|
Title:
|
PARALLEL PORTING AND PERFORMANCE EVALUATION OF A COLUMN BASED OLAP SYSTEM |
|
Author(s):
|
R. Aversa , B. Di Martino , S. Venticinque , L. De Rosa |
|
ISBN:
|
978-972-8924-97-3 |
|
Editors:
|
Hans Weghorn and Pedro Isaías |
|
Year:
|
2009 |
|
Edition:
|
V I, 2 |
|
Keywords:
|
OLAP, OpenMP, MPI, parallelization, distributed memory, shared memory |
|
Type:
|
Full Paper |
|
First Page:
|
67 |
|
Last Page:
|
75 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Adoption of column-oriented in On Line Analytical Processing (OLAP) applications forces to reconsider several aspects
of data management and queries processing. Here we focus on the use of parallelism to restructure and to improve OLAP
system performances. Especially we report results of an experimental work done on a commercial database kernel
(SADAS) to improve performances of OLAP queries trough the use of HPC techniques and paradigms. We show how
the original sequential code can be extended with a minimum effort in order to support its execution on both shared and
distributed memory architectures. Experimental results demonstrate an improvement in term of speedup and efficiency on
different target execution platforms. |
|
|
|
|
|
|
