In the hyper-connected world of today, most of us are empowered by computers. Little do we realise that this power was born from decades of work! One of the key events that accelerated the spread of computers and computing power to the hands of the masses was the semiconductor revolution. Along with it came the integrated circuit (IC) (which was preceded by the transistor, of course, but that’s another story). The IC has grown in leaps and bounds since its inception. Dr. Gordon Moore is credited with coming up with a projection of this growth rate (Moore’s law) in terms of the number of transistors that can be fit into an IC, and boy was he right. What a visionary!
Something that gave me goosebumps is a paper written by Dr. Moore in 1965 for the Electronics magazine: "Cramming more components onto integrated circuits". What completely blew my mind was that word-for-word, his predictions had come true!
Let’s take a look at a few excerpts from the paper:
“… at least terminals connected to a central computer-automatic controls for automobiles, and portable communications equipment.”
The hottest topics of this decade: autonomous transport and mobile phones, both brought up right in the beginning!
“… the biggest potential lies in the production of large systems. In telephone communications, integrated circuits in digital filters will separate channels on multiplex equipment. Integrated circuits will also switch telephone circuits and perform data processing.”
Signal processing and advanced communication systems, another key area of IC application.
… applying [such] films directly to an active semiconductor substrate.
Not only does he talk about applications, but also on the manufacturing advances. A direct reference to a process that eventually became photolithography.
“That means by 1975, the number of components per IC for minimum cost will be 65,000.”
The initial projection, which has now boomed all the way to housing ~2 trillion transistors on a single die1!
“In fact, shrinking dimensions on an integrated structure makes it possible to operate the structure at higher speed for the same power per unit area.”
A nod to Dennard scaling, almost a decade before the seminal publication that would announce it!
“Perhaps newly devised design automation procedures could translate from logic diagram to technological realization without any special engineering.”
Electronic design automation (EDA) would go on to become one of the biggest industries. Modern EDA tools such as Quartus Prime do provide, in some sense, direct schematic-to-realization capabilities. This has also manifested in other important advances such as hardware description languages (HDLs), high-level synthesis (HLS). The modern VLSI and ASIC industry would be nothing without EDA. EDA plays a critical role in keeping the costs of today’s ICs down by saving huge amounts of money during the design and testing.
“The integrated r-f amplifier might well consist of integrated stages of gain …”
“The successful realization of such items as phased-array antennas, for example, using a multiplicity of integrated microwave power sources, could completely revolutionize radar.”
He’s even got things right in the linear IC domain! Multi-stage amplifier ICs are commonplace nowadays. Even radical applications such as radar-on-chip (RoC) have not gone unnoticed. Tesla cars use RoCs for their navigation, biomedical devices benefit from RoC, MIMO and other modern communication systems use ICs as the backbone of their designs. They certainly have revolutionized RADAR!
Although Moore’s law has slowly started declining in the past few years, the fact that it is still holding on for so long is in itself proof of the expertise and vision Dr. Moore had in his field. It is an incredible insight into how one must think in order to propel innovation.