Title | ||
---|---|---|
A Method for Runtime Recognition of Collective Communication on Distributed-Memory Multiprocessors |
Abstract | ||
---|---|---|
In this paper, we present a compiler optimization for recognizing patterns of collective communication at runtime in data-parallel languages that allow the dynamic data decomposition. It has a calculation time of the order O(m), and is appropriate for large numerical applications and massively parallel machines. The previous approach took O(n
O + ... + n
m–1) time, where m is the number of dimension of an array and n
i is the array size on the i-th dimension. The new method can be used for data redistribution and intrinsic procedures, as well as data pre-fetch in parallelized loops. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/BFb0024231 | ISHPC |
Keywords | Field | DocType |
runtime recognition,distributed-memory multiprocessors,collective communication,compiler optimization,distributed memory,dynamic data | Massively parallel,Computer science,Parallel computing,Collective communication,Distributed memory,Optimizing compiler,Dynamic data,Distributed computing | Conference |
ISBN | Citations | PageRank |
3-540-63766-4 | 0 | 0.34 |
References | Authors | |
10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Takeshi Ogasawara | 1 | 4 | 1.11 |
Hideaki Komatsu | 2 | 410 | 34.00 |