In 1975, looking at the next decade, a guy named Gordon Moore revised his previous forecast of the number of integrated circuits in a microchip doubling every year to doubling every two years. Moore was not a prophet, nor a brilliant data analyst, but as his prediction held true, it later became known as a law.
The law has become more of a guide, influencing the policies for research and development of the largest companies and chip manufacturers in the world. And it, and a new machine helping to keep Moore’s law alive, are what your iPhone and those robots from Boston Dynamics with the best dance moves have in common.
Let There Be Light
First, we must understand lithography, an analogous method for making printed circuits. Technically defined, lithography is printing on a plane surface treated to repel the material being printed except where it is intended (or in the case of circuits, needed) to stick.
The use of light for this treating and etching process is common, but one machine, built by ASML, a Dutch company that has cornered the market for etching the tiniest nanoscopic features into microchips with light, is playing a huge role in keeping Moore’s law viable.
ASML introduced the first extreme ultraviolet (EUV) lithography machines for mass production in 2017, after decades spent mastering the technique, and the machine needed for the process is to put it mildly, massive and mind blowing. It’s expensive too, with a sticker price of around $150 million. TSMC, Samsung, and Intell are initial customers.
Amazon Prime won’t be enough to get the massive machine delivered, unless you have 40 freight containers, three cargo planes, and 20 trucks on standby. What’s the big deal with this machine, and why does it (and it’s future children) matter?
How it Works
Think of a machine the size of a bus with 2 kilometers of cabling and over 100,000 parts. Inside are a series of nano-mirrors polished to precision that literally project extremely focused ultraviolet light into future chips to etch features that are often just a few atoms wide. That’s right, atoms.
This means chips with components smaller (and more durable in many ways) than they have ever been. Smaller chips that are just as powerful, nano-sensors that are just as sensitive or accurate in a fraction of the space they take up now, and more will enable chips to get tinier, lighter, and more powerful than ever before.
The Moore’s Law Limit
How small can chips get? Some think that Moore’s law is reaching the point where it is no longer viable, for three key reasons:
- Electrical leakage – As transistors get smaller, they at first become more efficient, but as they have reached nano-size, the transistor often can’t handle all of the electricity, and that means heat, and heat means potential damage to the transistor and maybe even the entire chip in some circumstances. Therefore, we can only decrease the size of a chip as we increase cooling power.
- Heat – The electrical leakage and resulting heat means that one of two things must be limited: the amount of voltage or the number of the transistors in a given chip, thus limiting the power. The technology of Extreme Ultroviolet Lithography may offer some help in this area, but that remains unknown.
- Economics – The price of this machine is just one factor. As chips get hotter and need more cooling the cost of keeping a data center at a viable temperature goes up, and that cost must be passed on to someone, generally the consumer. And businesses also want to extend the life of their equipment, ensuring it lasts as long as possible. Faster equipment with a shorter lifespan may not be as appealing to the average buyer or data center manager.
What does all this mean when we break it down?
Well, the data center of tomorrow may be a fraction of the size of those we have today. Or it may be equally as large, but able to store and deliver data at rates we can’t even imagine. Equipment, servers, remote sensors, everything may keep shrinking, to a point. But there will be a point when Moore’s law will no longer be valid or achievable, and that day may come sooner rather than later.
Are you running the data center of today, but looking forward to the data center of tomorrow? Are you interested in the latest remote monitoring and cabling solutions? Contact us at AnD Cable Products. We’d love to talk about what tomorrow looks like, and how we can help you head the right direction today.
WHITEPAPER – Optimizing Server Cabinet Rack Space to Maximize Efficiency and Reduce Costs
- How Much Rack Space You Could Save
- How to Optimize for Maximum Efficiency
- Savings for New and Retrofit Installations
- Overall Cost and Space Savings Post-Optimization
About the Author
Louis Chompff – Founder & Managing Director, AnD Cable Products
Louis established AnD Cable Products – Intelligently Designed Cable Management in 1989. Prior to this he enjoyed a 20+ year career with a leading global telecommunications company in a variety of senior data management positions. Louis is an enthusiastic inventor who designed, patented and brought to market his innovative Zero U cable management racks and Unitag cable labels, both of which have become industry-leading network cable management products. AnD Cable Products only offer products that are intelligently designed, increase efficiency, are durable and reliable, re-usable, easy to use or reduce equipment costs. He is the principal author of the Cable Management Blog, where you can find network cable management ideas, server rack cabling techniques and rack space saving tips, data center trends, latest innovations and more.
Visit https://andcable.com or shop online at https://andcable.com/shop/