Talks about nanoseconds and ultra fast code ... doesn't lose a word about cache ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		leon_ on March 17, 2012 \| parent \| context \| favorite \| on: Why we didn't use a bloom filter Talks about nanoseconds and ultra fast code ... doesn't lose a word about cache locality?

brazzy on March 17, 2012 [–]

You may want to reread the article. One of his main points is how his custom algorithm accesses the dataset sequentially and thereby massively outperforms bloom filters which need random access.

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