Pat Gelsinger
① 他说过的话
13 条
现在已经没有什么东西是一块芯片了,而是一个机架。
指向原始笔记的链接
Nothing’s a chip anymore, it’s a rack.
—— Pat Gelsinger · [00:22]
所以,我可以三个月就把这东西设计出来,但实际上我没法在九个月内把它大规模做成真正的硅片。
指向原始笔记的链接
So, I can design the thing in three months, but I can’t actually get it into real silicon at scale for nine months.
—— Pat Gelsinger · [10:20]
而且,正如我所说,HBM 是一种糟糕的内存,它只是我们目前拥有的最好的选择。
指向原始笔记的链接
And, you know, for that, as I’ve described, HBM is a hideous memory. It’s just the best one that we’ve got.
—— Pat Gelsinger · [12:12]
你知道,它们不会全都赢,它们不会全都赢,因为归根结底,你必须在这些东西上获得规模。
指向原始笔记的链接
And you know, they’re not all going to win and they’re not all going to win because at the end of the day, you have to get scale on these things.
—— Pat Gelsinger · [18:09]
所以我认为,说会有上百家这样的东西,是有点违背逻辑的。
指向原始笔记的链接
So I think it sort of defies logic that you’re going to have a hundred of these things.
—— Pat Gelsinger · [18:20]
那么过去 30 年里,我们到底有过多少种主要的新内存?零。
指向原始笔记的链接
And exactly how many major new memories have we had over the last 30 years? Zero.
—— Pat Gelsinger · [23:17]
但我认为三十年来的首次存储创新即将到来。
指向原始笔记的链接
But I think memory innovation for the first time in 30 years is nigh upon us.
—— Pat Gelsinger · [26:55]
而每比特通信的飞焦耳相对而言差了大约一千倍。
指向原始笔记的链接
The femtojoules per bit of communication is comparatively a thousand times worse.
—— Pat Gelsinger · [33:35]
我大约 25 年前就宣告了铜的死亡。最终,我会是对的。
指向原始笔记的链接
I declared the death of copper about 25 years ago. Eventually, I’ll be right.
—— Pat Gelsinger · [35:10]
你知道,实际上,我本来就不应该建造 NVL 72。这是一项工程奇迹,但也是一场制造噩梦,对吧?
指向原始笔记的链接
You know, in reality, I should have never built an NVL 72. You know, it’s an engineering marvel and it’s a manufacturing nightmare, right?
—— Pat Gelsinger · [36:47]
因为在 AI 数字时代,能源容量等于经济容量。
指向原始笔记的链接
Because in a AI digital age, energy capacity equals economic capacity.
—— Pat Gelsinger · [43:53]
而且我认为你会看到越来越多的数据中心项目出现违约,因为能源不会到位。
指向原始笔记的链接
And I think you’re going to see more and more defaults happening on many of those data center projects because the energy won’t be there.
—— Pat Gelsinger · [45:28]
顺便说一下,作为工作负载演进的另一个特征,我确实认为训练和推理的分离未来会变得不那么明显,而不是更明显。
指向原始笔记的链接
By the way, as another characteristic of workload evolution, I do think the separation of training and inferencing is going to become less so going forward, not more so.
—— Pat Gelsinger · [40:41]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Intel · VMware · Playground Global · NVIDIA · OpenAI · Anthropic · HBM · 记忆 · 推理 · 智能体
