Welcome to CES 2023. I am so happy to see you here today, and I'm also pleased to welcome back to the CES keynote stage, one of the tech world's most visionary leaders, AMD Chair and CEO, Dr. Lisa Su. You know, Lisa has been a keynoter at CES several times, most recently joining us here on this stage in Las Vegas in 2019, but also digitally in 2021. Since my last conversation with Dr. Su on a keynote stage, our world has changed dramatically. Back in early 2021, first responders and frontline workers were just getting the first vaccine doses, developed of course, with the help of high performance and adaptive computing. Cut to today, and what do we see? AMD's technology is powering nearly every product and service shaping the future of computing.
In fact, AMD is supporting advances in scientific research, healthcare, and safe driving, not to mention the gaming equipment and software the brand is known for. None of this would be possible without a leader like Dr. Su. She's actually a real and true immigrant success story. Having immigrated to the U.S. from Taiwan at a young age, pioneering new research as a grad student, and making a real impact at Texas Instruments, IBM, and Freescale Semiconductor before joining AMD. She has pushed AMD to diversify and invest in new technologies, helping AMD become the industry leader it is today. More recently, she has served on President Biden's Council of Advisors on Science and Technology, and in fact, last year won the International Peace Honor for achievements in high performance computing, donation of supercomputing power for infectious disease research, and inspiring young people to pursue careers in STEM.
Just incredible. To share more on her vision for the future of computing, please welcome AMD Chair and CEO, Dr. Lisa Su.
This is where the world's most advanced processors meet the world's most important challenges. This is where together we advance. Together, we discover stars instead of wishing on them. We use supercomputers to help change the nature of climate change. We supercharge renewable energy and accelerate the pace of discovery. Together we push limits. To shatter records with some of the world's fastest processing speeds. To work smarter, bridge oceans, and save more than the day. Together, we see power and potential. We tilt the fight in our favor with AI and AR. We lose ourselves in new worlds and create them pixel by pixel. Together, we turn the hardest problems into the greatest possibilities. AMD, together we advance.
Fantastic.
Thank you.
You have a good time.
All right. Woo! Thank you so much, Gary, for that wonderful introduction. Good evening, Las Vegas. How's everyone doing tonight? It's so wonderful to be here. Really wanna welcome everyone who's also watching on the world cast. I would say that it's so wonderful to be back here in person this year. I am so honored to be opening CES 2023. Now, we have a lot of new products and a lot of new technologies to show you tonight. Let's go ahead and get started. You know, this is truly an incredible time to be in the semiconductor industry. If you think about what the last few years have been, you know, there have been many challenges. There's also been this incredible surge in demand that stressed all aspects of our supply chain.
One thing is true, the pandemic made it clear that semiconductors are absolutely essential to everything that we do. Virtually every product, every service, every experience in our lives is powered by semiconductors. Whether you're talking about cloud services or how we work, game, and connect, chips have become a critical enabler of everything in our modern life. With the growth of AI across all of these applications, the technology is becoming even smarter and more sophisticated every single day. At AMD, we're all about pushing the envelope in high performance and adaptive computing and using technology to create solutions to the world's most important challenges. Tonight, I wanna give you just a peek into all of the ways technology is transforming how we do things.
We have a truly packed show for you, and I'm really excited to be joined by some of our closest partners to discuss what we're doing across AI, hybrid work, gaming, healthcare, aerospace, and sustainable computing. Let's get started with AI. AI is truly the most important mega-trend for the future of tech, and at its simplest, AI leverages the power of high-performance computing to analyze and interpret massive amounts of data to uncover patterns and make predictions on future outcomes. Now, we're already using AI every day. Think about Siri or Alexa on your smartphone or your smart device, or when you're doing shopping, you know, identifying your shopping preferences online or creating individualized medical treatments or even predicting weather patterns and numerous other business applications.
The full potential of AI, though, can only be realized when it is available across a range of devices, from intelligent endpoints to the edge, to the cloud. To bring the right level of AI capability to all devices, we need multiple compute engines, and that means CPUs, GPUs, and adaptive accelerators. We are one of the only companies in the world that have all of these engines. Let me start today with a brand-new accelerator that we're bringing into the market. AMD XDNA is a highly configurable AI accelerator that originated from our acquisition of Xilinx. What it does is it actually allows us to scale from PCs to intelligent endpoints, to edge devices, and even into the cloud. What we've done with this architecture is it's actually very configurable, so you can really configure it for the right application and the right power efficiency.
We Because of this, we can deploy XDNA broadly across our entire product portfolio. The first use of this architecture in AMD products will be in our Ryzen mobile CPUs for notebooks. Today I'm very proud to announce the all-new Ryzen 7040 Series. You guys know we always use CES to announce our new notebook products, and this is our next-generation processor for ultra-thin notebooks. It's the industry's first mobile x86 processor to integrate a dedicated on-chip AI engine, which we call Ryzen AI. It features up to eight Zen Core, Zen 4 cores, our latest RDNA 3 graphics, and our new Ryzen AI engine that runs four dedicated AI streams simultaneously, delivering up to 12 trillion AI operations per second. Thank you very much. As you guys know, I love showing chips, here is the all-new 7040.
This chip uses 4 nm process technology. It has more than 25 billion transistors, almost twice as many as our Ryzen 6000 generation. Here you go. Take good care of it, please. Let's take a look at some of the performance. You can see that the Ryzen 7040 is significantly faster than both our x86 competition as well as Apple. In CPU-intensive workloads like Cinebench, we're delivering up to 34% more performance for creators. In AI, we outperform the Apple M2 by 20%, while our x86 competition doesn't have an on-chip dedicated AI engine. When you look at gaming, we're more than 20% faster. Let's take a look at some of that performance in action. What we're showing here is a time-lapse video of the popular Blender rendering application.
On the right is our top-of-stack Ryzen 7040 CPU with Apple's best in the middle and Intel's highest-end ultra-thin chip on the left. I'm gonna let the demo go for just a little bit. Just a little bit. As the demo completes for AMD, what we see is the Ryzen system is 30% faster than Apple and 45% faster than our x86 competition. This just shows you the tremendous overall performance. It's not only about performance, it is very much about battery life. With our 4 nm process technology, and frankly, our designers have been spending a tremendous amount of effort trying to optimize power across the entire design, the Ryzen 7040 Series will enable more than 30 hours of battery life, which is just simply fantastic. What I'm most excited about with the new 7040 is actually the Ryzen AI capability.
