Download:
|
by Preeti Ranjan Panda, Nikil D. Dutt, Alexandru Nicolau
http://www.ics.uci.edu/~ppanda/pubs/irreg.ps.gz
Add To MetaCart
Abstract:
Abstract. We address the problem of improving the data cache performance of numerical applications-- specifically, those with blocked (or tiled) loops. We present DAT, a data alignment technique utilizing arraypadding, to improve program performance through minimizing cache conflict misses. We describe algorithms for selecting tile sizes for maximizing data cache utilization, and computing pad sizes for eliminating self-interference conflicts in the chosen tile. We also present a generalization of the technique to handle applications with several tiled arrays. Our experimental results comparing our technique with previous published approaches on machines with different cache configurations show consistently good performance on several benchmark programs, for a variety of problem sizes. 1
Citations
|
676
|
A data locality optimizing algorithm
– Wolf, Lam
- 1991
|
|
487
|
The cache performance and optimizations of blocked algorithms
– LAM, ROTHBERG, et al.
- 1991
|
|
245
|
Computer Organization and Design: The Hardware/Software Interface
– Hennessy, Patterson
- 1998
|
|
240
|
Software prefetching
– Callahan, Kennedy, et al.
- 1991
|
|
173
|
More iteration space tiling
– Wolfe
- 1989
|
|
168
|
Tile size selection using cache organization and data layout
– Coleman, McKinley
- 1995
|
|
138
|
Cache profiling and the SPEC benchmarks: A case study
– LEBECK, WOOD
- 1994
|
|
94
|
Compiler blockability of numerical algorithms
– Carr, Kennedy
- 1992
|
|
27
|
MOB forms: a class of multilevel block algorithms for dense linear algebra operations
– Navarro, Juan, et al.
- 1994
|
|
22
|
Improving data locality for caches
– Esseghir
- 1993
|
|
7
|
Jalby "To Copy or Not to Copy : A Compile-Time Technique for Assessing When Data Copying Should be Used to Eliminate Cache Conflicts
– Temam, Granston, et al.
- 1993
|
|
6
|
C Language Algorithms for
– Embree, Kimble
- 1991
|
|
4
|
Numerical Recipes in C: The Art of Scientific Computing
– al
- 1992
|
