Time stamp algorithms for runtime parallelization of DOACROSS loops with dynamic dependences

IEEE Transactions on Parallel and Distributed Systems

Volumn 12, Issue 5, 2001, Pages 433-450

  Xu, Cheng Zhong ^a,b   Chaudhary, Vipin ^a,b  

^a IEEE   (United States)

^b Wayne State University   (United States)

Author keywords

Compiler; Doacross loop; Dynamic dependence; Inspector executor; Parallelizing compiler; Runtime support

Indexed keywords

FULLY CONCURRENT READS (FCR); PARTIALLY CONCURRENT READS (PCR); TIME STAMP ALGORITHMS;

ITERATIVE METHODS; PARALLEL ALGORITHMS; PROGRAM COMPILERS; SERVERS; STORAGE ALLOCATION (COMPUTER);

PARALLEL PROCESSING SYSTEMS;

EID: 0035335764     PISSN: 10459219     EISSN: None     Source Type: Journal    
DOI: 10.1109/71.926166     Document Type: Article

References (40)

1. Conversion of control dependence to data dependence
2. Compiler transformations for high-performance computing
3. Automatic program parallelization
4. Nonlinear and symbolic data dependence testing
5. Performance and programming experience on the tera MTA
6. An empirical study on doacross loops
7. On effective execution of nonuniform DOACROSS loops
8. Redundant synchronization elimination for DOACROSS loops
9. An efficient algorithm for the run-time parallelization of Doacross loops
10. DOACROSS: Beyond vectorization for multiiprocessors
11. On the automatic parallelization of the perfect benchmarks
12. Techniques for speculative runtime parallelization of loops
13. Cyclic staggered scheme: A loop allocation policy for DOACROSS loops
14. Parallelization of DOALL and DOACROSS loops: A survey
15. Parallelizing molecular dynamics programs for distributed memory machines: An application of the CHAOS runtime support library
16. Unique sets oriented partitioning of nested loops with nonuniform dependences
17. A chip-multiprocessor architecture with speculative multithreading
18. Improving the performance of runtime parallelization
19. A loop allocation policy for DOACROSS loops
20. Compiler algorithms for synchronization
21. Run-time parallelization: Its time has come
22. Run-time methods for parallelizing partially parallel loops
23. The LRPD test: Speculative runtime parallelization of loops with privatization and reduction parallelization
24. Run-time parallelization and scheduling of loops
25. An empirical study on array subscripts and data dependencies
26. The superthreaded processor architecture
27. Dependence uniformization: A loop parallelization technique
28. Effects of parallelism degree on runtime parallelization of loops
29. A memory-layout oriented runtime technique for locality optimization
30. Techniques for reducing the overhead of runtime parallelization
31. A scheme to enforce data dependence on large multi-processor systems