As I said, this is brand-new for us to integrate on chip, and what it does is it'll actually open up a whole new set of experiences for our users. Things like more lifelike collaboration experiences with enhanced audio and video. Think about, you know, content creation being much more productive or gaming performance being more real time. Even when you think about security, we can use AI to change the way we monitor security. There's a lot of excitement in the industry around our Ryzen 7040 Series. You're gonna hear from some of our partners, but I wanted to make sure that you guys saw that the first Ryzen 7040 notebooks will be available in March, and we will have more than 250 ultra-thin gaming and commercial notebook designs spanning our entire Ryzen 7000 Series portfolio on track to launch this year.
Okay, but as you guys know, it's not just about hardware. To truly unlock the full potential of our silicon, we need to have very deep partnerships with our software and our system partners. That brings me to our first guest. Microsoft represents our deepest and broadest partnership, spanning across hardware, software, and systems, and also across client, edge, and cloud. Let me welcome Microsoft EVP and Chief Product Officer, Panos Panay.
All right. Your jacket. Your jacket's pretty rad. It's pretty rad. It's a pretty cool jacket, you have to admit. You got me.
Panos was not supposed to embarrass me in the first five seconds.
I have to say, it's great to be here, Lisa. I'm so excited. Like, we're in person. I mean, last time we did this it was digital. It's been ages since I've been in front of a crowd. This is really cool.
It is a pretty good crowd, though, tonight. What do you think?
It's pretty cool. Yeah. It's a good crowd.
Ah.
Good energy. Good energy. A lot of familiar faces. A lot of familiar faces.
It is fantastic to have you here.
Thank you.
I would say, you know, I mean, you heard everything I said about Microsoft as our partner. You guys have an incredible mission for, you know, where technology is going, and our teams have done so much together over the years. Can you talk a little bit about, you know, that collaboration?
Yeah, I think so. I think it's good. Like, anchoring on the vision is perfect. Let's start there. Like, at Microsoft, you know, we remain just guided by our mission. It's what drives me. It's what drives our teams. The mission to empower every human on the planet, every organization on the planet to achieve more through technology. I think we do that together. I think Microsoft and AMD have a long history, an incredible history, and a partnership, as a matter of fact, that has an impact in making a difference for people through tech. Now, Lisa, now, I think more than ever, I feel it's our responsibility to create experiences together. Like you just talked about it, there's so much transformation happening right now.
These experiences need to empower and amplify what people can do with tech, and I can certainly say we're really on that path already. If you think about, Xbox Series X and S, I'm sure we have some fans in here, ultimately powered by AMD's SoCs.
Xbox fans?
These are products we designed together all the way to the innovation experiences created across the silicon, Windows 11, including the Pluton security that you've so amazingly brought to market, we're proud of that. Ultimately, even the work that you do with us on Azure, like it all comes together so beautifully and comes together. I feel like our partnerships continues to grow and the difference that you're making in the world is pretty awesome.
Well, I really appreciate that, Panos.
You bet.
You know, you just heard me talk about Ryzen 7040.
Yep.
You know, we spend a lot of time when we're together with our teams, talking about empowering our customers with new user experiences and the importance of AI. You know, we've really had our teams working on this, you know, really big sprint with bringing Ryzen 7040 to the market. Can you talk a little bit about that and what people can expect?
Yeah, absolutely. I would love to. Let me just start by saying... You hit it, AI is the defining technology of our time. It's like nothing I've ever seen before. It's transforming industries. It's improving our daily lives in many ways. Some of it you see, some of it you don't see. We are right now, right this moment, at an inflection point. This is where computing from the cloud to the edge is becoming more and more intelligent, more personal, and it's all done by harnessing the power of AI. Lisa, here's a way to think about it. AMD has been at the forefront of compute, tech for a very long time and continues to be.
Agreed.
I think we're gonna see a lot of that today.
Thank you.
Driving key innovations, we talked about Xbox, Windows, and Azure. Now AMD is also at the forefront of AI technology with Ryzen, the 7040 Series alongside Windows 11. It is our next step in this journey together. I'm pretty pumped about it. We can now run massive models that were required with large GPUs now more efficiently on AMD-powered devices.
You've told me every top I put on that chip, you're gonna use.
I'm gonna try.
That's what he said. Can you give us just a little bit of an example?
Yeah. Yeah, sure. Okay. Like when you take Ryzen AI, here's the easiest way. It was kind of in your slides, if you take Windows Studio Effects, these are pretty powerful. Now we're living in a time, these effects enable us really to be seen, to be heard, to participate with one another, really unlocking that human connection we all crave. It's super important to be able to connect with one another. I mean, just a year ago, we were leveraging our PC screens in such a big way, we continue to be. Now you bring in portrait blur, you bring in eye contact, you bring in automatic framing, you bring in noise suppression. There are so many different things that AI bring to the forefront. You can't see, you can feel it. This is so important.
When you're connecting with somebody else, you either have that direct eye contact, that background blur without disappearing into it, which is so important, or the framing that you can see here on Sheila where it auto frames. These experiences, though, they demand trillions of operations per second, to your point, and where you're pushing it. Here's what's awesome. They can now run on AMD's AI engine, not taxing the CPU or GPU, while only consuming a few hundred milliwatts. What does that mean? What does that mean? Like, get out of that jargon. It means you get this incredible AI power. You sacrifice no battery life, you sacrifice no performance, essentially no performance. In essence, letting you run the powerful natural language models. What does it translate to?
It means I can connect with human beings without anything getting in my way and doing whatever else I want to do on the PC at the same time.
It is absolutely the wave of the future. It's what, you know, we believe in. I know that it's what we've spent a lot of time on. We're very excited about Ryzen AI and bringing some of the Windows Studio effects to the market. Panos, just one more question, 'cause we're here at CES, and, you know, everybody wants to know what's next. Our teams spend a lot of time on the future. You spend a lot of time on the future.
Right.
So-
This is the question you're not supposed to ask me.
No, no. Let's tell the world what some of the future may bring.
I think those are for the meetings where we kinda do it in closed door sessions, not with 2,000, 3,000 people in front of us.
There might be a few more online, too.
Yeah, it just, it feels different. All right, let me offer this. Here, here's a thought. Like, you know, I'm a mouse and keyboard person. This is how I started at Microsoft. Take a lot of pride in my heritage in that. I would say just like the mouse helped reinvent the graphical user interface, it was such an important part when the scroll wheel came and what it meant, what pointing meant, things started to transform. I know it's a simple example, but it's meaningful to me. AI is gonna reinvent how you do everything on Windows, quite literally. Like, these large generative models, I think language models, code gen models, image models, these models are so powerful, so delightful, so useful, personal, but they're also very compute-intensive. We haven't been able to do this before.
