@InProceedings{multiproc05,
   author = {Tim Harris and Simon Marlow and Simon {Peyton Jones}},
   title = {Haskell on a Shared-Memory Multiprocessor},
   booktitle = {Haskell '05: Proceedings of the 2005 ACM SIGPLAN workshop on Haskell},
   year = {2005},
   month = {September},
   abstract = {Multi-core processors are coming, and we need ways to program them.
The combination of purely-functional programming and explicit, monadic threads,
communicating using transactional memory, looks like a particularly promising
way to do so.  This paper describes a full-scale implementation of shared-memory
parallel Haskell, based on the Glasgow Haskell Compiler.  Our main technical 
contribution is a lock-free mechanism for evaluating shared thunks that eliminates
the major performance bottleneck in parallel evaluation of a lazy language.
Our results are preliminary but promising: we can demonstrate wall-clock speedups 
of a serious application (GHC itself), even with only two processors, compared
to the same application compiled for a uni-processor.
},
   url = {http://community.haskell.org/~simonmar/papers/multiproc.pdf},
   doi = {http://doi.acm.org/10.1145/1088348.1088354},
   isbn = {1-59593-071-X},
   pages = {49--61},
   location = {Tallinn, Estonia},
   publisher = {ACM Press}
}