Name: 超微半導體 AMD 2024 年電腦展演講，12 分鐘濃縮重點！ (AMD's 2024 Computex Keynote: Everything Revealed in 12 Minutes)
Uploaded: 2024-06-06T09:37:08.000Z
Duration: 12 min 31 s

Welcome to everyone joining us today in Taipei and from around the world as we open Computex 2024.

歡迎今天在臺北和來自世界各地的各位參加 2024 年臺北國際電腦展開幕式。

Today, I'm excited to show you what's next for PC gaming with Ryzen.

今天，我很高興向大家展示 Ryzen 為 PC 遊戲帶來的下一步發展。

Our new Ryzen 9000 CPUs are the world's fastest consumer PC processors, bringing our new Zen5 core to the AM5 platform with support for the latest I.O.

我們的新型 Ryzen 9000 CPU 是世界上速度最快的消費類 PC 處理器，為 AM5 平臺帶來了全新的 Zen5 內核，支持最新的 I.O.技術。

and memory technologies including PCIe5 and DDR5.I'm happy to show you now our brand new Zen5 core.

我很高興現在向大家展示我們全新的 Zen5 內核。

Zen5 is actually the next big step in high performance CPUs and when you look at the technology behind this, we have so much new technology.

實際上，Zen5 是高性能 CPU 的下一個重大進步。

We have a new parallel dual pipeline front end and what this does is it improves branch prediction accuracy and reduces latency.

我們有一個新的並行雙流水線前端，其作用是提高分支預測的準確性並減少延遲。

It also enables us to deliver much more.We also designed Zen5 with a wider CPU engine and instruction window to run more instructions in parallel for leadership compute throughput and efficiency.

在設計 Zen5 時，我們還採用了更寬的 CPU 引擎和指令窗口，以並行方式運行更多指令，從而提高計算吞吐量和效率。

As a result, compared to Zen4, we get double the instruction bandwidth, double the data bandwidth between the cache and floating point unit, and double the AI performance with full AVX-512 throughput.

是以，與 Zen4 相比，我們獲得了雙倍的指令帶寬、雙倍的高速緩存和浮點運算單元之間的數據帶寬，以及雙倍的人工智能性能和完整的 AVX-512 吞吐量。

All of this comes together in the product in Ryzen 9000 series and we're delivering an average of 16% higher IPC across a broad range of application benchmarks and games compared to Zen4.So now let me show you the top of the line Ryzen 9 9950X for the very first time.

與 Zen4 相比，Ryzen 9000 系列在各種應用基準測試和遊戲中的 IPC 平均提高了 16%。

We have 16 Zen5 cores, 32 threads, up to 5.67 gigahertz boost, a large 80 megabyte cache at 170 watt TDP.

我們有 16 個 Zen5 內核、32 個線程、高達 5.67 千兆赫的提升頻率、80 兆字節的大緩存、170 瓦的 TDP。

This is the fastest consumer CPU in the world.We know all of our fans love gaming.

這是世界上速度最快的消費級 CPU。我們知道，我們所有的粉絲都熱愛遊戲。

The 9950X 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 lets you upgrade across multiple product generations and with Ryzen, we've done just that.

對於臺式機而言，我們知道發燒友希望擁有一種可讓您跨多代產品升級的基礎架構，而 Ryzen 正是這樣一款產品。

Our original Ryzen platform, Socket AM4, launched in 2016 and now we're approaching the ninth year and we have 145 CPUs and APUs across 11 different product families in Socket AM4 and we're actually still launching new products.

我們最初的 Ryzen 平臺 Socket AM4 於 2016 年推出，現在已經接近第九個年頭，我們在 Socket AM4 上擁有 11 個不同產品系列的 145 款 CPU 和 APU，而且我們實際上仍在不斷推出新產品。

We actually have a few Ryzen 5000 CPUs that are coming next month and we're taking this exact same strategy with Socket AM5 which we now plan on supporting through 2027 and beyond.

實際上，我們下個月將推出幾款 Ryzen 5000 CPU，我們對 Socket AM5 也採取了完全相同的策略，現在我們計劃將其支持到 2027 年及以後。

So you're going to see AM5 processors from us for many, many years to come.Now in addition to the top of the stack Ryzen 9950X, we're also announcing the 12, 8, and 6 core versions that will bring the leadership performance of Zen 5 to mainstream price points and all of these go on sale in July.We're so excited to announce today our third gen Ryzen AI processors.

是以，在未來的很多很多年裡，你都會看到我們的 AM5 處理器。現在，除了頂級的 Ryzen 9950X 之外，我們還發布了 12 核、8 核和 6 核版本，它們將把 Zen 5 的領先性能帶入主流價位，所有這些處理器都將在 7 月份上市。

Our new Ryzen AI series actually is a significant increase in compute and AI performance and sets the bar for what a co-pilot PC should do.

實際上，我們的全新 Ryzen AI 系列大幅提升了計算和人工智能性能，併為副駕駛 PC 設定了標準。

Strix is our next generation processor for ultra-thin and premium notebooks and it combines our new Zen 5 CPU, faster RDNA 3.5 graphics, and the new XDNA 2 NPU.