We have never seen this intense workloads at this scale before. They're right here. It's gonna require an operating system that blurs the line between the cloud and edge, and that's what we're doing right now. It takes the right silicon in the right place to deliver the best experience for our customers, 'cause now you can do what you want to be doing at an exponential level. Like, nothing stops you from the chip all the way through to the cloud, enabled in great part by what you're doing, Lisa. I think the next generation of these products are gonna inspire a ton. That's what I think. Is that all right?
Fantastic. Thank you so much, Panos.
Okay. Thank you for having me.
I appreciate so much for being here, thank you for the partnership. All right. Now let's move to another very important area, which is around hybrid work. Now, while many of us have, you know, really been working remotely over the last couple of years, there's a lot more we need to do to make hybrid work and remote work more seamless. According to a recent survey, more than 80% of employees say that they like the flexibility of working from home, and it makes them happier. More than half of those employees also say that their connectivity issues are actually limiting their career, and only 25% of people believe their organizations are really prepared for hybrid work. When you look at the biggest issues that are limiting productivity, actually, I think every one of us has experienced this, right?
You're in a hybrid meeting, you're just getting to the most important part of the discussion, and something happens. Your audio drops, your video freezes, or your laptop runs out of battery. We know that technology can make this much better. We believe that deep co-engineering of, at the solution level is really required to make hybrid work frictionless for both users and also IT departments. To talk more about how we're approaching this opportunity, let me introduce my next guest, HP President and CEO, Enrique Lores. Enrique, thank you so much for joining us on this very important topic. You know, HP has been a wonderful partner with AMD. We've done so much together.
You've also been really a thought leader on how, you know, hybrid work is evolving, and you've spent a lot of time, you know, talking to customers about it.
Mm-hmm.
What are you hearing?
First of all, Lisa, thank you for inviting us to participate here. I think what we are experiencing is probably the biggest change in how people work that we are going to see in our lifetime. If we think about how are we engaging now with our teams, how do we motivate them, how do we measure their productivity is very different from what it was. Think about the role of the office and how what people like in the office is totally changing from what we used to do only a few years ago. Think also about new professions and new type of work that is growing. For example, our estimate is that in five years from now, 50% of the workforce in the U.S. are going to be freelancers.
All these are radical changes that are opening the opportunity for disruptions, for opportunities, for innovation. This is what makes the current situation so attractive and so relevant for all of us. Really excited about the changes that are happening and the opportunities for partnering this is bringing.
I completely agree with you. I think that the changes give us opportunities. I think innovation requires us to really work differently. This is one of the things I really appreciate so much about our relationship, because it really is about how do we co-engineer for the, some of these new challenges. Can you talk a little bit about how our teams are now working differently together?
Sure. I think there has been a very fundamental change on how the two teams have been working from what we, how we used to work in the past. We all start by really identifying what are the user needs we are going after, what are the customer pain points that we are trying to address, then by putting the two engineering teams together to address and to find the right solutions. What we have found is that when we put the HP team and the AMD together, and they can really think together about the solutions they're bringing, magic happens. Magic is really what we are after because this is really what creates innovation and what drives customer satisfaction.
One of the things I know that the engineering team tells me is they can't actually tell, you know, who has which badge when they're working together. Along those lines, you had a very exciting announcement this morning on your new Dragonfly Pro device, which was one of the things that we worked on together with our Ryzen processors. Can you tell us why this is such a big step forward?
Sure. I think this is a great example of how the two teams together can really deliver wonderful things. Today, we announced the Dragonfly Pro product. Really, this is targeting the freelancer community that I was mentioning before and is really designed to address the needs of this new and growing customer segment. For example, we know that for these people, having a long battery life is tremendously important. They work long hours. They want to make sure that they can always access information when they need it. And we, by working together, we have been able to deliver 40% higher PassMark score than the M1 that was the leading product until now. We also know how important it is for these people to get the right type of customer support.
They don't work for large organizations like ours, they need the support that whenever they are having a problem with an application or with a device. We have built a solution, a service in the device that just by clicking a button, they can get that type of support. We also know that now communication has become critical for these customers. We have built all the technology, HP Presence technology, to make sure they always get the right audio and the right video. Really we have integrated in this solution the right experiences that these customers are going to be demanding.
No, it's fantastic. I know we're very excited. It's an amazing product. It really highlights, you know, the benefits, as I said, of really optimizing hardware, software, and systems together. Now, can you share a little bit about some of the other products that our teams are working on for 2023?
Sure. I would say that this product is just the beginning. You have heard today about the Ryzen 7000 technologies that Lisa has been announcing. You will be seeing a full portfolio of solutions in the spring that will leverage all these products. Lisa, you and I have been working together for many, many years now. I have to say that I am really more excited now than I have ever been about the innovation that is gonna be coming from both companies in the future. I want to take this opportunity to say thank you for all the innovation that your team has brought. Thank you.
Oh, thank you so much, Enrique. It's been a wonderful partnership.
Thank you.
Really appreciate you being here.
Thank you.
Yeah. All right. Let's move to the world of gaming. Do we have any gamers in the house? You guys know, at AMD, gaming is actually in our DNA. We love gamers, and we're intensely focused on bringing the best experiences possible to the more than 3 billion gamers around the world, the majority of whom actually play on either PCs or consoles. AMD Ryzen processors and Radeon graphics are at the heart of gaming all over. When you think about gaming PCs from OEMs or DIYers, the PlayStation 5, Microsoft Xbox Series X and S, Valve Steam Deck, consoles, cloud gaming services like Microsoft's xCloud, and we're even bringing high-end gaming to cars with the newest generation of Teslas. In the last few months, we launched our new Ryzen 7045 Series CPUs and Radeon RX 7900 Series GPUs, which has been really exciting.
We know a growing number of gamers want to game everywhere. Today, we have a number of products to talk to you about on both the mobile side and as well as the desktop side. Let's start first with mobile, with our Ryzen 7045 CPUs. The Ryzen 7045HX Series is our first mobile CPU based on a chiplet design. It's for gamers and creators who want the highest possible performance in a notebook. It combines up to 16 of our high-performance Zen 4 cores with boost speeds up to 5.4 GHz and up to 80 MB of on-chip memory in 5 nm process technology. Let's just take a look at the performance. Our previous generation, Ryzen 6900HX Series, were already phenomenal for 1080p gaming.
What we're doing with the Ryzen 7045HX is to take that to a different level of performance. What we're seeing is on average 24% higher performance across a range of popular games. When you look at content creation and productivity applications, when we compare against our competition, those 16 Zen 4 cores are delivering significantly more performance, more than 50% faster across a wide range of applications that will enable creators to accomplish so much more with this notebook. The Ryzen 7045HX enables a different category of mobile laptops for gaming and content creation, but we're also bringing new mobile gaming GPUs to the market today. The RDNA 3 that we launched in the desktop, we're now launching our first products in laptops with our new Radeon RX 7000 Series mobile GPUs.
