June 7, 2009

Daniel Abadi on Kickfire and related subjects

Daniel Abadi has a new blog, whose first post centers around Kickfire.  The money quote is (emphasis mine):

In order for me to get excited about Kickfire, I have to ignore Mike Stonebraker’s voice in my head telling me that DBMS hardware companies have been launched many times in the past are ALWAYS fail (the main reasoning is that Moore’s law allows for commodity hardware to catch up in performance, eventually making the proprietary hardware overpriced and irrelevant). But given that Moore’s law is transforming into increased parallelism rather than increased raw speed, maybe hardware DBMS companies can succeed now where they have failed in the past

Good point.

More generally, Abadi speculates about the market for MySQL-compatible data warehousing.  My responses include:

Anyhow, as previously noted, I’m a big Daniel Abadi fan. I look forward to seeing what else he posts in his blog, and am optimistic he’ll live up to or exceed its stated goals.

Comments

2 Responses to “Daniel Abadi on Kickfire and related subjects”

  1. Daniel Weinreb on June 8th, 2009 5:52 am

    Having been a founder of Symbolics, I have already seen commodity hardware run ahead of special-purpose hardware, for the reasons you mention, plus the reason that new software techniques sometimes evolve that make the special hardware unnecessary.

    That said, there is still room for some kind of special processing hardware today. The Azul Java machine is an interesting example. The use of GPGPU’s is very promising because they’re made in such quantity, and their speed and quality and price are all being driven by the ever-growing digital game industry.

    However, a GPGPU is not promising for database systems, at least not in any very obvious way. It’s good when you have a relatively small amount of data that needs a relatively large amount of computation. Database systems, on the other hand, spend a lot of their effort on moving data around. So at this point I don’t particularly expect GPGPU technology to apply to database systems in any conventional way (although I could imaging special-purpose DBMS’s, that embed a lot of numerics inside the DB, perhaps).

    In any case, I think extrapolating forward from the failure of, say, the old Britton-Lee database machine is not a good idea. The balances between components of hardware change rapidly, and as they do, the tradeoffs between what to do in hardware and what to do in software can change just as radically as the tradeoffs between what to do locally (on a client) and what to do remotely (on a server).

    It’s a new world out there, since then, and it’s too early to judge simply the concept of “special hardware” per se. It depends on what special hardware, how you’re using it, and so on.

    Of course I wish InfoBright the best of success.

  2. Curt Monash on June 8th, 2009 6:20 am

    Dan,

    Actually, Kickfire are the guys with the cool “non-Von-Neumann” super-parallel chip. :)

    Best,

    CAM

Leave a Reply




Feed: DBMS (database management system), DW (data warehousing), BI (business intelligence), and analytics technology Subscribe to the Monash Research feed via RSS or email:

Login

Search our blogs and white papers

Monash Research blogs

User consulting

Building a short list? Refining your strategic plan? We can help.

Vendor advisory

We tell vendors what's happening -- and, more important, what they should do about it.

Monash Research highlights

Learn about white papers, webcasts, and blog highlights, by RSS or email.