Kjellquist Blog

Within the last week or so there have been at least 2 announcements that I believe give renewed life to Moore’s law (not that it has been in any real danger). If you recall, Moore’s law ( as it has become known) was the prediction in 1965 by the co-founder of Intel, that “number of transistors on a chip doubles about every two years.” Over the years this prediction was extrapolated to refer to computing power as being analogous to the number of transistors (true for many years).

Below is a graph that illustrates Moore’s law

The recent announcements that will probably keep this curve going were from Intel and D-Wave Systems. On Feb 11, Intel announced an 80-core (note the dual core on the chart) chip that had achieved Teraflop — or trillions of calculations per second performance with a stunning 62 watts of power. To give you an idea of the magnitude of this achievement (and Moore’s Law), the first computer to ever achieve a teraflop performance was the ASCI Red Supercomputer built by Intel in 1996 for the Sandia National Laboratory. That computer took up more than 2000 square feet, was powered by nearly 10,000 Pentium® Pro processors, and consumed over 500 kilowatts of electricity.

Intel doesn’t have any plans to bring this chip to market. It’s a research effort. But, it does show the level of current research and gives a peek at things to come.

The second announcement, by D-Wave Systems involves quantum computing. Quantum computing has the promise of revolutionizing computing. In a classical (or conventional) computer, the amount of data is measured by bits; in a quantum computer, the data is measured by qubits. The basic principle of quantum computation is that the quantum properties of particles can be used to represent and structure data, and that quantum mechanisms can be devised and built to perform operations with these data.

To date, quantum computing has been approximately where computing and transistors were 1947.

On Feb 13, D-Wave Systems announced the first commercially viable quantum computer with field deployable units by the end of 2008. Again, it isn’t really important whether D-Wave makes it or even if their approach ultimately succeeds. Rather, it reinforces an optimistic view that computing power won’t see an end anytime soon!