What we're doing here, the first chip in the series, the RX 7000 Series for gaming and creator laptops, is the new Radeon 7600M XT. What we have here is 32 RDNA 3 compute units, 8 GB of GDDR6 memory, and a configurable power that allows us to adjust for the best balance of performance and battery life across a wide range of system designs. Let's take a look at some of the performance here. What we see for these guys in 1080p, the 7600M actually delivers next-level performance in its class, with 26% faster frame rates on average compared to the competition. Now, you're gonna see these guys in the market very, very soon. We'll have Ryzen 7945 and Radeon 7600M XT laptops starting in February.
You'll see even more gaming notebooks coming later this year, including some new AMD Advantage notebooks. To talk more about how we bring some of these products to life, our next partner is one that has adopted AMD very broadly across their portfolio, and that is Lenovo. Let me welcome Lenovo EVP and President Matt Zielinski to the stage. Welcome, Matt. It's so great to see you here tonight. Thank you for joining us.
Well, good evening, everyone, thank you, Lisa. It's such a pleasure to be here with all of you during my favorite week of the year, CES. Honestly, what makes this year even more special is the honor of being here on stage with you, Lisa.
Thank you.
I'm so excited to have the opportunity to share more on our two companies' deep and storied partnership and our strong shared commitment to keep this flame burning even brighter year after year.
Well, we really appreciate the breadth of our partnership with Lenovo. I think we've seen deep collaboration in a lot of products. Can you talk a little bit about some of those products?
Lisa, we've talked a lot about how collaboration is the key to unlocking innovation. Over the years we've built a deep partnership between Lenovo and AMD that spans from the data center to the workstation and all form factors of PCs. We're stronger together, and together we really believe there isn't a problem or challenge that we can't solve. At Lenovo, we're focused on a vision of developing and delivering smarter technology for all, and I know how deeply you personally and AMD share in that vision. Our partnership is really built on a proud history of decades of working together, bringing groundbreaking hardware and tech solutions to the market, and these include the ThinkPad Z Series that we announced last year at CES together, which were among the first to use AMD Ryzen PRO 6000.
Lenovo was also the exclusive workstation launch partner with AMD's Threadripper PRO and our powerful ThinkStation P620. That really has been a game changer in accelerating workflows across various industries.
Yeah. Thank you so much, Matt, for the for the deep partnership. We are in the gaming section and I take it Lenovo knows something about gaming. Can you talk about some of the products that you have launching here at CES?
I would love to, Lisa. In fact, look, since 2017, we've launched Ryzen in our most powerful Lenovo Legion PCs. As the world's number one PC company, Lenovo is here to deliver our shared vision to this growing gaming community by providing the best gaming hardware and experiences on the planet. Gaming communities are massive and growing, as you mentioned earlier. Esports, for example, is one of the fastest growing sports in the world. Tomorrow we'll be unveiling our first Lenovo Legion Pro Series laptops, and they integrate the latest generation of AMD Ryzen 7045 Series of processors that you just launched, Lisa, to take gaming to the next level. The new Ryzen 7045HX Series bring fantastic best in class processors to gaming laptops.
We really have been tied at the hip on every aspect of our new gaming platforms.
Yeah. No, it's wonderful. I know there's a lot of new technology in the Legion Pro. Can you share a little bit about what we've done with some of those experiences?
Absolutely. We've spent a lot of time with AMD in realizing the potential of the new Lenovo Legion laptops. Our teams really work together to ensure that the new Legion Pro can fully leverage the new Ryzen 7000 Series to max out frames per second, pushing the envelope even further. The multi-core power and performance we managed to tap from the CPU is truly impressive. This is gonna be the most powerful AMD Ryzen gaming laptop we've ever released, and I can't wait for gamers to experience these new incredible platforms. Lisa, we also agree that AI is one of the keys to unlocking improved and unmatched gaming experiences. AI really elevates gaming with benefits including improving network bandwidth, lowering your device's power consumption, and increasing frames per second, and even more than that.
The new Ryzen 7000 Series have been a big part of really making all of this happen. We have AI engineered into our systems that can work alongside AMD Ryzen processors to dynamically tune the CPU for up to a target 5% boost in performance. In doing so, we really pushed gaming performance far beyond what was thought to be possible.
Well, I think we both agree that Legion Pro is fantastic. You know, the other thing is we also realize that this is really just the beginning. Can you talk a little more about some of the future and what we should expect from Lenovo and AMD?
Absolutely. Well, as you know, this is just the beginning. In all, Lenovo's gonna have 50 different laptops, desktops, and workstations powered by AMD in 2023. That's a big number. Stay tuned because, as we like to say, we're just getting started.
I love it. I love it. Thank you, Matt.
Thanks, Lisa. Take care. Thank you.
Okay. Lots of systems will be out there. Now let's move into desktops. I know a few of you may be waiting for some desktop chips perhaps, right? Yes? No? Maybe? One of the biggest recent innovations in gaming PCs has been our introduction of 3D V-Cache memory technology in our Ryzen 7 5800X3D CPUs last year. What we did is we used 3D packaging to stack memory on top of CPUs to deliver substantially more performance in gaming. When Ryzen 7 5800X3D launched, it launched as the world's fastest gaming processor. Tonight I'm very excited to announce that we are now bringing 3D V-Cache technology to our Ryzen 7000 processors.
The Ryzen 7 7800X3D is 8 cores, 16 threads, up to 5 GHz frequency, and 104 MB of cache, which more than doubles the cache compared to the Ryzen 7 7700X non-X3D version. These larger caches are important, especially in gaming. Now let's take a look at some of this performance. The 7800X3D delivers on average 15% more performance than the 5800X3D across popular games. Is that okay? Guys, as great as the 7800X3D is, I've had a lot of our fans asking me for even higher end options. For tonight, I'm very happy to announce that we're also bringing 3D V-Cache technology to 12 and 16 core Ryzen 7000 processors. We've been working hard on this.
The Ryzen 9 7950X3D is our first 16-core Ryzen processor with V-Cache technology and our fastest 3D stack chip ever. It features 16 high-performance CPU cores, boost speeds up to 5.7 GHz , and a huge 144 MB cache. Let's take a look at some of this performance. In 1080p gaming performance versus the competition, you can see that the 7950X3D is faster across a wide range of games, consistently delivering much higher frames per second, which makes this the ultimate processor for gamers and creators. When you think about processors, you also need great games. What I'd like to show you now is one of the most anticipated new games of 2023, Star Wars Jedi: Survivor from our friends at Respawn.
