, which is good news For the same time, we're trying to also, uh, take on one part. I'm you know, >>all right, Vivienne, I can't let you off the hook as the cto without talking a little bit about that. You know, I think earlier in my career there was the old discussion and said you know, we should have started it, you know, a year or two ago. But, you know, we didn't. So we should start it today with changing pace of technology. You know, I've always said, you know, if I could I'd rather wait a year because I could take the next generation. I can take advantage of all these other things, but I can't wait, because then I'd never ship any things that I need to start now, Give us a little bit, you know, Look out in the future. How is your architecture designed to be able to take advantage of all the wonders coming with five G and everything there, Um, and anything that we should be looking at, You know, through the next kind of 12 18 months on the roadmap that you could share >>your Ah, yes. So, um, I would first of all say that we didn't build a part of, actually, what we build was a platform on which we can build multiple products. And we started we started off going there because we thought that, you know, the the platform that we're building is capable of capable of doing a lot more things than than one use case that we start off with. And so, to that point, I would say that yes. I mean, he started focusing on one product initially on the possibilities off. Trying to take it to multiple segments is is normally very much there. But we are already, you know, having those conversations to see what is the core set of use cases that we could we could get into for different segments. Besides the data center, you know, public Private Data center, you're looking at edge. We're looking by the looking at, Yeah, you mentioned this is as well as the, you know, storage and conversion infrastructure. So I would say that the food of all those things that we're starting to engage is going to start showing up in next 18 months. I could actually I think we are very well boys to take advantage of what we have. The hardware that we're shipping is going to be 100% compatible with four programs, but I don't those. So that is that is lot more possibilities are interesting. More use cases as people. The software's architecture that we have built is very extensible as well. Eh so we believe that. You know, uh, we believe that we can normally satisfy those use cases, but we're starting to you get into those things now, which will start to show up in and actually useful products of unusable for us with customer testimonials and then maybe 12 to 18 months from now. All >>right, well, thank you so much. It's great to catch up with. You really appreciate you coming on. >>Thank you to Because they're talking to you. And, you know, I appreciate your time. >>All right, I'm stew minimum. And be sure to check out the cube dot net for all the coverage. Go see the launch that we did. So in the second half of 2019. Thank you for watching you. Yeah, Yeah, yeah, yeah.

(bright music) >> Announcer: From the Cube studios in Palo Alto in Boston, connecting with thought leaders all around the world. This is a Cube conversation. >> Hi, I'm Stu Miniman, and welcome to a Cube conversation. I'm coming to you from our Boston area studio. And we're going to be digging into P4, which is, the programming protocol independent packet processors. And to help me with that, first time guest on the program, Mario Baldi, he is a distinguished technologist with Pensando. Mario, so nice to see you. Thanks for joining us. >> Thank you. Thank you for inviting. >> Alright, so Mario, you have you have a very, you know, robust technical career, lot of patents, you've worked on, you know, many technologies, you know, deep in the networking and developer world, but give our audience a little bit of your background and what brought you to Pensando. >> Yeah, yes, absolutely. So I started my my professional life in academia, actually, I worked for many years in academia, about 15 years exclusively in academia, and I was focusing both my teaching in research on computer networking. And then I also worked in a number of startups and established companies, in the last about eight years almost exclusively in the industry. And before joining Pensando, I worked for a couple of years at Cisco on a P4 programmable switch and that's where I got in touch with P4 actually. For the occasion I wore a T shirt of one of the P4 workshops. Which reminds me a bit of those people when you ask them, whether they do any sports, they tell you they have a membership at the gym. So I don't just have membership, I didn't just show up at the workshop. I've really been involved in the community and so when I learned what pensando was doing, I immediately got very excited that the ASIC that Pensando has developed these is really extremely powerful and flexible because it's fully programmable, partly programmable, with P4 partly programmable differently. And Pensando is starting to deploy these ASIC at the edge and Haas. And I think such a powerful and flexible device, at the edge of the network really opens incredible opportunities to, on the one hand implement what we have been doing in a different way, on the other hand, implement completely different solution. So, you know, I've been working most of my career in innovation, and when when I saw these, I immediately got very excited and I realized that Pensando was really the right place for me to be. >> Excellent. Yeah, interesting, you know, many people in the industry, they talk about innovation coming out of the universities, you know, Stanford often gets mentioned, but the university that you, you know, attended and also were associate professor at in Italy, a lot of the networking team, your MPLS, you know, team at Pensando, many of them came from them. Silvano guy, you know, written many books, they're, you know, very storied career in that environment. P4, maybe step back for a second, you know, you're you're deep in this group, help us understand what that is, how long it's been around, you know, and who participates in it with P4? >> Yeah, yeah. So as you were saying before, one of the few P4 from whom I've heard saying it, because everyone calls it P4 and nobody says what it really means. So programming protocol, independent packet processor. So it's a programming language for packet processors. And it's protocol independent. So it doesn't start from assuming that we want to use certain protocols. So P4 first of all allows you to specify what packets look like. So what