[ad_1]
Speaker 1: Welcome to everyone who has joined us today in Taipei and from around the world as we open Compex 2024 in A MD. We love games. Today I’m excited to show you what’s next for ryzen PC gaming. Our new Ryzen 9000 processors are the fastest consumer PC processors in the world, bringing our new Zen five cores to the AM five platform. With support for the latest IO and memory technologies, including PCIE five [00:00:30] and DDR five, I am happy to show you now our brand new Z five Core Zen five is actually the next big step in high performance processors. And when you look at the technology behind it, we have so much new technology. We have a new dual-pipelined parallel front-end, and what it does is it improves branch prediction accuracy and reduces latency. It also allows us to provide much higher performance per clock. We also designed Zen [00:01:00] five with a wider CPU engine and instruction window to execute more instructions in parallel for leadership, computation, throughput and efficiency. As a result, compared to the Zen four, we get double the instruction bandwidth, double the module-to-module floating-point data bandwidth, and double the AI performance with the full throughput of the AV X five 12. All of this adds up to the product at RISE in the 9000 series and we deliver an average of 16% higher IPC [00:01:30] across a wide range of app and gaming benchmarks compared to the Zen four. Speaker 1: So now let me show you the top of the line growing 999.50x for the first time. Here it is. Speaker 1: We have 16 zen five cores, 32 threads up to 5.67 gigahertz boost, [00:02:00] large 80 megabyte cache at 170 watts TDP. It is the fastest consumer CPU in the world. We know all our fans love games. 99 50 x delivers best-in-class gaming performance across a wide range of popular games. Now with desktops, we know that enthusiasts want to have an infrastructure that allows you to build across multiple product generations. And we’re with Verizon. We just did [00:02:30] that. Our original Ryzen socket AM four platform launched in 2016 and we are now approaching year nine and have 145 CPUs and apus across 11 different product families in Socket AM four. And we’re actually still launching new products. We actually have several Ryzen 5000 processors coming next month, and we’re using the same strategy with Socket AM 5, which we now plan to support through 2027 and beyond. [00:03:00] So you’ll be seeing AM five processors from us for many, many years to come. Now in addition to the top of the stack growing 99 50x, we’re also announcing 12, eight, and six core versions that will bring Zen pet’s leadership performance to mainstream price points, all of which will go on sale in July. Speaker 1: We’re so excited to announce today our third generation of the rise of AI processors. Our news is growing in AI [00:03:30] series is actually a significant increase in computational and AI performance and sets the bar for what a copilot computer should be able to do. Thank you, Drew. Here we are. This is STR. strix is our next generation processor for ultra thin and premium notebooks and combines our new N five CPU faster RDNA 3.5 [00:04:00] graphics and the new XD NNA two NPUs. Thank you. Speaker 1: And when you look at what we have, it’s really the best technology on a chip. We have a new NPU that delivers industry leading 50 tops. Today we’re going to talk a lot about tops. 50 best computations that can power new AI experiences at very low power. We have our new N five cores [00:04:30] enabling all the computing performance for ULTRATHIN notebooks, and we have faster RDNA 3.5 graphics that truly bring best-in-class application acceleration as well as console-level gaming to notebooks. Now we have a few distortions. The flagship risen nine, HX three 70 has 12 and five cores, 24 threads, 36 megabytes of money. The industry’s most integrated NPU and our latest RDNA graphics. strix is simply the best [00:05:00] mobile processor. So let’s talk a little bit about what’s special about this new NPUN PS are really new and really there for all these AI applications and workloads. Speaker 1: Now compared to our previous generation XD A two has a large array of 32 AI tiles with twice the multitasking performance. It’s also a highly efficient architecture that delivers up to twice the energy efficiency of our previous generation at work [00:05:30] Gen AI loads. In addition to Microsoft, we’re also working with all the leading software developers, including Adobe, epic Games, SolidWorks, Sony, zoom and many more, to accelerate the adoption of AI-powered desktop applications. And by the end of 2024, we’re on track to have more than 150 ISVs developing for MD AI platforms for content creation, consumer gaming and productivity applications. Now to give [00:06:00] to take a look at some of these upcoming copilot plus computers, let me welcome our next guest, a very close partner and good friend, Enrique Lores, president and CEO of HP. Hello. Hello. Speaker 2: And we’re