You know, this title has actually been developed on Ryzen, and it's been optimized for Ryzen processors. That looks great, doesn't it? I'm very excited to announce that we will be bundling the game with our select Ryzen 7000 Series CPUs starting later this month. When I look at all of these things, what I'm very happy to say is we're gonna have an incredible portfolio for you with Ryzen desktop processors. The new 7800, 7900, and 7950 X3D parts will launch in February, and we are also launching new low-power 65 watt Ryzen 7000 processors and an expanded portfolio of entry-level AM5 motherboards that will make Ryzen the best CPU at every price point in the desktop market.
Let's switch gears now and transition to a very different world where tech is making a huge difference. This is the world of adaptive computing. Last year, we acquired Xilinx, which gave us leadership in a whole new set of technologies and a whole new set of markets. Adaptive computing solutions are unique in that the hardware can be changed and optimized multiple times to perform whichever task you need. This allows a chip to be adapted for optimal performance for a specific application or actually changed on the fly to add new features. We are very proud to be number one in adaptive computing with 10 of the top auto manufacturers, six of the top seven 5G wireless equipment manufacturers, and more than 6,000 different customers across healthcare, aerospace, industrial, and other embedded markets that are using our products.
Let's start with healthcare. This is actually something that's very personal for me. I believe that technology should do good, and there's nothing more important than using technology to improve our healthcare. This is being used in a number of areas. To help us understand more about this, let's welcome a true expert in this field and one of our deepest healthcare partners, Bob DeSantis, EVP and Chief Product Officer at Intuitive Surgical. Thank you, Bob. Welcome. Thank you so much for being here.
Wow, it's exciting to be here. Thank you, Lisa.
I would say that, you know, there's so much we have to learn about what technology can do in healthcare. Can you tell us a little bit about what Intuitive does and, you know, what it means to healthcare?
Absolutely. Intuitive was founded on a vision that surgery could be improved by leveraging advanced processing and electromechanical systems, i.e. robotics. We really work at the intersection of healthcare and technology to enable surgeons to ultimately help patients. The da Vinci Surgical platform, the da Vinci Surgical System, is the realization of that vision. Just some numbers to give you a perspective for kind of the scope and the impact that da Vinci is having. To date, over 11 million patients have benefited from having a surgical procedure performed on the da Vinci platform. Every day, every 18 seconds, every day right now, someone, somewhere around the globe, a patient is having another da Vinci procedure.
That means that in our short time here on stage, about another 12 patients will benefit from the da Vinci Surgical System. To give you a feel for how the platform actually works, I'd like to show you a video. The video contains some stories from two of our most important customer categories. One, the surgeon, and also the patient. This patient happens to also be an employee. In the video, we'll see three of our surgical platforms. The first is called single port, because all the instrumentation goes into the body through a single access point about the size of a quarter. The second is called the Ion endoluminal system. The Ion makes no incisions at all. It goes through a natural orifice. This one goes through the mouth, through the trachea.
The last is called multi-port, multiple arms, multiple incisions, small incisions that go into the body. That right now is really the bulk of our procedures right now. Multi-port does a variety of procedures from the pelvis to the abdomen, to the thoracic cavity. Let's take a look at the video.
When you're sitting in the robot, you feel like you have control over all of the technology around you. You've got your hands controlling one thing, your eyes and your feet in another. You apply that technology and say, "Let's look at what the robot can show me.
I'm a patient. I've had a da Vinci surgery. My father was a patient. He had a da Vinci surgery. In my every day, I'm charged up about what we're doing about building better products. We're thinking about different types of robots, different instruments to be able to do more jobs more efficiently, more safer, ways to bring new vision technologies to the surgeons so that they can see yet more that the naked eye can't see. Giving that surgeon more information to do their job better.
That is truly wonderful. You know, it is great to see how Intuitive is really improving the surgical process and helping the lives of so many patients every day. Can you talk a little bit about how AMD technology participates?
AMD is critical for us. Our engineering teams are focused on developing systems that, again, enable surgeons to obtain better outcomes, improving and sometimes saving lives. AMD's adaptive computing technology is a key component in achieving this for us. We've worked very closely together to integrate your adaptive technology. Handling multiple real-time functions concurrently with real-time compute and with low latency is key, which is why we use adaptive SOCs to power the precise motion control of the arms, the visualization, processing, and augmentation, and the safety mechanisms of our platform. When it comes to surgery and especially robotic surgery, motion control, visualization, and safety mechanisms are essential. Having a multi-generational, scalable, and reusable compute platform helps Intuitive integrate the same parts across multiple product platforms by programming, adapting them to suit our needs.
I love it. I love it. Now, one of the things I found so interesting, Bob, was that, you know, Intuitive's technology can also help reduce the time to diagnose disease and really help, you know, patients get answers more quickly. Can you talk a little bit about, you know, this?
Absolutely. I'll use lung cancer as an example. Due to current limitations with diagnosing lung cancer, it can take sometimes months, even years, to get a definitive diagnosis and treatment. Our Ion platform, again, a robotically driven bronchoscopic catheter, enables access deep inside the lung that wasn't previously possible. That helps physicians to get a biopsy and potentially diagnose lung cancer sooner, which can lead to earlier treatment. As you can see from the graphic, these are two patients with a suspicious lung lesion that have gone through two different patient journeys. The one with the robotic approach allows a diagnosis and a treatment much sooner. When it comes to lung cancer, time really matters.
We are so proud of our partnership and the role that adaptive computing plays to, you know, do things like this. you know, Bob, I'm asking everyone, as you look out over the next few years, how are you thinking, you know, the future evolves and the role of AI in your products?
Yeah, with everything we're doing with our platforms today, we really believe we're at the tip of the iceberg. We currently have AI and AR integrated into our ecosystem and into our platform. We are further developing it, using it to enable surgeons to develop more efficient techniques, to provide better, safer surgery. The safer surgery, you know, whether it's planning before the surgery, during the surgery, intraoperatively, the imaging, the planning stage, the adjunct of AR, AI is really helping us bring the future forward.
Sounds like our engineers are gonna be pretty busy over the next few years. Bob-
Absolutely.
Thank you so much for the incredible partnership. We're truly honored to be your partner.
Thank you.
Medical imaging is another area where AMD technology is dramatically improving patient care. Whether it's CT scans or ultrasounds, our adaptive SoCs and FPGAs are used to create high-resolution scans in real time to diagnose medical conditions as early as possible. Tonight, we are announcing new Vitis medical imaging libraries that will make it even easier for medical device manufacturers to offer high-resolution imaging at 1,000 frames per second or more. Let's hear from another partner who's using our technology, Clarius, to transform access to healthcare in remote areas.
