Transcending Moore's Law

Oct 1, 2001
Red Herring

Intel co-founder Gordon Moore has chuckled at those who have predicted the imminent demise of Moore’s Law in decades past. In 1965, Moore observed a doubling of transistor density every year, a pattern that has held true to this day.

But the traditional semiconductor chip is finally approaching some fundamental physical limits. Moore recently admitted that Moore’s Law, as we know it, will run out of gas in 2017. Intel’s .045um process is expected to come on line in 2007 with a gate oxide that is only 3 atoms thick. It is hard to imagine many more doublings from there, even with further innovation in insulating materials.

Another factor is the escalating cost of a semiconductor fab plant, which is doubling every three years, a phenomenon dubbed Moore’s Second Law. Human ingenuity keeps shrinking the CMOS transistor, but with increasingly expensive manufacturing facilities – currently $3 billion per fab.

Any one technology, such as the CMOS transistor, follows an elongated S-shaped curve of upward progress over time. But a more generalized capability, such as computation, storage, or bandwidth, tends to follow a pure exponential – bridging across a variety of technologies and their cascade of S-curves.

If history is any guide, Moore’s Law will continue on and will jump to a different substrate than CMOS silicon. It has done so five times in the past. In his forthcoming book, Ray Kurzweil traces the historical exponential capability curves for a variety of technologies. The exponential curve of Moore’s Law extends smoothly back in time to 1890, long before the invention of the semiconductor. Through five paradigm shifts – such as electro-mechanical calculators and vacuum tube computers – the processing power that $1000 buys has doubled every two years. For the past 30 years, it has been doubling every year.

We have been investing in a variety of companies, such as FlexICs, Nantero, Cognigine, Coatue, Phosistor and Binoptics, that are working on the next paradigm shift to extend Moore’s Law beyond 2017. One near term extension to Moore’s Law focuses on the cost side of the equation. Imagine rolls of wallpaper embedded with inexpensive transistors. FlexICs deposits traditional transistors at room temperature on plastic, a much cheaper bulk process than growing and cutting crystalline silicon ingots.

Another strong contender for the post-silicon computation paradigm is molecular electronics, a nano-scale alternative to the CMOS transistor. Eventually, these molecular switches will revolutionize computation by scaling into the third dimension – overcoming the planar deposition limitations of CMOS. Initially, they will substitute for the transistor bottleneck on an otherwise standard silicon process with standard external I/O interfaces.

For example, Nantero is growing carbon nanotubes on silicon to create high-density nonvolatile memory chips. Carbon nanotubes are small (10 atoms wide), stronger than diamond, and perform the functions of wires and transistors with better speed, power, density and cost. Cheap nonvolatile memory enables important advances, such as "instant-on" PCs.
Other companies, such as Hewlett Packard and ZettaCore, are combining organic chemistry with a silicon substrate to create memory elements that self-assemble by chemical bonds that form along pre-patterned regions of exposed silicon or metal.

Unlike memory chips, which have a regular array of elements, processors and logic chips are limited by the rats’ nest of wires that span the chip on multiple layers. The bottleneck in logic chip design is not raw numbers of transistors, but a design approach that can utilize all of that capability in a timely fashion. For a solution, Cognigine has redesigned "systems on silicon" with a distributed computing bent; wiring bottlenecks are localized, and chip designers can be more productive by using a high-level programming language, instead of wiring diagrams and logic gates. Chip design benefits from the abstraction hierarchy of computer science.

Compared to the relentless march of Moore’s Law, the cognitive capability of humans is relatively fixed. We have relied on the compounding power of our tools to achieve exponential progress. To take advantage of accelerating hardware power, we must further develop layers of abstraction in software to manage the underlying complexity. For the next 1000-fold improvement in computing, the imperative will shift to the growth of distributed complex systems. Our inspiration will likely come from biology.