Improving hash join performance through prefetching
Hash join algorithms suffer from extensive CPU cache stalls. We show that the standard hash join algorithm/or disk-oriented databases (i.e. GRACE) spends over 73% of its user time stalled on CPU cache misses, and explores the use of prefetching to improve its cache performance. Applying prefetching...
Saved in:
Published in | Proceedings. 20th International Conference on Data Engineering pp. 116 - 127 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
Los Alamitos CA
IEEE
2004
IEEE Computer Society |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Hash join algorithms suffer from extensive CPU cache stalls. We show that the standard hash join algorithm/or disk-oriented databases (i.e. GRACE) spends over 73% of its user time stalled on CPU cache misses, and explores the use of prefetching to improve its cache performance. Applying prefetching to hash joins is complicated by the data dependencies, multiple code paths, and inherent randomness of hashing. We present two techniques, group prefetching and software-pipelined prefetching, that overcome these complications. These schemes achieve 2.0-2.9X speedups for the join phase and 1.4-2.6X speedups for the partition phase over GRACE and simple prefetching approaches. Compared with previous cache-aware approaches (i.e. cache partitioning), the schemes are at least 50% faster on large relations and do not require exclusive use of the CPU cache to be effective. |
---|---|
ISBN: | 9780769520650 0769520650 |
ISSN: | 1063-6382 2375-026X |
DOI: | 10.1109/ICDE.2004.1319989 |