Fernie is a town of 5,000 people. We have limited resources. We don't have CT scan, we don't have diagnostic ultrasound. Sometimes we can't even do an X-ray. Before we started using handheld ultrasound, people would have to travel for diagnostic ultrasound, and in the winter, that was a significant risk.
Clarius is a leader in handheld ultrasounds. Our mission is to bring the power of medical imaging in every setting.
Traditional ultrasound systems are expensive, they're not portable, and they're very difficult to use. We got really excited about creating a solution that's wireless, that's inexpensive, and that's powered by artificial intelligence.
As a physician, we're using technology more and more in our practice, and it's important that we can trust that technology.
When we found out about the AMD Zynq, it was a game changer for us.
The AMD Zynq really helped solve our technical challenges by creating a platform where we can add software, automation, and artificial intelligence to bring all those controls and automations onto a single platform. It's incredibly inspiring to see our devices being used by thousands of users and affecting millions of patients' lives.
Ultrasound can help me save lives. In a few years, we'll have handheld ultrasound all over the province, and people will be able to diagnose conditions without their patients having to travel thousands of miles.
Those are great stories. You know, I'd like to talk about another one which is also a very interesting area. There's a lot of talk these days about the metaverse, whether you're talking about virtual or augmented reality. What really excites me most are applications that really help make our lives better. We are seeing some amazing innovation in the operating room. Magic Leap is a true leader in AR and a long time AMD partner. To talk more about how AR is advancing healthcare, let me welcome CEO Peggy Johnson to the stage.
Hey, Lisa.
Welcome, Peggy.
Thank you.
It's so wonderful to have you here.
Thank you. Thanks for having me.
You know...
Awesome.
It's so much excitement, a lot of discussion around AR, VR, the Metaverse. Talk a little bit about how Magic Leap sees the market.
Yes. It is such an exciting time to be working in this field right now because the progress being made in augmented reality is accelerating. Businesses are beginning to really understand the value this technology can deliver today. Let me start by saying that augmented reality and virtual reality are two very different technologies with very different capabilities and use cases. Virtual reality is great for things like gaming, entertainment, and providing you with a total escape from your physical world. Augmented reality is the merging of your physical world with your digital world, and you still see your physical world as it is, but we merge digital content into your field of view.
With highly immersive augmented reality, like that enabled by Magic Leap 2, that digital content can now become a digital twin of a factory or 3D visualizations of the data, or even a surgical plan where you can overlay on the patient a guide for the surgeon to operate. It can also connect you with a remote expert, who can guide you through perhaps a complicated procedure and even annotate your physical space from afar, from anywhere in the world really, using Magic Leap 2 or even a laptop.
It's fascinating technology, and I know, you know, we've been working on it together for, a number of years. Congratulations on the launch of Magic Leap 2. Can you tell us a little bit more about what makes Magic Leap 2 so special?
Yeah. A couple things. First is Magic Leap 2's optical stack. That's the thing that enables this industry-leading image quality when you put the headset on. The text legibility is very clear. There's a large field of view to put that digital content in front of. We have a first to market feature called Dynamic Dimming. That is a capability which allows you to darken the area behind the digital content, so it appears even more solid in brightly lit settings like an operating room. It's really needed in there. To power these capabilities, we needed a high performance processor. There's a lot going on here. It needed to be capable of driving experiences and use cases that our customer needed.
Because of AMD's leadership in Zen Core and Radeon graphics, we partnered with your team to define a custom processor for Magic Leap 2. We also developed a custom computer vision and AI processing engine that's been a key component to how Magic Leap 2 maps and then understands that physical world. Our collaboration with AMD has resulted in the industry's most advanced augmented reality platform for enterprise. Well, thank you for that.
Thank you. Thank you. You know, what I love about this is, again, is this is back to the motto of you have to optimize silicon, system, and software together...
Absolutely.
To get the best result. Healthcare is clearly one of the most promising areas for AR. I know you're very active in it with lots of partners. Can you talk about how customers are using Magic Leap?
Yeah. You're right. Today, healthcare probably has some of the most advanced AR use cases, they actually generate today positive outcomes for patients and for doctors. Think of surgical planning and 3D visualizations of MRIs that can help a practitioner get a better understanding of the patient's anatomy before surgery, and even guide them through an operation. We've got a really great partner in SentiAR. They've developed this solution that connects physicians to clinical data and the image of those on the Magic Leap 2 platform. In certain procedures, physicians have to actually guide a catheter through the blood vessels of the heart, and they do that now while looking at a 2D screen in front of them.
With SentiAR, the physician is able to see this 3D map of the patient's heart in front of their eyes and the location of the catheter all in real-time. This is absolutely game-changing for the industry, and it's a use case that's really only possible with augmented reality.
No, it's amazing technology, really. What's next for Magic Leap 2?
Okay. Well, I'm excited to announce that we are now what's called 60601 certified. That means we're approved to take into the operating room. The surgeon can wear it in. We're currently the only AR device with this certification in place. In fact, the SentiAR solution is now under that standard review by the FDA. We hope to see their software on our platform a little bit later this year in the market.
It's fantastic. Fantastic. It's clear that there's, you know, tremendous potential in healthcare. I know you're also looking at a number of other use cases. What's next for this industry?
The industry, first, we really need to focus on growing the content ecosystem that sits on top of a platform like Magic Leap 2, and that will bring more and more utility to devices like this. Then we need to make it smaller. We wanna have just glasses format at some point, but to do that, we need to offload a lot of the compute to cloud instances like those powered by EPYC CPUs. Pervasive AI will also play a big part by maximizing the value of the data that Magic Leap 2 can process, so it can turn into actionable insights for the user. It goes without saying that all of this will require very close collaboration with the industry.
I think, you know, Peggy, again, our engineers love working with your team because it really is about collaboration and doing something that you might have thought was impossible. We're very proud to partner with you. Congratulations on Magic Leap 2, and we look forward to making this next era of computing a reality.
Thank you, Lisa. Thanks for having me.
You know, it's not just on our planet where we're seeing the profound impact of high performance and adaptive computing. AMD has also been a trusted partner in aerospace for decades, and we continue to work with the industry that innovates beyond boundaries of our planet. AMD solutions have been part of many recent space missions, from Mars Curiosity and Perseverance to the recently launched Artemis moon mission. We've also been working with commercial partners in adaptive computing for space travel, as well as for communications. To hear more about how AMD technology is helping to power the future of space exploration, I'm pleased to welcome a former NASA astronaut and Air Force colonel with more than 180 days in space.
