More iteration space tiling
Michael Wolfe · Proceedings - Supercomputing · 1989
Subdividing the iteration space of a loop into blocks or tiles with a fixed maximum size has several advantages. Tiles become a natural candidate as the unit of work for parallel task scheduling. Synchronization between processors can be done between tiles, reducing synchronization frequency (at some loss of potential parallelism). The shape and size of a tile can be optimized to take advantage of memory locality for memory hierarchy utilization. Vectorization and register locality naturally fits into the optimization within a tile, while parallelization and cache locality fits into optimization between tiles.
Cited by 429 works. doi:10.1145/76263.76337 Open-access PDF
Authors
References
- Optimizing supercompilers for supercomputers
- Automatic translation of FORTRAN programs to vector form
- Parallelism exposure and exploitation in programs
- The parallel execution of DO loops
- Dependence Analysis for Supercomputing
- Program Improvement by Source-to-Source Transformation
- Supernode partitioning
- Automatic loop interchange
- On the Performance Enhancement of Paging Systems Through Program Analysis and Transformations
- Iteration Space Tiling for Memory Hierarchies