Advanced Array Optimizations for High Performance Functional Languages
AuthorCann, D. C.
SourceIEEE Transactions on Parallel and Distributed Systems
Google Scholar check
MetadataShow full item record
In this paper, we discuss and evaluate three opti- mizations for reducing memory management overhead and data copying costs in SISAL 1.2 programs that build arrays. The first, called framework preconstruction, eliminates superfluous allocate-deallocate sequences in cyclic computations. The second, called aggregate storage subsumption, reduces the management overhead for compound array components. The third, called predictive storage preallocation, eliminates superfluous data copying in filtered array constructions and simplifies their parallelization. We have added all three optimizations to the Optimizing SISAL Compiler with rewarding improvements in SISAL program performance on vector-parallel machines such as those built by Cray Computer Corporation, Convex, and Cray Research. © 1995 IEEE
Showing items related by title, author, creator and subject.
Brief Announcement: Optimally work-competitive scheduling for cooperative computing with merging groups Georgiou, Chryssis; Russell, A.; Shvartsman, A. A. (2002)The development of algorithms with guaranteed work efficiency for any pattern of fragmentations and merges of the underlying network is addressed. Current results are discussed for the abstract setting where asynchronous ...
Samaras, George S.; Britton, K.; Citron, A.; Mohan, C. (1995)An atomic commit protocol can ensure that all participants in a distributed transaction reach consistent states, whether or not system or network failures occur. The atomic commit protocol used in industry and academia is ...
Paspallis, Nearchos; Papadopoulos, George Angelos (2008)Because of the high potential of mobile and pervasive computing systems, there is an ongoing trend in developing applications exhibiting context awareness and adaptive behavior. While context awareness guarantees that the ...