feature article
Subscribe Now

Square Root of Two to the Fortieth

Four Decades of Moore

The athlete leans for the tape, pouring his last ounce of energy into the final instant. The crowd is on its feet. A flurry of flashguns trigger, trying to capture the historic moment on digital film. There’s a brief pause as all eyes move up to the giant high-resolution display for the results. The numbers flash on the screen “Square Root of Two to the Fortieth!” The sportscaster’s voice breaks as he shouts with excitement. It’s official – a world record. The most progress ever in the history of progress itself!

Forty years ago today (April 19, 1965) Gordon Moore published his paper, ultimately predicting that integrated electronics would progress by a factor of two every two years (or by a factor of square-root of two each year, for those of us that like to annualize). Today, rather than adding our accolades to the many rightfully heaped on Mr. Moore for his astonishing insight, we’d like to celebrate the almost incomprehensible accomplishment of our profession. During the past four decades, those of us who develop digital electronics have made more progress than possibly any group on any metric in human history.

Skeptical? Let’s review a few. The wheel has improved our ability to get around by (generously) no more than a factor of one thousand. Fire has probably reduced the mortality rate by no more than an order of magnitude, and no more than tripled the habitable area of the planet. Antibiotics haven’t even doubled the human life expectancy. Take a look at our number again – 1,048,576. From roughly fifty transistors on a chip in 1965 to fifty million in 2005. Find anything else that’s increased by a factor of one million in forty years (and no fair dividing by zero! – the number of Britney Spears CDs, for example, doesn’t count.)

Is this truly progress, and if so what are the tangible benefits? Throughout time, two of mankind’s most passionate pursuits have been the collection and communication of information. Information exchange is what gave our type transcendence (good or bad) to take the reins as the dominant species on the planet. Conversely, lack of communication in all its forms has accounted for most of the fear, hatred, and violence in human history. By enabling free, accessible, and open global communications, our technology has made huge strides in furthering the prospects for world peace. While it’s true that electronics have also improved our ability to make war, we were already adept at killing ourselves as early as the 1940s.

In the category of protecting the planet, the advent of the internet has made it possible for a publication like this one to reach tens of thousands of readers in over 80 countries worldwide each week without ever killing a tree for paper, burning fossil fuels in a delivery truck, or firing up an airplane to cross the oceans. Our staff doesn’t have to clog the highways and damage the ozone layer twice each day commuting to and from work, and many of the people that benefit from the information we provide use it to improve that very same infrastructure with which it was delivered.

While much is made of the inevitable abuse of the free and open global forum afforded by the internet, the abuse it undermines, namely the concentration of the power of global communication in the hands of a few, is much more significant. By creating a global medium that allows almost any individual the same access as the largest, most powerful special interests, the potential for corruption and manipulation by centralized control of the media has been dramatically reduced. Additionally, by creating a mechanism whereby any two people on the planet can easily debate, understand, and hopefully eventually embrace their individual and cultural diversity, we erode the very fabric of misunderstanding, suspicion, and fear that fuels our worst conflicts.

On a more individual note, the technology our profession has created helps us live longer, safer lives while being more efficiently entertained than ever before. It also provides educational power tools whose impact has only begun to be felt. When I was in school, I had to carefully prioritize what I researched, because gathering information usually involved a long and arduous visit to the library and considerable effort. As a result, I would seek answers to only the few questions I deemed most interesting or important. All the rest remained in my head unanswered. My kids, on the other hand, have had internet search engine access through most of their academic careers. Their behavior is different. When they have any question at all, no matter how insignificant, they can quickly tap a few keys, click a mouse and have a reasonable answer. Almost all of their questions, then, are quickly answered. The cumulative effect of this over the course of their education has had a dramatic effect. They are far more informed, worldly and wise than I was at their age. I attribute most of this to access to information technology rather than advances in our education system.

FPGAs were made possible by this progress. In the late 1980s and early 1990s, there was frequent discussion about what could be done with the “white space” on semiconductor devices. This white space represented the difference between the number of transistors we could fabricate on a chip, and the number we could productively use given the state of the art in design tool technology. Programmability became the “killer app” that used all the white space and more. For a broad class of applications, it made Moore’s Law worth pursuing for at least an additional decade.

While the list of benefits from our engineering accomplishments goes on and on, it is also interesting to look at the process that created those gains. Yes, we had physics and a couple of pivotal technological advances on our side, but I’d argue that the primary driving force behind the success of the past forty years is an unprecedented level of worldwide, multi-disciplinary collaboration and teamwork. I can think of no other project where ideas from so many sources have folded into a community knowledge base and acted as stepping-stones for further advancement. Despite the golden restraints of intellectual property protection, techniques and technology have crossed company and country lines where they have become the basis for important new derivative ideas. Advance has piled upon advance in fields as diverse as physics, chemistry, optics, process engineering, circuit design, mechanical engineering, mathematics, software, and operations research. The cumulative effect of such interdisciplinary intellectual-mechanical advantage is largely responsible for our six-order-of-magnitude accomplishment.

There is little doubt that Mr. Moore’s mathematics will eventually play out. The long-term future of any exponential ratio in the real world is limited by physics. However, the foundation it gives us for future progress is equally awe-inspiring. As of today, our ability to leverage this incredible accomplishment in hardware is primitive at best, owing to the relative immaturity of software technology. While Moore’s Law may slow to a crawl in hardware within the next decade or so, its legacy will certainly live on indefinitely as we explore the possibility of leveraging this bounty of hardware capability more effectively and efficiently with ever-improving algorithms and intelligence on the software and applications side.

Congratulations to us all!

Leave a Reply

featured blogs
Aug 17, 2018
Samtec’s growing portfolio of high-performance Silicon-to-Silicon'„¢ Applications Solutions answer the design challenges of routing 56 Gbps signals through a system. However, finding the ideal solution in a single-click probably is an obstacle. Samtec last updated the...
Aug 17, 2018
If you read my post Who Put the Silicon in Silicon Valley? then you know my conclusion: Let's go with Shockley. He invented the transistor, came here, hired a bunch of young PhDs, and sent them out (by accident, not design) to create the companies, that created the compa...
Aug 16, 2018
All of the little details were squared up when the check-plots came out for "final" review. Those same preliminary files were shared with the fab and assembly units and, of course, the vendors have c...
Aug 14, 2018
I worked at HP in Ft. Collins, Colorado back in the 1970s. It was a heady experience. We were designing and building early, pre-PC desktop computers and we owned the market back then. The division I worked for eventually migrated to 32-bit workstations, chased from the deskto...
Jul 30, 2018
As discussed in part 1 of this blog post, each instance of an Achronix Speedcore eFPGA in your ASIC or SoC design must be configured after the system powers up because Speedcore eFPGAs employ nonvolatile SRAM technology to store its configuration bits. The time required to pr...