Computer graphics, image processing, physics simulations, combinatorial optimizations, graph processing, database processing, and of course, the very famous linear algebra of deep learning.

計算機圖形學、圖像處理、物理模擬、組合優化、圖形處理、數據庫處理，當然還有非常著名的深度學習線性代數。

There are many types of algorithms that are very conducive to acceleration through parallel processing.

有許多類型的算法都非常有利於通過並行處理來加速。

So we invented an architecture to do that.

是以，我們發明了一種架構來實現這一目標。

By adding the GPU to the CPU, the specialized processor can take something that takes a great deal of time and accelerate it down to something that is incredibly fast.

通過將 GPU 添加到 CPU 中，專用處理器可以將需要大量時間的工作加速到令人難以置信的速度。

And because the two processors can work side by side, they're both autonomous and they're both separate, independent that is, we could accelerate what used to take 100 units of time down to one unit of time.

由於兩個處理器可以並肩工作，它們都是自主的，都是獨立的，也就是說，我們可以把過去需要 100 個組織、部門的時間加速到 1 個組織、部門的時間。

Well, the speed up is incredible.

嗯，速度快得令人難以置信。

It almost sounds unbelievable.

這聽起來幾乎令人難以置信。

It almost sounds unbelievable.

這聽起來幾乎令人難以置信。

But today I'll demonstrate many examples for you.

不過，今天我將為大家演示許多例子。

The benefit is quite extraordinary.

這種好處非同一般。

100 times speed up, but you only increase the power by about a factor of three.

速度提高 100 倍，但功率只提高了約 3 倍。

And you increase the cost by only about 50%.

而你只增加了大約 50% 的成本。

We do this all the time in the PC industry.

在個人電腦行業，我們經常這樣做。

We add a GPU, a $500 GPU, GeForce GPU, to a $1,000 PC, and the performance increases tremendously.

我們在一臺 1000 美元的電腦上添加一個 GPU，一個 500 美元的 GPU，GeForce GPU，性能就會大大提高。

We do this in a data center.

我們是在數據中心完成這項工作的。

A billion dollar data center, we add $500 million worth of GPUs, and all of a sudden, it becomes an AI factory.

一個價值十億美元的數據中心，我們添加價值五億美元的 GPU，一下子就變成了人工智能工廠。

This is happening all over the world today.

今天，這種情況正在世界各地發生。

Well, the savings are quite extraordinary.

那麼，節省的費用就非常可觀了。

You're getting 60 times performance per dollar.

每一元錢可以獲得 60 倍的性能。

100 times speed up, you only increase your power by 3X.

加速 100 倍，也只能增加 3 倍的能量。

100 times speed up, you only increase your cost by 1.5X.

加速 100 倍，成本只增加 1.5 倍。

The savings are incredible.

節省的費用令人難以置信。

The savings are measured in dollars.

節省的費用以美元計算。

It is very clear that many, many companies spend hundreds of millions of dollars processing data in the cloud.

很明顯，很多很多公司花費數億美元在雲端處理數據。

If it was accelerated, it is not unexpected that you could save hundreds of millions of dollars.

如果加快速度，節省數億美元並非意料之外。

Now, why is that?

這是為什麼呢？

Well, the reason for that is very clear.

原因很清楚。

We've been experiencing inflation for so long in general purpose computing.

在通用計算領域，我們已經經歷了很長時間的通貨膨脹。

Now that we finally came to, we're finally determined to accelerate, there's an enormous amount of captured loss that we can now regain.

現在，我們終於走到了這一步，我們終於下定決心要加速了，我們現在可以重新獲得大量的捕獲損失。

A great deal of captured, retained waste that we can now relieve out of the system, and that will translate into savings.

我們現在可以從系統中清除大量捕獲和保留的廢物，這將轉化為節約。

Savings in money, savings in energy.

節約資金，節約能源。

And that's the reason why you've heard me say, the more you buy, the more you save.

這就是你聽我說過的 "買得越多，省得越多 "的原因。