hackertube.io

New computers don't speed up old code

Matthias random stuff · explainer · Watch on YouTube

Software performance & optimizationComputer architecture & CPUs

What it is

Matthias Wandel tests old and new code on a range of PCs, including a new mini PC, to measure how much faster modern hardware really is. He also shows optimization techniques such as branchless code, with benchmark programs on GitHub.

Why Hacker News recommends it

Used as evidence that CPU speed for branchy, dependent code has improved only modestly in 15-20 years, so software optimization matters.

  • 3 people recommended it
  • 3 different months
  • 1 strong recommendations
  • first 2025, last 2025

What HN commenters said

  1. “This great video [0] demonstrates how CPU performance has only increased 1.5-2x over the past 15(!) years when executing extremely branchy code.”

    CPU speedup only 1.5-2x on branchy code; CRC branchless demo.

    MontyCarloHall, 2025-09 · Strong recommendation · in “The Weird Concept of Branchless Programming”

  2. “Computers today aren't that much faster than the computers of 20 years ago, unless you specifically code for them”

    Modern computers are not much faster for old code.

    dijit, 2025-05 · Recommendation · in “The world could run on older hardware if software optimization was a priority”

  3. “New computers aren't as much faster as benchmarks would lead you to believe.”

    New CPUs gain little on branchy, dependent code.

    torginus, 2025-08 · Recommendation · in “Uncle Sam shouldn't own Intel stock”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: benchmarks, branchless programming, optimization, cpu, legacy code

Also recommended by the same people