Advanced optimization strategies in the Rice dHPF compiler

Concurrency and Computation: Practice and Experience

Volumn 14, Issue 8-9, 2002, Pages 741-767

  Mellor Crummey, J ^a   Adve, V ^b   Broom, B ^a   Chavarria Miranda D ^a   Fowler, R ^a   Jin, G ^a   Kennedy, K ^a   Yi, Q ^a  

^a Rice University   (United States)

^b University of Illinois at Urbana Champaign   (United States)

Author keywords

Automatic parallelization; Computation partitioning; High Performance Fortran; Multipartitioning; NAS benchmarks

Indexed keywords

BENCHMARKING; CODES (SYMBOLS); FORTRAN (PROGRAMMING LANGUAGE); OPTIMIZATION; PARALLEL PROCESSING SYSTEMS;

AUTOMATIC PARALLELIZATION;

PROGRAM COMPILERS;

EID: 0036640963     PISSN: 15320626     EISSN: None     Source Type: Journal    
DOI: 10.1002/cpe.647     Document Type: Article

References (26)

1. High performance Fortran language specification
2. Efficient implementation of a 3-dimensional ADI method on the iPSC/860
3. Using integer sets for data-parallel program analysis and optimization
4. High performance Fortran compilation techniques for parallelizing scientific codes
5. Towards compiler support for scalable parallelism
6. Data-parallel compiler support for multipartitioning
7. On efficient parallelization of line-sweep computations
8. Compiler support for out-of-core arrays on data parallel machines
9. Process decomposition through locality of reference
10. Implementing the beam wanning method on the hypercube
11. Alternating direction methods on multiprocessors
12. Parallelization of a class of implicit finite-difference schemes in computational fluid dynamics
13. Taming the memory hogs: Using compiler inserted releases to manage physical memory intelligently
14. Performing out-of-core FFTs on parallel disk systems
15. Compiling high performance Fortran for distributed-memory systems
16. Communication optimization and code generation for distributed memory machines
17. Updating distributed variables in local computations
18. Simplifying control flow in compiler-generated parallel code
19. A common computational infrastructure for adaptive algorithms for PDE solutions
20. Telescoping languages: A strategy for automatic generation of scientific problem-solving systems from annotated libraries