She was part of two space shuttle missions and led a 6-month expedition to the International Space Station, where she served as the lead robotics and science officer. Please welcome Dr. Cady Coleman to the stage. Cady, it is such an honor to have you with us today. I know that everyone is dying to hear about your experiences. Not many people can say they've been to space. As someone with more than 24 years of experience in space exploration, can you tell us a little bit about your missions?
As a materials scientist and Lisa, just thank you for having me here. It's been really amazing for me to learn all the different things that go into what I actually got to do. As a materials scientist, I was really excited that my very first space shuttle mission was a science mission, and our results actually helped design the International Space Station as an orbiting laboratory. The second mission was led by Colonel Eileen Collins, first woman commander of the space shuttle, and our crew successfully deployed the Chandra X-ray Observatory. This is a telescope that literally everything that any of us know about black holes was revealed by this telescope. My third mission was my favorite, I have to say, because I got to live on the space station and I got to work there.
It's a test bed for going to the Moon and Mars, the weightless environment allows us to do experiments that we literally can't do here on Earth. It forms not just space exploration, but it's pivotal for improving lives down here on Earth as well.
It's absolutely amazing. Absolutely amazing. For a long time, we've been working with the space, you know, industry and adaptive computing part, co- products like our Xilinx FPGA play an important part. Can you give us a sense of how this technology is used in space?
When you asked me to be part of tonight, I, of course, had to do some homework. It was really fascinating for me to understand more about what a difference adaptive computing can make. I mean, for explorers, it gives them literally a whole new toolbox of tools that can solve many of the challenges that we face at every turn. I mean, space exploration is hard and by definition, is about investigating into the unknown, and it's seldom straightforward, and it's never, ever easy, especially when you put people on board those missions. Whether it's a planetary probe or a space station or a rover, they take years to design and launch these kinds of missions, and resources are limited. We have to plan the missions with the technology we have at the time.
It's really imperative that these critical technologies be adaptable. We need to be able to modify instruments and detectors. This was really big for me. We need instruments and detectors that so that after the mission is launched, then their functions can be changed. We can take advantage of innovation and optimize their functionality. I mean, for example, on the Perseverance Mars rover, adaptive technologies are used to help Perseverance or Percy, as many call her, it's true, to navigate on the surface of Mars using object recognition and terrain avoidance.
That same technology is actually used for being able to analyze rock and soil samples, and this is really critical right now at this moment where Perseverance is collecting these samples because some of those samples will be actually brought back here to Earth by the Mars Sample Return mission that is upcoming. It's really important and it's really invaluable to be able to, you know, adapt both hardware and software as missions evolve.
Yeah. I mean, it's such a, it's such a special use case to think about how the technology is being used. Now, I love hearing about, how our technology is being used. Now, all of us at AMD are extremely excited that we participated in the recent Artemis I mission. We had a lot of tech in Artemis. Can you tell us a little bit about why that's so important for the future of space exploration?
First, can I ask, did anybody either see the launch in person or watch it on TV? It was simply amazing to see. I did actually get to see it in person, I mean, this is the test mission, the Artemis program is designed to return humankind to the moon, not just to work there for a few days, but to stay and to use the lunar surface as a testing ground for sending humans to Mars. Artemis I was a test flight of both the space launch system and the Orion capsule, NASA launched the most powerful rocket that we have launched in 50 years to the moon, the Orion spacecraft returned 26 days later. The next mission will have humans on the moon.
I mean, this one tested, I'll say that again. This mission tested integrated systems for launching, for navigation and for reentry, and the next mission will have humans aboard that spacecraft in preparation for landing on the moon in future missions. They used adaptive technology for systems like engine controllers, for displays, for command systems, and the Orion capsule had more than 5,000 unique sensors, and that was just on the mannequins inside of the capsule, okay? There's really a lot that this is helping us understand the effects of the deep space environment on people.
I think it's amazing, really, if you think about all that we were able to put, there, and it's just something that, you know, we can't even imagine.
These missions are continuing and unfortunately, it's, you know, they're long in between, and that's where the adaptive part I think really comes in, is we don't wanna launch with, you know, many years ago, you know, technology. For me, I don't. You know, what I think is really amazing about the Artemis missions is that, you know, the moon is not just a bright shape in the sky for me anymore. It's a place that we are going. The name Artemis is the sister of Apollo. It's very fitting because the first woman and the first person of color will take those first steps on the moon. I think Lisa and I both have our hands up. You never know.
I'm retired from there now, but these are really exciting times. I mean, you should know that your child or the children of your friends and neighbors could very well someday live on the moon or travel to Mars.
I have to say, Cady, you know, looking at your career and what you've accomplished, I think I'm speaking for everybody in the audience here. You are such a role model and a true inspiration for so many people. Now, I know you're very passionate about STEM education and, you know, how do we bring more people into, you know, these types of environments. Can you just tell us a little bit about, you know, what you think we should be doing as an industry?
Well, the challenges I think that we face in exploration, I mean, they're big and they're hard. I think they demand courageous and inquisitive young people, younger than probably anybody in this room, that they bring their vision, their ingenuity, and their cross-disciplinary scientific expertise to innovation and to design. That is why STEM and STEAM are super critical.
I completely agree.
I think we can all help by making sure that all of us tell the stories of our work and our discoveries in ways that compel the next generation to play a part in exploration, whatever kind they choose. I mean, your stories can ignite curiosity, which is fundamental to science and exploration, and just one spark can make a difference. I know it did for me. It never occurred to me to become an astronaut until I was in college, and I went to the same college that Lisa did, a really neat technical school on the banks of the Charles River in Boston. Dr.
Sally Ride, the first American woman astronaut, came and she talked at MIT, and I went to listen to her, and that's when the light bulb really went off for me, which was that she was a person that I could relate to, and she had applied for and qualified for this amazing job. For me, it really was a revelation to realize that maybe I too could try to be qualified for that. As professionals in STEM fields, I think that we both understand the nature and the number of the challenges that we face. I mean, and due to those, I mean, we really cannot leave behind any potential teammates, especially those who think differently than a lot of people on our team already.
I'm actually just certain, Lisa, that if women had walked on the moon 60 years ago, every one of us in this room would have a different horizon today. That's one of the reasons that I'm so excited about Artemis and those goals becoming a reality. I mean, on these first missions, we may be sending just a few people to the moon, but we'll definitely be changing the world.
Katie, I would, you know, say I think you might have inspired a few people tonight. Thank you so much for being here, and thank you for all that you do.
Thank you and your team for having me. Thanks.
