Also known as: Moore's Law

Moore’s law is the observation, made by Intel co-founder Gordon Moore in 1965, that the number of transistors on an integrated circuit roughly doubles about every two years.¹

Overview

It is not a law of physics but an empirical trend that held for decades as semiconductor makers steadily shrank feature sizes, packing ever more switches onto a chip at falling cost per transistor. That exponential scaling is what turned room-sized computers into pocket-sized ones and made each generation of CPUs and GPUs dramatically more capable. A related trend, Dennard scaling, once let clock speeds rise as transistors shrank — but that broke down in the mid-2000s, pushing designers toward multiple cores.

Where it fits

Moore’s law explains why computing got cheap and abundant enough that a hobbyist can run real DSP — like GopherTrunk decoding multiple trunked channels — on a board costing a few tens of dollars. The doubling has slowed as features approach atomic scale, so progress now leans more on parallelism, specialized accelerators, and packaging than on raw shrinking.

Sources

1. Moore’s law — Wikipedia, on the transistor-doubling trend and its slowdown. ↩

See also

• Transistor
• Integrated circuit
• Semiconductor
• Central processing unit (CPU)
• Clock speed
• Graphics processing unit (GPU)