Blocking and array contraction across arbitrarily nested loops using affine partitioning

Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP

Volumn , Issue , 2001, Pages 103-112

  Lim, A W ^a   Liao, S W ^a   Lam, M S ^a  

^a STANFORD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; BENCHMARKING; DATA STORAGE EQUIPMENT; HIERARCHICAL SYSTEMS; MULTIPROCESSING PROGRAMS; PROGRAM COMPILERS;

ARBITRARILY NESTED LOOPS;

COMPUTER PROGRAM LISTINGS;

EID: 0034823777     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/379539.379586     Document Type: Conference Paper

References (24)

1. Synthesizing transformations for locality enhancement of imperfectly-nested loop nests
2. Tiling imperfectly-nested loop nests
3. Compiler transformations for high-performance computing
4. Compiler optimizations for improving data locality
5. Some efficient solutions to the affine scheduling problem, Part I, one dimensional time
6. Collective loop fusion for array contraction
7. Solution of the Euler equations by a multigrid method
8. Optimizing for parallelism and data locality
9. Maximizing loop parallelism and improving data locality via loop fusion and distribution
10. Data-centric multi-level blocking
11. The implementation and evaluation of fusion and array contraction in array languages
12. An seine partitioning algorithm to maximize parallelism and minimize communication
13. Maximizing parallelism and minimizing synchronization with affine transforms
14. Maximizing parallelism and minimizing synchronization with affine partitions
15. Iteration space slicing for locality
16. Optimization of array accesses by collective loop transformations
17. A data locality optimizing algorithm