{"id":20854,"date":"2022-12-04T14:04:11","date_gmt":"2022-12-04T14:04:11","guid":{"rendered":"https:\/\/mailinvest.blog\/index.php\/2022\/12\/04\/what-is-moores-law-and-why-are-people-saying-its-dead\/"},"modified":"2022-12-04T14:04:11","modified_gmt":"2022-12-04T14:04:11","slug":"what-is-moores-law-and-why-are-people-saying-its-dead","status":"publish","type":"post","link":"https:\/\/mailinvest.blog\/index.php\/2022\/12\/04\/what-is-moores-law-and-why-are-people-saying-its-dead\/","title":{"rendered":"What Is Moore\u2019s Law and Why Are People Saying It\u2019s Dead?"},"content":{"rendered":"

<\/a>\n<\/p>\n

\n
\"Iridescent
Quardia\/Shutterstock.com<\/a><\/span><\/figcaption><\/figure>\n

Moore’s “Law” is an observation by Intel founder Gordon Moore that transistor density doubles at intervals while staying the same price. Some in the industry think that those days are over.<\/p>\n

Gordon Moore, the co-founder of Intel, is the man responsible for Moore\u2019s Law. It\u2019s an observation Moore made that the transistor density of integrated circuits doubles every two years. Some say that Moore\u2019s Law is now dead, but why?<\/p>\n

What Moore\u2019s Law Says<\/h2>\n

Gordon Moore made his original observation<\/a> in 1965:<\/p>\n

\n

\u201cThe complexity for minimum component costs has increased at a rate of roughly a factor of two per year. Certainly over the short term this rate can be expected to continue, if not to increase. Over the longer term, the rate of increase is a bit more uncertain, although there is no reason to believe it will not remain nearly constant for at least 10 years.\u201d \u2013 Gordon Moore in\u00a0Cramming more components onto integrated<\/em> circuits.<\/a><\/p>\n<\/blockquote>\n

This can be interpreted in a few ways, but it implies two things. First, (at the time) the most basic Integrated Circuit (IC) would double in transistor density every year. Second, that this would also be true at the lowest cost level. So if the cost to manufacture an IC of a given size remains stable over time (taking inflation into account), this would effectively mean that the cost per transistor would halve every two years.<\/p>\n

\"FinFET
Ascannio\/Shutterstock.com<\/a><\/span><\/figcaption><\/figure>\n

This is a startling level of exponential growth demonstrated by the \u201cwheat and chessboard problem<\/a>\u201d where if you put one grain of wheat (or rice) on the first square and then double the amount for each successive square, you\u2019d be up to\u00a0well over 18 quintillion grains by square 64!<\/p>\n

Moore later revised his observation to extend the time to once every eighteen months, and then eventually once every two years. So while transistor density is still doubling, the pace seems to be slowing down.<\/p>\n

It\u2019s Not Actually a Law<\/h2>\n

Although it\u2019s been nicknamed Moore\u2019s \u201cLaw,\u201d it isn\u2019t a law in the proper sense of the word. In other words, it\u2019s not like a natural law that describes how things like gravity work. It\u2019s an observation and a projection of historical trends into the future.<\/p>\n

On average, Moore\u2019s Law has held up since 1965, and in some ways, it\u2019s a benchmark for the semiconductor industry<\/a> to tell roughly whether it\u2019s on track, but there\u2019s no reason why it has to be true, or remain true indefinitely.<\/p>\n

There\u2019s More to Performance Than Transistor Density<\/h2>\n

The transistor is the fundamental component of a semiconductor device, such as a CPU<\/a>. It\u2019s from transistors that devices such as logic gates are built, allowing for the structured processing of data in binary code<\/a>.<\/p>\n

In theory, if you double the number of transistors that you can fit into a given amount of space, you double the amount of processing that can happen. However, not just how many transistors you have but what you do with them counts. Microprocessors have received many advancements in efficiency, with specialized designs to accelerate specific types of processing, such as decoding video or doing the specialized math needed for machine learning.<\/p>\n

Shrinking transistors generally also means reaching higher operating frequencies while using less power for the same amount of processing power from a previous generation. Moore\u2019s Law is confined to transistor density, but the relationship between transistor density and performance isn\u2019t linear.<\/p>\n

What Do You Mean \u201cIt\u2019s Dead\u201d?<\/h2>\n

Over the years, the phrase \u201cMoore\u2019s Law is dead\u201d has been uttered several times, and whether that\u2019s true depends on your perspective. Transistor densities are still doubling, but at a slower pace as Moore has revised the time frame several times now.<\/p>\n

The reason why some contend that the law is dead isn\u2019t that transistor density isn\u2019t still doubling, but that the cost of transistors isn\u2019t halving. In other words, you can\u2019t get twice the number of transistors for the same money after a doubling cycle anymore.<\/p>\n

One important part of why this is happening is because we\u2019re approaching the limits of how small we can make transistors. At the time of writing, 5nm<\/a> and 3nm manufacturing processes are the current and next generation of technology. As we push towards the ultimate limit of what\u2019s possible, the number of problems and the cost of overcoming them are both likely to increase.<\/p>\n

However, just because transistors may not be halving in price the way they used to does not mean that performance isn\u2019t doubling or halving in price. Remember, transistor count is only one part of performance. We\u2019re achieving higher clock speeds, fitting more cores into a single processor unit, doing more with our transistors, and creating novel silicon that can accelerate specific jobs such as machine learning<\/a>. In this expanded sense, Moore\u2019s Law still has life in it, but in its original form, it\u2019s on life support.<\/p>\n

Moore\u2019s Law Has to Die Sometime<\/h2>\n

No one ever believed that Moore\u2019s observation about transistor density and cost would hold true forever. After all, the exponential plot would eventually trend towards infinite transistor density and computing performance. As far as anyone knows, that\u2019s not actually possible, and it\u2019s particularly unlikely to be possible using semiconductor electronics as we know them today.<\/p>\n

There are already numerous challenges with the tiny components in modern processors struggling with unwanted quantum effects. At some point, you can\u2019t keep electrons inside your tiny circuits anymore, so trying to make things smaller hits a brick wall.<\/p>\n

At that point, it may be time to move to another type of computing substrate, such as photonics<\/a>, but there are likely myriad ways to get more performance from semiconductors that don\u2019t involve making transistors smaller.<\/p>\n

We\u2019re already seeing cost-effective ways to build large processors from multiple smaller processors, such as AMD\u2019s chiplet designs<\/a> or Apple\u2019s strategy of gluing their baseline chips together<\/a> to make mega CPUs that operate as if they were one system. There\u2019s potential in the idea of building CPUs with 3D circuits<\/a>, with layers of microchip components that communicate vertically and horizontally.<\/p>\n

While the ultimate limit of transistor density seems to get closer and closer every day, the true limit of achievable computing power is still an open question.<\/p>\n

RELATED:<\/strong> Huge Supercomputers Still Exist. Here’s What They’re Being Used for Today<\/em><\/strong><\/a><\/p>\n<\/div>\n