the headers look like, and how they can be parsed. And secondly, because P4 is specifically designed for packet processing, and it's based on the idea that you want to look up values in tables. So it allows you to define tables, in keys that are being used to look up those tables and find an entry in the table. And when you find an entry, that entry contains an action and parameters to be used for that action. So the idea is that the package descriptions that you have in the program, define how the package should be processed. Header fields should be parsed, values extracted from them, and those values are being used as keys to look up into tables. And when the appropriate entry in the table is found, an action is executed and that action is going to modify those header fields, and these happens a number of times, the program specifies a sequence of tables that are being looked up, header fields being modified. In the end, those modified header fields are used to construct new packets that are being sent out of the device. So this is the basic idea of a P4 program. You specify a bunch of tables that are being looked up using values extracted from packets. So this is very powerful for a number of reasons. So first of all, its input, which is always good as we know, especially in networking, and then it maps very well on what we need to do, when we do packet processing. So writing a packet processing program, is relatively easy and fast. Could be difficult to write a generic programming in P4, you could not, but the packet processing program, it's easy to write. And last but not least, P4 really maps well on hardware that was designed specifically to process packet. What we call domain specific processes, right. And those processes are, in fact designed to quickly look up tables that might have decamping side, they might have processes that are specialized in performing, in building keys and performing table lookup, and modifying those header fields. So when you have those processors that are usually organized in pipelines to achieve a good throughput, then you can very efficiently take a P4 program and compile it to execute it very high speed on those processors. And this way, you get the same performance of a fixed function ASIC, but it's fully programmable, nothing is fixed. Which means that you can develop your features much faster, you can add features and fix bugs, you know, with a very short cycle, not with a four or five year cycle of baking a new ASIC. And this is extremely powerful. This is the strong value proposition of P4. >> Yeah, absolutely. I think that that resonates Mario, you know, I used to do presentations about the networking industry and you would draw timelines out there in decades. Because from the standard to get deployed for, you know, the the hardware to get baked, the customers to do the adoption, things take a really long time. You brought up, you know, edge computing, obviously, you know, we are, you know, it is really exciting, but it is changing really fast, and there's a lot of different, you know, capabilities out there. So if you could help us, you know, connect the dots between what P4 does and what the customers need. You know, we talked about multi-cloud and edge. What is it that you know, P4 in general, and what Pensando is doing with P4 specifically, enables this next generation architecture? >> Yeah, sure. So, Pensando has developed these card, which we call DSC distribute services card, that is built around an ASIC, that has a very very versatile architecture. It's a fully programmable. And it's fully programmable it's various levers, and one of them is in fact P4. Now this card and has a PCIE interface. So it can be installed in horse. And by the way, this is not the only way this powerful as you can be deployed. It's the first way Pensando has decided to use it. And so we have this card, it can be plugged into a host, it has two network interfaces. So it can be used as a network adapter. But in reality, because the card is fully programmable and it has several processors inside, it can be used to implement very sophisticated services. Things that you wouldn't even dream of doing with the typical network adapter, with a typical NIC. So in particular, this card, this ASIC contains a sizable amount of memory. Right now we have two sizes four, an eight gig but we are going to have versions of the card with even larger memory. Then it has some specialized hardware for specific functions like cryptographic functions, compression, computation of CRCs and if sophisticated queueing system with packet buffer with the queuing system to end the packets that have to go out to the interfaces or coming from the interfaces. Then it is several types of processors. It has generic processors, specifically arms, arm processors that can be programmed with general purpose languages. And then a set of processors that are specific for packet processing that are organized in a pipeline. In those, idea to be programmed with P4. We can very easily map a P4 program, on those pipeline of processor. So that's where Pensando is leveraging P4, is the language for programming those processes that allow us to process packets at the line rate of our 200 gigabit interfaces that we have in the card. >> Great. So Mario, what about from a customer viewpoint? Do they need to understand you know, how to program in P4, is this transparent to them? What's the customer interaction with it? >> Oh yeah, not at all. The Pensando platform, Pensando is offering a platform that is a completely turnkey solution. Basically the platform, first of all, the platform has a controller with which the user interacts, the user can configure policies on this controller. So using an intent based paradigm, the user defines policies that the controller is going to push those policies to the cards. So in your data center in your horse, in your data center, you can deploy thousands of those cards. Those cards implement distributed services. Let's say, just to give a very simple example, a distributed stateful firewall implemented on the all of those cards. The user writes a security policy, says this particular application can talk to these other particular application, and then translate it into configuration for those cards. It's transparently deployed on the cards that start in force the policies. So the user can use this system at this very high level. However, if the user has more specific needs, then the system, the platform offers several interfaces and several API's to program the platform through those interfaces. So the one at the highest level, is a