Veteran: CMOS Scaling Is Tapped Out, Sparsity Is AI's Next 10x

Hardware veteran blelbach argues that CMOS scaling gains have bottomed out since 2015, and that genuinely sparse hardware—rather than today's dense linear-algebra machines—could unlock the next 10x in AI compute.

2026-09-17 ~ 2026-09-17 · 4 related posts

• Moore's Law in three eras: from free lunch (1970-2005) to software hell (2015-now) — blelbach · 2026-09-17
• Chip scaling's three eras: CMOS shrinks gave only efficiency after 2015, says blelbach — blelbach · 2026-09-17
• Hardware veteran: low-precision gains nearly exhausted, true sparsity is AI's next 10x — blelbach · 2026-09-17
• Sparse silicon could be the next 10x for AI compute, argues hardware veteran — blelbach · 2026-09-17