“How Fractal Trees Work” at MIT today

Posted on:



Share Button

I’ll be talking about How Fractal Trees Work  today at MIT in the Computational Research In Boston and Beyond (CRIBB) seminar (http://www-math.mit.edu/crib/2011/nov4.html). The talk is at 12:30 in the Stata Center room 32-141.  Pizza available before.

This talk will be academically-oriented (not much marketing).  The abstract is as follows:

Most storage systems employ B-trees to achieve a good tradeoff between the ability to update data quickly and to search it quickly.  It turns out that B-trees are far from the optimimum in this tradeoff space. I’ll talk about Fractal Tree indexes, which were developed in a collaboration between MIT, Stony Brook, and Rutgers.  I’ll talk about how they work, and what their performance bounds are.  My startup, Tokutek, is commercializing fractal tree indexes as part of a MySQL storage engine.

The slides are here.

Share Button


, , ,

Tokutek, TokuView

  • Was this talk recorded? A audio/video would have been really helpful for everyone who couldn’t attend the talk.

  • We unfortunately did not get video in this forum. However, we do have other talks Tokutek recorded this year which cover how Fractal Tree Indexes work (see http://vimeo.com/26471692). In addition, if you are local to the MA area, we will be speaking at the next MySQL Meetup in January about Fractal Trees (details here http://t.co/l8UE8LxN).

  • Hi Bradley,
    Thanks for replying. I have already watched 2 talks(one by you and other by Zardosht) which give a good overview about the concepts behind fractal trees. I really enjoyed them :).
    I believe that visual media is the best way to disseminate knowledge to wider audience. Looking foward to see more deep dive session in the future.

    Thank you.

Leave a Reply