REST API to the controller. So if the customer has an orchestrator, they can use that orchestrator to automatically send policies to the controller. Or if a customer already have their own controller, they can interact directly with the DSCs with the cards on the horse, with another API's that's fully open, is based on GRPC. And in this way, they can control the cards directly. If they need something even more specific, if they need a functionality that Pensando doesn't offer on those card, hasn't already ever written software for the cards, then customers can program the card, and the first level at which they can program it is the ARM processors. We have ARM processors, those are running in version of Linux, so customers can program it by writing C-code or Python. But if they have very specific needs, like when they write a software for the ARM processor, they can leverage the P4 code that we have already written for the card for those specialized packet processors. So they can leverage all of the protocols that our P4 program is already supported. And by the way because that's software, they can pick and choose in a Manga library of many different protocols and features we support, and decide to deploy them and then integrate them in their software running on the ARM processor. However, if they want to add their own proprietary protocols, if they want, if they need to execute some functionalities at very high performance, then they that's when they can write P4 code. And even in that case, we are going to make it very simple for them. Because they don't have to write everything from scratch. They don't have to worry about how to process AP packets, how to terminate TCP, we have to solve the P4 code for them. They can focus just on their own feature. And we are going to give them a development environment that allows them to focus on their own little feature and integrate it with the rest of our P4 program. Which by the way, is something that P4 is not designed for. P4 is not designed for having different programmers, write different pieces of the program and put them together. But we have the means to enable this. >> Okay, interesting. So, you know, maybe bring us inside a little bit, you know the P4 community, you're very active in it, when I look online, there's a large language consortium, many of, you know, all the hardware and software companies that I would expect in the networking space are on that list. So what's Pensando's participation in the community? And you were just teasing through, you know, what does P4 do and then what does Pensando, maybe enable, you know, above and beyond what, you know, P4 just does on its own? >> Yeah, so yes Pensando is very much involved in the community. There has been recently an event, online event that substituted the yearly P4 workshop. It was called the P4 expert round-table series. And Pensando had very strong participation. our CTO, Vipin Jain, had the keynote speech. Talking about how P4 can be extended beyond packet processing. P4, we said, has been designed for packet processing, but today, there are many applications that require message processing, which is more sophisticated then. And he gave a speech on how we can go towards that direction. Then we had a talk that was resulting from a submission that was reviewed and accepted on in fact, the architecture of our ASIC, and how it can be used to implement many interesting use cases. And finally, we participated into a panel in which we discussed how to use P4 in mix-ins Martin at the edge of the network. And there we argued with some use cases and example and code, how before it needs to be extended a little bit because NICs have different needs and open up different opportunities rather than switches. Now P4 was never really meant only for switches. But if we looked at what happened, the community has worked mostly on switches. For example it is defined that what is called the PSA, portable switch architecture. And we see that the NICs have an edge devices, have a little bit different requirements. So, one of the things we are doing within the communities working within one of the working groups, is called the architecture work group. And they are working in there to create the definition of a PNA, Portable NIC Architecture. Now, we didn't start this activity, this activity has started already in 2018. But it did slow down significantly, mostly because there wasn't so much of a push. So now Pensando coming on the market with this new architecture really gave new life to this activity. And we are contributing, actively we have proposed a candidate for a new architecture which has been discussed within the community. And, you know, just to give you an example, why do we need a new architecture? Because if you think of the switch, there are several reasons but one, it's very intuitive. If you think of a switch, you have packets coming in, they've been processed and packets go out. As we said before, there's the PMA then sorry, PSA architecture is meant for these kinds of operation. If you think of a NIC, it's a little bit different because yes, you have packets coming in, and yes, if you have multiple interfaces like our card, you might take those packets and send them out. But most likely what you want to do, you want to process those packets, and then not give the packets to the host. Otherwise the host CPU will have to process them again, to pass them again. You want to give some artifacts to the host, some pre-processed information. So you want to, I don't know take those packets for example, assemble many TCP messages and provide a stream of bytes coming out of this TCP connection. Now, these requires a completely different architecture, packets come in, something else goes out. And goes out, for example, through a PCI bus. So, you need the some different architecture and then you will need in the P4 language, different constructs to deal with the fact that you are modifying memory, you are moving data from the card to the host and vice versa. So again, back to your question, how are we involved in the workgroups? We are involved in the architecture workgroup right now to define the PNA, the Portable NIC Architecture. And also, I believe in the future we will be involved in the language group to propose some extensions to the language. >> Excellent. Well, Mario, thank you so much for giving us a deep dive into P4, where it is and you know some of the potential futures for where it will go in the future. Thanks so much for joining us. >> Thank you. >> Alright. I'm Stu Miniman, thank you so much for watching the Cube. (gentle music)