Automatic implementation of affine iterative algorithms: Design flow and communication synthesis

Computer Physics Communications

Volumn 139, Issue 1, 2001, Pages 109-131

  Marongiu, Alessandro ^a   Palazzari, Paolo ^b  

^a SAPIENZA UNIVERSITY OF ROME   (Italy)

^b ENEA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER AIDED DESIGN; COMPUTER ARCHITECTURE; COMPUTER HARDWARE DESCRIPTION LANGUAGES; COMPUTER SOFTWARE; ITERATIVE METHODS; MATRIX ALGEBRA;

DATA-FLOW GRAPH; PARALLEL ARCHITECTURES;

PARALLEL PROCESSING SYSTEMS;

EID: 0035449532     PISSN: 00104655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0010-4655(01)00234-X     Document Type: Article

References (31)

1. APEmille
2. Stellar dynamics on 200 Tflops special purpose computers
3. Geometrical tools to map system of affine recurrence equations on regular arrays
4. A new memory saving technique to map System of Affine Recurrence Equations (SARE) onto distributed memory systems
5. Linear mapping of n-dimensional uniform recurrences onto k-dimensional systolic arrays
6. A toolbox for affine recurrence equations parallelization
7. OPERA: A toolbox for loop parallelization
8. Automatic mapping of System of N-dimensional Affine Recurrence Equations (SARE) onto distributed memory parallel systems
9. A systolic design methodology with application to full-search block-matching architectures
10. Solutions to the communication minimization problem for affine recurrence equations
11. Affine dependence classification for communications minimization
12. Communication optimization for affine reccurence equations using broadcast and locality
13. Synthesizing regular arrays from single affine recurrences via quadratic and branching parametric linear programming
14. High level software synthesis of affine iterative algorithms onto parallel architectures
15. Data flow analysis of scalar end array references
16. Optimization of automatically generated parallel programs
17. A unifying lattice-based approach for the partitioning of systolic arrays via LPGS and LSGP
18. A library for doing polyhedral operations
19. Parameterized polyhedra and their vertices
20. A comparison of clustering heuristics for scheduling directed acyclic graphs on multiprocessors
21. On the granularity and clustering of directed acyclic task graphs
22. Real time pipelined system design through simulated annealing
23. The parallel execution of DO loops
24. Optimal systolic implementation of N-dimensional recurrences
25. Converting affine recurrence equations to quasi-uniform recurrence equations