Haskell on a shared-memory multiprocessor Export

@inproceedings{citeulike:342280, 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.}, address = {New York, NY, USA}, author = {Harris, Tim and Marlow, Simon and Peyton-Jones, Simon}, booktitle = {Haskell '05: Proceedings of the 2005 ACM SIGPLAN workshop on Haskell}, citeulike-article-id = {342280}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1088348.1088354}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1088348.1088354}, doi = {10.1145/1088348.1088354}, isbn = {159593071X}, keywords = {haskell, parallel\_computation}, pages = {49--61}, posted-at = {2008-11-11 02:00:45}, priority = {2}, publisher = {ACM Press}, title = {Haskell on a shared-memory multiprocessor}, url = {http://dx.doi.org/10.1145/1088348.1088354}, year = {2005} }

TY - CONF ID - citeulike:342280 L3 - citeulike-article-id:342280 N2 - 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. SN - 159593071X AD - New York, NY, USA EP - 61 TI - Haskell on a shared-memory multiprocessor PB - ACM Press T2 - Haskell '05: Proceedings of the 2005 ACM SIGPLAN workshop on Haskell SP - 49 KW - haskell KW - parallel_computation AU - Harris, Tim AU - Marlow, Simon AU - Peyton-Jones, Simon PY - 2005/// UR - http://dx.doi.org/10.1145/1088348.1088354 ER -