Low-Power CMOS VLSI Design
The invention of the transistor brought about a giant technological leap in microelectronics. Unlike the vacuum tube, which required several hundred volts of anode voltage and few watts of power, the transistor required only milli-watts of power. With the advent of the transistor and, decades later, the arrival of the integrated circuit, power dissipation became a lesser concern. Greater emphasis was placed on performance and miniaturization, yet power dissipation was not entirely ignored. In fact, battery-powered applications drove low-power electronics—such as pocket calculators, hearing aids, implantable pacemakers, portable military equipment used by individual soldiers and, most importantly, wristwatches. For all such applications, the longer the battery could last, the better. Consequently, ever since then, power requirement reduction has become one of the most critical factors in the evolution of microelectronics technology, even for desktop applications. To continue to improve the performance of the circuits and to integrate more functions into each chip, feature size had to shrink more and more. As a result, the magnitude of power per unit area has kept growing and the accompanying problem of heat removal and cooling has kept getting worse, as exemplified by general-purpose microprocessors.
Please disable any pop-up blockers for proper viewing of this Whitepaper.