Triton join: Efficiently scaling to a large join state on gpus with fast interconnects
Database management systems are facing growing data volumes. Previous research
suggests that GPUs are well-equipped to quickly process joins and similar stateful …
suggests that GPUs are well-equipped to quickly process joins and similar stateful …
Design and analysis of a processing-in-dimm join algorithm: A case study with upmem dimms
Modern dual in-line memory modules (DIMMs) support processing-in-memory (PIM) by
implementing in-DIMM processors (IDPs) located near memory banks. PIM can greatly …
implementing in-DIMM processors (IDPs) located near memory banks. PIM can greatly …
Analyzing vectorized hash tables across cpu architectures
Data processing systems often leverage vector instructions to achieve higher performance.
When applying vector instructions, an often overlooked data structure is the hash table, even …
When applying vector instructions, an often overlooked data structure is the hash table, even …
A systematic review of deep learning applications in database query execution
B Milicevic, Z Babovic - Journal of Big Data, 2024 - Springer
Modern database management systems (DBMS), primarily designed as general-purpose
systems, face the challenging task of efficiently handling data from diverse sources for both …
systems, face the challenging task of efficiently handling data from diverse sources for both …
Building a compiled query engine in python
H Shahrokhi, A Shaikhha - Proceedings of the 32nd ACM SIGPLAN …, 2023 - dl.acm.org
The simplicity of Python and its rich set of libraries has made it the most popular language
for data science. Moreover, the interpreted nature of Python offers an easy debugging …
for data science. Moreover, the interpreted nature of Python offers an easy debugging …
A design space exploration and evaluation for main-memory hash joins in storage class memory
In this paper, we seek to perform a rigorous experimental study of main-memory hash joins
in storage class memory (SCM). In particular, we perform a design space exploration in real …
in storage class memory (SCM). In particular, we perform a design space exploration in real …
UPLIFT: parallelization strategies for feature transformations in machine learning workloads
Data science pipelines are typically exploratory. An integral task of such pipelines are
feature transformations, which transform raw data into numerical matrices or tensors for …
feature transformations, which transform raw data into numerical matrices or tensors for …
Fast detection of denial constraint violations
The detection of constraint-based errors is a critical task in many data cleaning solutions.
Previous works perform the task either using traditional data management systems or using …
Previous works perform the task either using traditional data management systems or using …
Building advanced SQL analytics from low-level plan operators
Analytical queries virtually always involve aggregation and statistics. SQL offers a wide
range of functionalities to summarize data such as associative aggregates, distinct …
range of functionalities to summarize data such as associative aggregates, distinct …
A practical approach to groupjoin and nested aggregates
Groupjoins, the combined execution of a join and a subsequent group by, are common in
analytical queries, and occur in about 1/8 of the queries in TPC-H and TPC-DS. While they …
analytical queries, and occur in about 1/8 of the queries in TPC-H and TPC-DS. While they …