incredibly excited about the new family of products that we’re launching in a few weeks because Speaker 1: I think you’ve got a lot to show us. Is this true? Okay. I hope. Speaker 2: And that’s actually what’s new [00:06:30] generation, because we have done together, we can show it together. That’s great. This is the next generation omni book when we integrate the latest AI 300 series which, as Lisa said before, will be the first product to have 50 tips integrated into the device. And performance, as Pavin used to say, is critical because the will [00:07:00] allow us to continue to deliver amazing experiences to our customers. Speaker 1: Let’s welcome Luca Rossi, president of Lenovo Intelligent Devices Group. Luca, you’ve been holding something and I think you’re going to show us what it is. Is this true? Speaker 3: Well, I haven’t even had to show this yet since it’s something we won’t be announcing until later this year, but Lisa, you’re right. I felt it was too exciting [00:07:30] you seem Speaker 1: Very happy actually. Speaker 3: Yes, very happy. So straight from our research and development lab straight from our research and development lab. This is the first sneak peek at our new yoga laptop powered by third-generation growing artificial intelligence. This is Speaker 1: Beautiful. Speaker 3: Maybe we want to do left and right. Yes, that means me [00:08:00] can share more about today. I can I can This is very beautiful. Thank you. I can tell you that this device represents a significant leap forward in next-generation AI computing and will include some of the exclusive Lenovo IP AI features I mentioned, and that’s just the beginning. Speaker 1: Next, I’d like to welcome one of the most important visionaries and innovators in the Taiwan ecosystem and a very, very close partner, Johnny, she is the President of Jesus. Speaker 4: [00:08:30] I think later today at 4pm we’ll be unveiling a range of cutting-edge IPCs in our brand new Zen Book professional art portfolio. We reserve things and IG laptops powered by the third generation A MD growing AI processors. These new ground labs are equipped with the world’s most powerful MPU with 50 cannons [00:09:00] and the superior MB xFi architecture, which leads the industry in compute and AI performance. The third-generation AI-powered processor is the catalyst that brings personalized computing to everyone, from content creators to gamers and business professionals, and empowers them like never before. This advancement gives the new manual higher AI performance than the MacBook [00:09:30] while making it thinner and lighter. Actually is so proud and honored to be the first OEM partner to make the third generation of emerging AI systems available to consumers. It will be ready for purchase in July. Isn’t it amazing? Thank you. Speaker 1: I have something to show you today. This is actually a preview of our upcoming fifth generation Epic processor called turn. Speaker 1: [00:10:00] So please look at the turn for the first time. It has 192 cores and 384 threads and has 13 different chips built in three and six nanometer technology. There is a lot of technology in Turin. It supports all the latest memory and IO standards and is a replacement for our existing ones [00:10:30] fourth-generation Epic platforms Turn will extend Epic’s leadership in general and high-performance computing workloads. So let’s look at some of that performance. namd is a very intensive scientific software that simulates complex molecular systems and structures. When simulating 20 million per model, the 128-core version of Turin is more than three times faster than the best competition, allowing researchers to complete models faster [00:11:00] which could lead to breakthroughs in drug research, materials science and other fields. Turin now also features AI inference performance when running smaller large language models. Speaker 1: I want to show you a demo here. Now. What this demo compares is Turin’s performance in running a typical enterprise LAMA deployment of two virtual assistants with minimum guaranteed latency to provide a high-quality user experience. Both servers start by loading multiple LAMA duplicates [00:11:30] since each assistant is asked to summarize a document upload immediately, you can see that the spin-right server adds double the number of sessions in the same time period, while responding to user requests significantly faster than the competition. And until the other server reaches the maximum number of sessions, you will soon see it stop. Basically, it can no longer support latency requirements. Turn continues scaling and delivers consistent performance [00:12:00] of nearly four times as many tokens per second. Our customers are extremely excited about the turnaround and I know many of our partners are actually here in the audience today. And I mean we’re on track to launch in the second half of this year. Thank you for being such a great audience and having a great Compex 2024. Thank you. Speaker 5: Thank you.
[ad_2]
