Results 1 
2 of
2
Accurate Data Redistribution Cost Estimation in Software Distributed Shared Memory Systems
 In Principles and Practice of Parallel Programming
, 2001
"... Distributing data is one of the key problems in implementing ecient distributedmemory parallel programs. The problem becomes more dicult in programs where data redistribution between computational phases is considered. The global data distribution problem is to nd the optimal distribution in multi ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Distributing data is one of the key problems in implementing ecient distributedmemory parallel programs. The problem becomes more dicult in programs where data redistribution between computational phases is considered. The global data distribution problem is to nd the optimal distribution in multiphase parallel programs. Solving this problem requires accurate knowledge of the cost of redistributing data. We are investigating this problem in the context of a software distributed shared memory (SDSM) system, in which obtaining accurate redistribution cost estimates is dicult. This is because SDSM communication is implicit: It depends on access patterns, page locations, and the SDSM consistency protocol. We have developed integrated compile and runtime analysis for SDSM systems to determine accurate redistribution cost estimates with low overhead. Our resulting system, SUIFAdapt, can eciently and accurately estimate execution time, including redistribution, to within 10% of the ac...
ABSTRACT Accurate Data Redistribution Cost Estimation in Software Distributed Shared Memory Systems ∗
"... Distributing data is one of the key problems in implementing efficient distributedmemory parallel programs. The problem becomes more difficult in programs where data redistribution between computational phases is considered. The global data distribution problem is to find the optimal distribution i ..."
Abstract
 Add to MetaCart
(Show Context)
Distributing data is one of the key problems in implementing efficient distributedmemory parallel programs. The problem becomes more difficult in programs where data redistribution between computational phases is considered. The global data distribution problem is to find the optimal distribution in multiphase parallel programs. Solving this problem requires accurate knowledge of data redistribution cost. We are investigating this problem in the context of a software distributed shared memory (SDSM) system, in which obtaining accurate redistribution cost estimates is difficult. This is because SDSM communication is implicit: It depends on access patterns, page locations, and the SDSM consistency protocol. We have developed integrated compile and runtime analysis for SDSM systems to determine accurate redistribution cost estimates with low overhead. Our resulting system, SUIFAdapt, can efficiently and accurately estimate execution time, including redistribution, to within 5 % of the actual time in all of our test cases and is often much closer. These precise costs enable SUIFAdapt to find efficient global data distributions in multiplephase programs. 1.