Strix 是我們針對超薄和高端筆記本電腦推出的下一代處理器，它結合了我們全新的 Zen 5 CPU、更快的 RDNA 3.5 圖形處理器和全新的 XDNA 2 NPU。

And when you look at what we have, it really is all of the best technology on one chip.

當你看到我們的產品時，你會發現它確實是集所有頂尖技術於一身的芯片。

We have a new NPU that delivers an industry-leading 50 tops.

我們有一個新的 NPU，可提供業界領先的 50 個頂點。

We're going to talk about tops a lot today.

50 tops of compute that can power new AI experiences at very low power.

50 頂尖的計算能力，能以極低的功耗為新的人工智能體驗提供動力。

We have our new Zen 5 core that enables all the compute performance for ultra-thin notebooks and we have faster RDNA 3.5 graphics that really brings the best-in-class application acceleration as well as console-level gaming to notebooks.Now we have a couple of SKUs.

我們擁有全新的 Zen 5 內核，可以為超薄筆記本電腦提供所有的計算性能，我們還擁有更快的 RDNA 3.5 圖形處理器，真正為筆記本電腦帶來了同類最佳的應用加速和遊戲機級別的遊戲體驗。

The flagship Ryzen 9 HX370 has 12 Zen 5 cores, 24 threads, 36 megabytes of cache, the industry's most integrated NPU, and our latest RDNA graphics.

旗艦 Ryzen 9 HX370 擁有 12 個 Zen 5 內核、24 個線程、36 兆字節高速緩存、業界集成度最高的 NPU 以及我們最新的 RDNA 圖形處理器。

Strix is simply the best mobile CPU.So let me talk a little bit about what's special in this new NPU.

讓我來談談這款全新 NPU 的特別之處。

NPUs are really new and they're really there for all of these AI applications and with double the multitasking performance.

NPU 確實是一種新技術，它們確實適用於所有這些人工智能應用，並且具有雙倍的多任務處理性能。

It's also an extremely efficient architecture that delivers up to two times better energy efficiency of our prior generation when running gen AI workloads.In addition to Microsoft, we're also working with all of the leading software developers including Adobe, Epic Games, SolidWorks, Sony, Zoom, and many others to accelerate the adoption of AI-enabled PC apps.

除了微軟，我們還與包括 Adobe、Epic Games、SolidWorks、索尼、Zoom 等在內的所有領先軟件開發商合作，以加快採用支持人工智能的 PC 應用程序。

And by the end of 2024, we're on track to have more than 150 ISVs developing for AMD AI platforms across content creation, consumer, gaming, and productivity applications.Now to give us a look at some of these upcoming Copilot Plus PCs, let me welcome our next guest, a very close partner and good friend, Enrique Lloras, HP President and CEO.

到 2024 年底，我們將有 150 多家 ISV 為 AMD AI 平臺開發內容創作、消費、遊戲和生產力應用。現在，讓我們來看看這些即將推出的 Copilot Plus PC，讓我歡迎下一位嘉賓，一位非常親密的合作伙伴和好朋友，惠普總裁兼首席執行官恩裡克-洛拉斯。

And we are incredibly excited about the new family of products we will be launching in a few weeks.

我們對幾周後即將推出的新產品系列感到無比興奮。

So I think you have something to show us, is that right?

我想你有東西要給我們看，是嗎？

Since we have done together, we can show it together.

既然我們一起做過，就可以一起展示。

This is the next generation Omnibook when we integrate the latest Raytheon AI 300 series that, as Lisa was saying before, will be the first product that will have 50 tops integrated in the device.

這是下一代 Omnibook，我們將集成最新的雷神人工智能 300 系列，正如麗莎之前所說，這將是第一款在設備中集成 50 個頂級功能的產品。

And performance, as Pavel was saying, is critical because it will enable us to continue to deliver incredible experiences to our customers.Let's welcome Luca Rossi, President of Lenovo Intelligent Devices Group.

正如帕維爾所說，性能至關重要，因為它將使我們能夠繼續為客戶提供令人難以置信的體驗。

Now, Luca, you've been holding something and I think you're going to show us what it is.

盧卡，你一直拿著什麼東西，我想你要給我們看是什麼。

Well, I wasn't supposed to even show this yet, since this is something we will not announce until later this year.

好吧，我本來還不應該展示這個的，因為這是我們今年晚些時候才會宣佈的事情。

So straight from our R&D, straight from our R&D lab, this is the first ever sneak peek at our new yoga laptop powered by third gen Ryzen AI.

這是我們的研發實驗室首次展示搭載第三代 Ryzen AI 的全新瑜伽筆記本電腦。

Yeah, so I can't share more for today, but I can tell you this device represents a significant leap forward in next generation AI computing.

是的，今天我不能分享更多，但我可以告訴你，這款設備代表了下一代人工智能計算的重大飛躍。

It will include some of the Lenovo exclusive IP AI features that I mentioned.