All right. Now for our final area of the night, let's turn to how we're bringing sustainable computing to the largest data centers in the world. Every day, billions of people around the world use our EPYC Data Center CPUs and Instinct accelerators. The leading cloud companies, including Amazon, Google, Microsoft, Meta, Oracle, and many more, have all deployed AMD technology in their data centers, and many of the largest enterprises in the world also use AMD technology, including financial services, healthcare, industrial, automotive, and even Formula 1. In entertainment, many of you may have seen Avatar: The Way of Water over the holidays. What you probably didn't know is that to really produce these movies, you need incredible technology. The artists at Wētā FX used AMD technology to build those stunning visuals. Let's take a look.
Creativity is an iterative process. The more performance we can get out of our workstations and servers, the more headroom and time the artists have to do their best work. We tested all of the technology available to us on the market at the time. AMD really came through for us. We found that it delivered the greatest performance per watt, per cabinet across our multiple workloads.
When we first installed the AMD EPYC CPUs, the comments and feedback that we received from artists and VFX supervisors was that they only wanted to use the new AMD EPYCs for their shows going forward.
Artists can now see their scene rendered live in front of them, whereas before, that would often have to go off and be on a render wall.
The partnership with AMD has been exceptional because it's been helping us drive forward solutions in creating some of the world's largest movies. Those types of partnerships are critical for the ongoing success of our industry.
At AMD, our job is to always push the envelope, especially in areas like high-performance computing and AI, where we're focused on meeting the insatiable demand for more compute in the most sustainable fashion. At the center of the modern data center is a high-performance CPU. Last November, we launched our 4th-gen EPYC processor, and it featured up to 96 Zen 4 cores and supports next generation memory and IO. 4th-gen EPYC is truly the world's best data center CPU with more than 300 world records. It also delivers leadership energy efficiency that translates into the best total cost of ownership.
When you look at the performance, EPYC is up to 3x faster in cloud, enterprise, and HPC applications and up to 2.6x faster in energy efficiency than the highest end processor from our competition. This is really critical as data center power consumption becomes a larger portion of the world's energy usage and IT departments manage higher energy costs and constrained energy supply. Let me put this in perspective in terms of numbers. If you take a typical rack in a data center, you can hold up to 15 servers. If you choose our competition servers, 15 servers would deliver 8,500 SPECint_rate performance. You can achieve that same level of performance with just five AMD 4th gen EPYC servers.
What this means, if you own a data center, this is just a huge benefit in terms of CapEx and OpEx. Now when you look at a broader perspective of what it means for sustainability at the industry scale, last year we deployed about 15 million servers worldwide. If you consider the performance and energy efficiency advantages of our 4th gen EPYC processors, that level, the impact is really profound. If you choose EPYC, you could save 52 billion kWh of electricity and avoid 26 million tons of CO2 emissions. To remove this much CO2 from our atmosphere would require 28 million acres of forest. That's actually more than all of the national forest land in the state of California. This is why we spend so much time on energy efficiency at AMD.
Now let me move to the world of data center AI, where the industry is focused on how to turn data into insights and actions. Today, we're gonna preview AMD's first inference accelerator. This is the AMD Alveo V70. It's built with AMD XDNA technology, that's the same AI engine processor that we talked about with Ryzen AI, but it's scaled up for use in servers to deliver 400 million AI operations per second. That's 400 trillion AI operations per second. We designed Alveo V70 to accelerate multiple AI models, including video analytics, customer recommendation engines, while delivering just great compute efficiency in a small form factor. Let's take a look at some of this performance. In video analytics applications, you need things like object detection, classification, and video code, decode real-time.
Alveo V70 delivers 70% more street coverage for smart city applications, 72% more hospital bed coverage for patient monitoring, and 80% more checkout lane coverage in a smart retail store than the competition, all of this is within a 75 watt power envelope. I'm very pleased to announce that we're gonna take pre-orders for the V70 cards today with availability this spring. Let me finish off here by talking about the largest computers in the world. The supercomputers used for the most advanced scientific research. We are very proud of our leadership in HPC. Today, the world's fastest supercomputer and the first to break the exaflop barrier actually resides at Oak Ridge National Labs, and it's powered by our AMD EPYC and Instinct technology. Actually, 75% of the world's top 20 most energy-efficient supercomputers are powered by AMD.
The next big challenge for the industry, it's about delivering the next step function of improvement in compute performance. That is processing even more data to enable the next generation of HPC and AI. To accomplish this, we've been developing the world's first data center processor that combines a CPU and GPU on a single chip. Our Instinct MI300 is the first chip that brings together a data center CPU, GPU, and memory into a single integrated design. What this allows us to do is share system resources for the memory and IO, and it results in a significant increase in performance and efficiency, as well as it's much easier to program. MI300 combines our next generation CDNA 3 GPU architecture that's optimized for HPC and AI performance, as well as 24 Zen 4 cores.
To feed all those compute engines, we added 128 GB of HBM3 memory. What we're doing here is it's actually extremely advanced technology. We're actually using 3D stacking to put multiple GPU and CPU chiplets on top of a base die, which connects the memory and the rest of the system. Let me show you one more chip tonight. This is a big one, guys. I am super proud to show you MI300 for the very, very first time. This is actually the most complex chip we've ever built. It has nine 5 nm chiplets that are 3D stacked on top of four 6 nm chiplets with significant HBM surrounding it, and it has more than 146 billion transistors.
From a performance standpoint on AI workloads, MI300 delivers 8 x more performance and 5 x better efficiency than our MI250X, which was already powering the world's fastest supercomputer. Let me tell you what this means. MI300 can train much larger AI models faster, at lower costs, and with less power. Just to put this in perspective, you know, over the holidays, there's been a lot of talk about, you know, ChatGPT and what you can do with these large language models. What you probably didn't know is that it takes months to train on thousands of GPUs that consume millions of dollars of electricity. MI300 can reduce the time to train these models from months to weeks with dramatically lower energy costs.
More importantly, it can also support much, much larger models that can be used for even more advanced and more powerful AI services in the future. I'm very happy to say Instinct MI300 is currently in the labs and will be sampling to customers shortly, and you can expect that we'll bring Instinct MI300 to market in the second half of this year for both HPC and AI solutions. It's been absolutely wonderful being here with you tonight, but it is time to wrap up. We showed you a ton of technology today, highlighting everything that we can do with high performance and adaptive computing.
Whether you're talking about mobile PCs or the best gaming processors or the next generation of AI, you know, the way we look at it is we as an industry have to come together with our partners and with the ecosystem to really solve some of the world's most important challenges. I am so happy and honored to be in this industry. This is the best time to be in semiconductors. It's the best time to be in tech, and I love what we're doing together. Thank you for being such a great audience here in Las Vegas, and thank you to everyone watching online. Have a great night.