The Latest and Greatest AI Chips. How Fast and How Much?

The Latest and Greatest AI Chips

How Fast and How Much?

We’ve heard of Artificial Intelligence (AI) and the computers required to carry out the job required. They consume massive power but can accomplish near-miraculous data processing tasks. But how fast and how much are values mostly unknown to most of us. Let’s look under the hood to get some idea of what’s inside.

The latest and greatest NVIDIA chip, the Blackwell GB200, is a key component of the NVIDIA GB200 NVL72, a multi-node, liquid-cooled, rack-scale system, which comprises 600,000 parts, including 72 GB200s. It's designed to be capable of delivering 720 petaflops* for training and 1.4 exaflops* for inferencing. (And it reportedly weighs 3,000 pounds – about the same as a mid-sized car.) Nvidia's Blackwell AI chip is expected to cost between $30,000 and $40,000 per unit, according to CEO Jensen Huang. This price is competitive with current Nvidia AI chips.

Nvidia's Blackwell generation boosts power consumption even further, with the B200 consuming up to 1,200W, and the GB200 (which combines two B200 GPUs and one Grace CPU) expected to consume 2,700W (Watts per hour). To better understand 2700W, note that the home A/C unit normally consumes about 3000W/hr.

Conclusion. AI chips are big, heavy, fast, and consume vast amounts of electrical power. It is no wonder that modern data centers require their own power-generating plants (also huge).

NOTES.

1. For reference, a typical PC CPU chip weighs about 1.0 ounces. So, the Blackwell chip weights 3000/(1/16) = 48000 PC CPU chips. At $500 per CPU chip, this comes to about $24 million.

2. For reference, the speed of the Blackwell is roughly 10,000 times faster than that of a typical desktop PC. Typical supercomputers run at speeds of 100 petaflops, which is faster than the Blackwell, but not by orders of magnitude. These speeds are almost beyond imagination – certainly mine.

3. Intel claims its Gaudi 3 chip is 1.5 times faster than the Blackwell. It should be launched later in 2024. If you know anything about Gaudi architecture in Spain, you will be amused.

4. The new Tesla Data Center in Austin, TX will employ up to 85,000 Blackwell chips by the end of 2024.

5. It is easy to understand why China wants to take over Taiwan, where these chips are manufactured. And not to bomb it to smithereens (easy), but intact. It’s easy to see why the USA (and the rest of the world) should try to prevent this. Whoever thought chips would be more important than bombs in warfare?

6. All the information, except for a few comparisons, in this report is available on the Internet.

*Petaflop: a unit of computing speed equal to one thousand million million (10¹⁵) floating-point operations per second. An exaflop (10¹⁸) is 1000 times faster than a petaflop. A FLOP is the time it takes to multiply floating point numbers, not just integers, but all kinds of numbers, where an exponent is needed to indicate magnitude) in the range from the tiniest to the largest.

P.S. When I did supercomputing some years back, chip speed was measured in GIGAFLOPS. These new chips are millions of times faster.

Human Simulation is Possible - by Humans

Human Simulation: Agent-Based Modeling and the Computational Case for Our Reality 1. Introduction In the essay, we introduce the notion that humanity could be a deliberate simulation based on an extremely simple single-celled organism, hardly anything more complex than that. This will allow an (apparently) new interpretation of the notion that humanity is simulated, but that there is no master engineer at a massive number of dials and switches, responsible for every twist and turn of our universe and lives. We begin with the notion that the universe exists and operates under its own laws. So, given the Earth [2] , when and where life first began, it was infused with a living agent, self-actualized, reproductive, and with other basic rules for its operations, interactions, and much of what single-celled organisms do today. The idea from this occurred some years back when writing code in ActionScript (formerly Flash), I was able to create...

The Calculus of Ideas and Patterns

Introduction. When dealing with ideas, patterns, intuition, and brainstorming, we need operations or rules not unlike those of arithmetic. The goal is not proof, a finished device, or a fait accompli , but rather a foundation for further investigation and study. In some cases, these operations may yield a proposition, that is, something capable of being proved. In this sense, they form a practical logic of intuition. The article concludes with a few select examples from a variety of venues. Setting. We are working with a given idea, problem, or project, or simply just thinking. Our aim is to discover pathways, patterns, or conceptual connections that may be useful. The following operations describe ways in which ideas and patterns can be generated, transformed, or refined. These also work toward understanding the imagination. Yet, this framework is distinguished from formal logic and proof. We are tempted to call them as “soft logic” because while nothing is proved, reasons...

Freedom of Speech

Think of freedom of speech as a living organism. Then think of what is required for it to survive. Coming to mind are a population agreeable to its constitution (its environment) and the institutions (its nutrients) that keep it healthy. Currently, many institutions, including some political parties, question unfettered freedom of speech and are working to deny it, claiming it is unhealthy for the body politic. Yes? No?

First Blog

Search This Blog