Moore’s Law on chip capacity questioned

Researchers at Rockefeller University have shed new light on the popular Moore’s Law, possibly the most famous technological prediction in the world, which states that “approximately every 2 years the number of transistors in a microprocessor doubles.”
The study, published by PLOS One , reveals a more nuanced historical pattern of the growth in density of transistors on silicon chips that make computers and other technological gadgets faster and more powerful.
In fact, since 1959, there have been six waves of such improvements, each lasting about six years, during which the density of transistors per chip increased by at least 10-fold, according to the research, titled ‘ Moore’s Law Revisited through Intel Chip Density ‘. The article builds on previous research on DRAM chips as model organisms for the study of technological evolution.
The new work clarifies the arcs of the wave pattern by taking a novel perspective on chip density that takes into account the changing size of the chips used in Intel processors since 1959.
The study has found that every six-year growth spurt is followed by one to three years of negligible growth. So say its authors, David Burg and Jesse Ausubel, from the Program for the Human Environment at Rockefeller University in New York. In fact, they claim that the next spurt in the growth of transistor miniaturization and computing power is overdue.
An acceleration that, they assure, will be driven by the demand for artificial intelligence technologies that require a lot of data, such as facial recognition; by mobile networks and equipment with 5G; for autonomous cars; and, finally, by similar high-tech innovations that require more processing speed and computing power.
Cerebras , a ‘startup’, has promoted the largest chip ever built, the Wafer-Scale Engine , 56 times larger than the largest graphics processing unit, which has dominated computing platforms for artificial intelligence and machine learning.
In any case, the end of the silicon chip era is in sight, as there would only be one or two pulses of silicon left before further advances become exponentially more difficult due to physical realities and economic constraints, they say. the researchers.