Column-stores vs. row-stores: how different are they really?

By Daniel J. Abadi, Samuel Madden, N. Hachem. SIGMOD Conference, 2008

615 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/746cf0e5e420670f181acf90b365af95f639b3e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Beng Chin Ooi
2. Gang Chen
3. Meihui Zhang
4. Daniel J. Abadi
5. Samuel Madden
6. Kian-Lee Tan
7. Hao Zhang
8. Rubao Lee

In Information Systems

1. Xiaodong Zhang
2. Samuel Madden
3. Kian-Lee Tan
4. Adam Marcus
5. Beng Chin Ooi
6. Zhiwei Xu
7. Rubao Lee
8. Meihui Zhang

In Signal Processing

1. Samuel Madden
2. Kian-Lee Tan
3. Adam Marcus
4. Beng Chin Ooi
5. M. Tamer Özsu
6. Lukasz Golab
7. M. Franklin
8. W. Hong

Citations in the corpus

• The Snowflake Elastic Data Warehouse (2016, background): “Columnar storage and execution is generally considered superior to row-wise storage and execution for analytic workloads, due to more effective use of CPU caches and SIMD instructions, and more opportunities for (light-weight) compression [1, 33].”
• In-Memory Big Data Management and Processing: A Survey (2015, methodology): “Columnar layout of relational table facilitates scan-like queries/analytics as it can achieve good cache locality [41], [88], and can achieve better data compression [89], but is not optimal for OLTP queries that need to operate on the row level [74], [90].”
• SW-Store: a vertically partitioned DBMS for Semantic Web data management (2009, background): “This decision is generally based on the expected cardinality of the join [5,6].”
• MMTF—An efficient file format for the transmission, visualization, and analysis of macromolecular structures (2017, background): “This approach represents a columnar encoding [12] of data, which facilitates data encoding and enhances data compressibility.”
• RCFile: A fast and space-efficient data placement structure in MapReduce-based warehouse systems (2011, background): “In conventional database systems, three data placement structures have been widely studied, which are: 1) horizontal row-store structure ([8]), 2) vertical column-store structure ([9][10][11][12]), and 3) hybrid PAX store structure ([13][14]).”
• Processing Analytical Queries over Encrypted Data (2013, neutral): “(§8.7)”