News for hackers. Stuff that matters.
Re:US Patent #7,650,331: System & method for efficient large... by loup-vaillant on Tuesday January 19, 2010 @04:30PM (#1063261)
The Idea behind Map Reduce itself is extremely general (and not brand new):

    map  :: (a -> b) -> [a] -> b
    fold :: (a -> a -> a) -> a -> [a] -> a  -- the first argument must be associative if you want a parallel fold.
    
    mapReduce :: (a -> b) -> (b -> b -> b) -> b -> [a] -> b
    mapReduce f g e l = fold g e (map f l)  -- conceptually. You have to write an actually parallel version.
If the patent isn't more specific than this (by being limited to MapReduce, for instance), I bet it can be overruled by prior art. Now, I admit I don't have the courage to check.
Re:US Patent #7,650,331: System & method for efficient large... by neilc on Tuesday January 19, 2010 @04:40PM (#1063300)
A cursory examination of the patent would tell you that it says very little about map and reduce functions as such -- the emphasis is on the system for executing such functions in parallel for large-scale data transformation.
Re:US Patent #7,650,331: System & method for efficient large... by ramchip on Tuesday January 19, 2010 @11:02PM (#1064017)
the emphasis is on the system for executing such functions in parallel for large-scale data transformation

As someone mentioned: the Glasgow Haskell Compiler and its RTS is such a system...