Hacker News new | past | comments | ask | show | jobs | submit login

> "solving" the fp32 incorrect-rounding problem by using fp64 is naive (not guaranteed to always work, although it will with high probability)

The key thing is there are only 2*32 float32s so you can check all of them. It sounds to me like the author did this, and realized they needed some tweaks for correct answers with log.






Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: