Abstract
This paper studies the relationship between storage requirements and performance. Storage-related dependences inhibit optimizations for locality and parallelism. Techniques such as renaming and array expansion can eliminate all storage-related dependences, but do so at the expense of increased storage. This paper introduces the universal occupancy vector (UOV) for loops with a regular stencil of dependences. The UOV provides a schedule-independent storage reuse pattern that introduces no further dependences (other than those implied by true flow dependences). OV-mapped code requires less storage than full array expansion and only slightly more storage than schedule-dependent minimal storage. We show that determine if a vector is a UOV is NP-complete. However, an easily constructed but possibly non-minimal UOV can be used. We also present a branch and bound algorithm which finds the minimal UOV, while still maintaining a legal UOV at all times. Our experimental results show that the use of OV-mapped storage, coupled with tiling for locality, achieves better performance than tiling after array expansion, and accommodates larger problem sizes than untilable, storage-optimized code. Furthermore, storage mapping based on the UOV introduces negligible runtime overhead.
Original language | English (US) |
---|---|
Pages (from-to) | 24-33 |
Number of pages | 10 |
Journal | Operating Systems Review (ACM) |
Volume | 32 |
Issue number | 5 |
DOIs | |
State | Published - Dec 1998 |
Externally published | Yes |
ASJC Scopus subject areas
- Information Systems
- Hardware and Architecture
- Computer Networks and Communications