The Memory Performance of DSS Commercial Workloads in Shared-Memory Multiprocessors
| Citations: | 54 - 3 self |
BibTeX
@MISC{Trancoso_thememory,
author = {Pedro Trancoso and Josep-l. Larriba-Pey and Zheng Zhang and Josep Torrellas},
title = {The Memory Performance of DSS Commercial Workloads in Shared-Memory Multiprocessors},
year = {}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Although cache-coherent shared-memory multiprocessors are sometimes used to run commercial workloads, little work has been done to characterize how well they support such applications. In particular, we do not have many insights on the demands of commercial workloads on the memory subsystem of such machines. In this paper, we analyze the memory access patterns of several queries that are representative of Decision Support Systems (DSS) databases. Our analysis shows that queries differ largely depending on how they access the database data, namely via indices or by sequentially scanning the records. The former queries, which we call Index-Queries, suffer most of their misses on the index data structure and on lock-related metadata structures that we identify. The latter queries, which we call Sequential-Queries, suffer most of their misses on the database records as they are scanned. An analysis of the data locality of the queries shows that, both Index-Queries and Sequential-...
