Implementation of speculative parallelism in functional languages
نویسندگان
چکیده
منابع مشابه
Implementation of Speculative Parallelism in Functional Languages
A compile-time analysis technique is developed to derive the probability with which a user-defined function or a supercombinator requires each one of its arguments. This provides a basis for identifying useful speculative parallelism in a program. The performance of speculative evaluation is compared with that of lazy evaluation, and the necessary conditions under which speculative evaluation p...
متن کاملExploring Speculative Parallelism in Spec2006 Exploring Speculative Parallelism in Spec2006 Exploring Speculative Parallelism in Spec2006
Computer industry has adopted multi-threaded and multi-core architectures as the clock rate increase stalled in early 2000’s. It was hoped that the continuous improvement of single-program performance could be achieved through these architectures. However, traditional parallelizing compilers often fail to effectively parallelize general-purpose applications which typically have complex control ...
متن کاملSpeculative Parallelism in Cilk++
Backtracking search algorithms are useful in many domains, from SAT solvers to artificial intelligences for playing games such as chess. Searching disjoint branches can, inherently be done in parallel though it can considerably increase the amount of work that the algorithm does. Such parallelism is speculative, once a solution is found additional work is irrelevant, but the individual branches...
متن کاملSpeculative Parallelism Improves Search
The extreme e ciency of sequential search and the natural tendency of tree prun ing systems to produce wide variations in workload partly explains why it is proving di cult to achieve more than e ciency for massively parallel implementations of the algorithm Here we introduce typical enhanced sequential algorithms and address the major issues of parallel game tree searching under conditions of ...
متن کاملParallel Implementation of Functional Languages
Lazy evaluation is optimal (up to overhead). Abstract. Great hopes in the exploitation of the (implicit) parallelism inherent in functional programs have driven a number of projects. General frustration resulted wherever implementations on distributed memory machines were attempted. The grain size of potentially parallel tasks is too small to amortize the enormous costs of the necessary communi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Parallel and Distributed Systems
سال: 1994
ISSN: 1045-9219
DOI: 10.1109/71.329669