它將包括我提到的一些聯想獨有的 IP AI 功能。

And this is just the beginning.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 Hsu, Chairman of ASUS.

接下來，我要歡迎臺灣生態系統中最重要的遠見卓識者和創新者之一，也是我們非常非常親密的合作伙伴，華碩董事長許智強。

I think later today at 4pm, we'll be unveiling a range of cutting edge AI PCs across our portfolio with brand new ZenBook, ProArt, VivoBook, ASUS TUF, and ROG laptops powered by the third gen AMD Ryzen AI processors.

我想，今天下午 4 點，我們將在我們的產品組合中推出一系列尖端的人工智能 PC，包括搭載第三代 AMD Ryzen AI 處理器的全新 ZenBook、ProArt、VivoBook、ASUS TUF 和 ROG 筆記本電腦。

These new lineups are equipped with the world's most powerful MPU with 50 tops and the superior AMD Zenfire architecture that leads the industry in compute and AI performance.

這些新產品系列配備了世界上最強大的處理器，擁有 50 個頂級處理器和卓越的 AMD Zenfire 架構，在計算和人工智能性能方面處於行業領先地位。

The third gen Ryzen AI processor is the catalyst to bring in personalized computing to everyone from content creators to gamers and business professionals and empower them like never before.

第三代 Ryzen AI 處理器是為從內容創作者到遊戲玩家和商務人士的每個人帶來個性化計算的催化劑，並賦予他們前所未有的能力。

This advancement gives the new ZenBook higher AI performance than MacBook while making it thinner and lighter as well.

這一進步使新款 ZenBook 的人工智能性能高於 MacBook，同時也使其更加輕薄。

ASUS is so proud and honored to be the first OEM partner to make the third gen Ryzen AI systems available to consumers.

華碩非常自豪和榮幸能夠成為首家向消費者提供第三代 Ryzen AI 系統的 OEM 合作伙伴。

Thank you.So I have something to show you today.

謝謝。今天我有東西要給你們看。

It's actually the preview of our upcoming fifth gen EPYC processor codenamed Turin.

實際上，這是我們即將推出的代號為 Turin 的第五代 EPYC 處理器的預覽版。

So please take a look at Turin for the very first time.

所以，請大家第一次來都靈看看吧。

Turin features 192 cores and 384 threads and has 13 different chiplets built in 3 and 6 nanometer process technology.

Turin 擁有 192 個內核和 384 個線程，採用 3 納米和 6 納米工藝技術，內置 13 種不同的芯片。

It supports all the latest memory and I.O.

它支持所有最新的內存和 I.O.。

standards and is a drop-in replacement for our existing fourth gen EPYC platforms.

標準，可直接替代我們現有的第四代 EPYC 平臺。

Turin will extend EPYC's leadership in general purpose and high performance computing workloads.So let's take a look at some of that performance.

都靈將擴大 EPYC 在通用和高性能計算工作負載方面的領先地位。

NAMD is a very compute intensive scientific software that simulates complex systems and structures.

NAMD 是一種計算密集型科學軟件，用於模擬複雜的系統和結構。

When simulating a 20 million atom model, a 128 core version of Turin is more than three times faster than the competition's best, enabling researchers to more quickly complete models that can lead to breakthroughs in drug research, material science, and other fields.

在模擬 2000 萬個原子模型時，128 核版本的都靈比競爭對手的最佳版本快三倍多，使研究人員能夠更快地完成模型，從而在藥物研究、材料科學和其他領域取得突破。

Now Turin also excels at AI inferencing performance when running smaller large language models.

現在，在運行較小的大型語言模型時，Turin 的人工智能推理性能也非常出色。

所以，我想在這裡給大家演示一下。

Now what this demo compares is the performance of Turin when running a typical enterprise deployment of LLAMA 2 virtual assistants with a minimum guaranteed latency to ensure a high quality user experience.

這個演示比較的是都靈在運行典型企業部署的 LLAMA 2 虛擬助手時的性能，並保證最低延遲，以確保高質量的用戶體驗。

Both servers begin by loading multiple LLAMA 2 instances with each assistant being asked to summarize an uploaded document.

兩臺服務器首先都加載了多個 LLAMA 2 實例，要求每個助手對上傳的文檔進行總結。

Right away you can see that the Turin server on the right is adding double the number of sessions in the same amount of time while responding to user requests significantly faster than the competition.

一眼就能看出，右側的都靈服務器在相同的時間內增加了兩倍的會話數量，同時響應用戶請求的速度明顯快於競爭對手。

And while the other server reaches a maximum number of sessions, you'll see it stop soon, it basically can't support the latency requirements anymore.

當另一臺服務器達到最大會話數的時候，你會發現它很快就會停止，因為它基本上已經無法支持延遲要求了。

Turin continues scaling and delivers a sustained throughput of nearly four times more tokens per second.

Turin 還在繼續擴展，每秒可提供近四倍的代幣持續吞吐量。

 Our customers are super excited about Turin, and I know many of our partners are actually here in the audience today, and

我們的客戶對都靈感到非常興奮，我知道我們的許多合作伙伴今天也來到了現場，而且