Michelle Mills Strout, Larry Carter, Jeanne Ferrante  Home/Search
Context
Related
| ucsd.edu/~mstrout/techreport.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: ucsd.edu/~mstrout/paper (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Gauss-Seidel is an iterative computation used for solving sets of simulataneous linear equations, Au = f . When these unknowns are associated with nodes in an irregular mesh, then the Gauss-Seidel computation structure is related to the mesh structure. We use this structure to subdivide the computation at runtime using a technique called sparse tiling. The rescheduled computation exhibits better data locality and therefore improved performance. This paper gives a complete proof that a... (Update)
Similar documents (at the sentence level):
31.8%: Tiling of Iterative Sparse Matrix Computations - Strout, Carter, Ferrante.. (Correct)
7.6%: Proof of Correctness for Sparse Tiling of Gauss-Seidel - Strout, Carter, Ferrante (2003) (Correct)
Active bibliography (related documents): More All
0.3: An Overview of Cache Optimization Techniques and Cache-Aware .. - Kowarschik, Weiß (2003) (Correct)
0.3: Using Sparse Tiling with Symmetric Multigrid - Strout, Carter, Ferrante (2002) (Correct)
0.3: A Compiler Method for the Parallel Execution of.. - Gutierrez, Plata, Zapata (2000) (Correct)
Similar documents based on text: More All
0.5: Cv - Strout (Correct)
0.3: Compile-time Composition of Run-time Data and Iteration.. - Strout, Carter, Ferrante (2003) (Correct)
0.2: An Asynchronous Space Decomposition Method - Tai, Tseng (1998) (Correct)
BibTeX entry: (Update)
@misc{ strout-proof,
author = "Michelle Mills Strout and Larry Carter and Jeanne Ferrante",
title = "Proof of Correctness for Sparse Tiling of Gauss-Seidel",
url = "citeseer.ist.psu.edu/462781.html" }
Citations (may not include all citations):474 A data locality optimizing algorithm (context) - Wolf, Lam - 1991
216 Strategies for cache and local memory management by global p.. (context) - Gannon, Jalby et al. - 1988 ACM DBLP
186 way partitioning scheme for irregular graphs (context) - Karypis, Kumar - 1998
178 Supernode partitioning (context) - Irigoin, Triolet - 1988 ACM DBLP
162 Improving data locality with loop transformations - McKinley, Carr et al. - 1996 ACM DBLP
111 More iteration space tiling (context) - Wolfe
84 Compiler blockability of numerical algorithms - Carr, Kennedy - 1992 ACM DBLP
57 Improving cache performance in dynamic applications through .. - Ding, Kennedy - 1999 ACM DBLP
48 New tiling techniques to improve cache temporal locality - Song, Li - 1999 ACM DBLP
32 Cache Optimization for Structured and Unstructured Grid Mult.. - Douglas, Hu et al. - 2000
30 Improving memory hierarchy performance for irregular applica.. (context) - Mellor-Crummey, Whalley et al. ACM DBLP
30 Some simplied NP-complete graph problems (context) - Garey, Johnson et al. - 1976
23 Optimizing the Performance of Sparse Matrix-Vector Multiply (context) - Im - 2000
20 Iteration space tiling for memory hierarchies (context) - Wolfe - 1987 ACM DBLP
15 Optimizing sparse matrix computations for register reuse in .. - Im, Yelick ACM DBLP
15 Architecture-cognizant divide and conquer algorithms - Gatlin, Carter - 1999 ACM
7 Rescheduling for locality in sparse matrix computations - Strout, Carter et al. ACM DBLP
3 Tiling optimizations for 3D scientic computations (context) - Rivera, Tseng
3 Ecient compiler and run-time support for parallel irregular .. (context) - Han, Tseng - 2000
3 Localizing non-ane array references (context) - Mitchell, Carter et al.
2 Cache-ecient multigrid algorithms (context) - Sellappa, Chatterjee
Documents on the same site (http://www-cse.ucsd.edu/~mstrout/paper.html): More
Schedule-Independent Storage Mapping for Loops - Strout, Carter, Ferrante, Simon (1998) (Correct)
Asynchronous Dynamic Load Balancing of Tiles - Nguyen, Strout, Carter, Ferrante (Correct)
Rescheduling for Locality in Sparse Matrix Computations - Strout, Carter, Ferrante (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC