Cramming More Components onto Integrated Circuits (1965) [pdf]

What a visionary article and a delightful read.<p>To give another context to look at this in retrospective, here&#x27;s [0] a die shot from a 2n3906 transistor made in 1965 (still available today). It&#x27;s roughly 60µm * 60µm in size. By comparison a high end chip made in 2022 has 80 billion transistors in an area of 814mm^2 [1].<p>That is three hundred and fifty thousand transistors (350,000!) in the same area 58 years later.<p>[0] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;2N3906#&#x2F;media&#x2F;File:2N3906_top_metal.jpg" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;2N3906#&#x2F;media&#x2F;File:2N3906_top_...</a> [1] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Hopper_(microarchitecture)" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Hopper_(microarchitecture)</a>

Wow, there&#x27;s a surprising number of predictions he nailed here. One of the most impressive is the suggestion that &quot;newly devised automation procedures could translate from logic diagram to technological realization without any special engineering&quot; -- hinting at the possibility of logic synthesis, which wouldn&#x27;t become viable until well into the 1980s (AFAIK?), but is now the standard methodology for complex digital ICs.

I always interpreted moores law as having 2 aspects, the scaling part (cramming more per mm2), and the economic aspect (for minimum component cost).<p>So when people say moores law is dead, it&#x27;s often confusing as clearly things are still scaling (3nm crams significantly more transistors in than 7nm), but the cost per transistor has flattened, or possibly inverted a bit.

Is cramming a term of art? It’s always seemed low brow to me? In any case, RIP, you were a giant.

reading the first three paragraphs after a week like this makes me crazy.