• Home
  • Search
  • Data page layouts for relational databases on deep memory hierarchies
  • Cite Icon135
  • https://doi.org/10.1007/s00778-002-0074-9Copy DOI Icon

Data page layouts for relational databases on deep memory hierarchies

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Relational database systems have traditionally optimized for I/O performance and organized records sequentially on disk pages using the N-ary Storage Model (NSM) (a.k.a., slotted pages). Recent research, however, indicates that cache utilization and performance is becoming increasingly important on modern platforms. In this paper, we first demonstrate that in-page data placement is the key to high cache performance and that NSM exhibits low cache utilization on modern platforms. Next, we propose a new data organization model called PAX (Partition Attributes Across), that significantly improves cache performance by grouping together all values of each attribute within each page. Because PAX only affects layout inside the pages, it incurs no storage penalty and does not affect I/O behavior. According to our experimental results (which were obtained without using any indices on the participating relations), when compared to NSM: (a) PAX exhibits superior cache and memory bandwidth utilization, saving at least 75% of NSM's stall time due to data cache accesses; (b) range selection queries and updates on memory-resident relations execute 1725% faster; and (c) TPC-H queries involving I/O execute 1148% faster. Finally, we show that PAX performs well across different memory system designs.

Similar Papers
  • Book Chapter
  • Citations1

Optimizing Both Cache and Disk Performance of R-Trees

  • Jan 01, 2003
  • Myungsun Park +1
  • Research Article

Prefetch R-tree: 디스크와 CPU 캐시에 최적화된 다차원 색인 구조

  • Aug 01, 2006
  • The KIPS Transactions:PartD
  • Myung-Sun Park
  • PDF
  • Preprint Article

Performance analysis of coalesce private or spill shared (CPOSS) replacement strategy overLRU to handle directory entry evictions from the slice last level cache (LLC) using a scalable coherent sparse directory in Multicore processor

  • May 06, 2024
  • Research Square
  • Narottam Sahu +3
  • Conference Article
  • Citations2

Cache performance of chronological garbage collection

  • May 24, 1998
  • Yuping Ding +1
  • Conference Article
  • Citations6

Improving cache performance of network intensive workloads

  • Jan 01, 2001
  • U Vallamsetty +3
  • Research Article
  • Citations1

Random data-aware flash translation layer for NAND flash-based smart devices

  • Jul 03, 2013
  • The Journal of Supercomputing
  • Se Jin Kwon +3
  • Conference Article
  • Citations39

ZExpander

  • Apr 18, 2016
  • Xingbo Wu +5
  • Research Article
  • Citations9

Software-based branch predication for AMD GPUs

  • Sep 14, 2010
  • ACM SIGARCH Computer Architecture News
  • Ryan Taylor +1
  • Book Chapter
  • Citations20

Exploiting Web Log Mining for Web Cache Enhancement

  • Jan 01, 2002
  • Alexandros Nanopoulos +2
  • Research Article
  • Citations5

Cache performance of NV-STT-MRAM with scale effect and comparison with SRAM

  • Apr 13, 2021
  • International Journal of Electronics
  • Zitong Zhang +3
  • Research Article
  • Citations22

Achieving high instruction cache performance with an optimizing compiler

  • Apr 01, 1989
  • ACM SIGARCH Computer Architecture News
  • W W Hwu +1
  • Research Article
  • Citations1

STUDI PERBANDINGAN PERBEDAAN KONSEPTUAL ANTARA SISTEM BASIS DATA RELASIONAL DENGAN SISTEM PENYIMPANAN DATA BERTIPE NON-RELASIONAL (NO-SQL) : EKSPLORASI PADA SERVER DATA CASSANDRA

  • Aug 01, 2013
  • JURNAL TEKNOLOGI TECHNOSCIENTIA
  • Adi Nugroho +1
  • Conference Article
  • Citations13

Query workload-aware overlay construction using histograms

  • Oct 31, 2005
  • Georgia Koloniari +3
  • Conference Article
  • Citations22

A 5GHz 7nm L1 cache memory compiler for high-speed computing and mobile applications

  • Feb 01, 2018
  • Michael Clinton +5
  • Conference Article

Automatic synthesis of high performance mathematical programs

  • Jul 28, 2009
  • Markus Püschel
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.