Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by kccqzy

16 hours ago

It’s ultimately based on a lot of hand-written heuristics. Google has some non-LLM based machine learning technique to guide optimization heuristics in LLVM; that would be closer to what you are looking for.

1 comment

kccqzy

Reply

dnautics  11 hours ago

I think your CPU might even have a small neural net in the branch predictor

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities