Home Page
07.19.2005 (previous | next)
Parallel Programming--Revolution in Progress

Last week I was in Miami for one of TTI/Vanguard's tech conferences for senior executives (I was speaking on digital copyright). Herb Sutter from Microsoft gave a very interesting presentation on the problem of programming the next generation of hardware. Moore's Law is running into limitations--as measured in clock cycles, the speed of processing has plateaued and is not expected to ramp up for some time. So hardware is moving in the direction of parallel processing--fast. The next generation of hardware is all going to be parallel, from PC's to game machines.

The problem is on the software side. People don't know how to program in parallel--and they don't think well that way either. It's been a problem for at least 20 years. The series of papers on the "Santa Claus Problem", designed by A.J. Trono, is illustrative.

Santa Claus sleeps at the North pole until awakened by either all of the nine reindeer, or by a group of three out of ten elves. He performs one of two indivisible actions: If awakened by the group of reindeer, Santa harnesses them to a sleigh, delivers toys, and finally unharnesses the reindeer who then go on vacation. If awakened by a group of elves, Santa shows them into his office, consults with them on toy R&D, and finally shows them out so they can return to work constructing toys. A waiting group of reindeer must be served by Santa before a waiting group of elves. Since Santa's time is extremely valuable, marshalling the reindeer or elves into a group must not be done by Santa.

The problem of parallel/concurrent programming has gotten mostly solved for servers and networks, but the sticky bit is on the client side.

On the policy side, it will be interesting to see how this intersects with patent reform issues. Presumably aspects of the solution to this problem will be patentable, and will be patented. For one thing, it will be interesting to see if some of the solution represents a greater innovative leap than is usual for software, where innnovation is traditionally incremental.

posted by Solveig Singleton @ 10:22 AM | Patents, Software

Link to this Entry | Printer-Friendly | Email a Comment | Post a Comment(0)









 
IPcentral WebLog

Blog Main

IPcentral Blogosphere Archives

Search the Blog

Recent Posts
  - IP and Marginal Cost
- Academics and Copyright
- More on Jammie Thomas from DOJ
- More Studies of Downloading
- Facebook, MySpace, and Network Externalities
- Copyright and the University: An Academic Symposium
- Tyler Cowan on Chinese Movie Piracy
- More WHO Antics--Roger Bate Reports
- Patents, Meds, and the Developing World: Clips & Links
- Jermaine Dupri's Gripe with iTunes
Archives by Month
  - December 2007
- November 2007
- October 2007
- September 2007
  - (see all)
Archives by Subject
  - Academia
- Access: Commons, Fair Use, Orphan Works, Public Domain
- Accounting
- Analog Holes
- Antitrust
- Art
- Aspen
- Big Tent
- Biotech
- Books
- Comments from Readers
- Counterfeit
- Digital Americas
- Digital Europe
- Digital Europe 2006
- DMCA
- DRM & Watermarks, etc.
- Economics, Game Theory & Public Choice
- Enforcement & Remedies
- Free Culture Movement
- Games
- General
- Infrastructure
- International
- Internet: P2P, Search Engines...
- Legislation and Legislators
- Liberty and IP
- Markets: Business, Investment & Innovation
- Media: Video, Music...
- Patents
- Pharma
- Physical Property
- Prices, Terms, and Licensing
- Privacy and Security
- Radio
- Software
- Spectrum & Wireless
- Standards
- Supreme Court
- Tax-Funded IP
- Telecom
- Theft of Service
- Universities
Links
 

Site Feed

  - Atom
- RSS 1.0
- RSS 2.0
We welcome comments by email - look for a link to the author's email address in the byline of each post. Please let us know if we may publish your remarks.


 
Home Page