Analyzing vectorized hash tables across cpu architectures

M Böther, L Benson, A Klimovic… - Proceedings of the …, 2023 - research-collection.ethz.ch
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 …

Can Learned Models Replace Hash Functions?

I Sabek, K Vaidya, D Horn, A Kipf… - Proceedings of the …, 2022 - par.nsf.gov
Hashing is a fundamental operation in database management, playing a key role in the
implementation of numerous core database data structures and algorithms. Traditional hash …

ADAMANT: A Query Executor with Plug-In Interfaces for Easy Co-processor Integration

B Gurumurthy, D Broneske, GC Durand… - 2023 IEEE 39th …, 2023 - ieeexplore.ieee.org
Today's processor landscape is increasingly heterogeneous with the availability of co-
processors. This landscape impacts query engines, as they need to be reworked to keep …

An investigation of atomic synchronization for sort-based group-by aggregation on gpus

B Gurumurthy, D Broneske, M Schäler… - 2021 IEEE 37th …, 2021 - ieeexplore.ieee.org
Using heterogeneous processing devices, like GPUs, to accelerate relational database
operations is a well-known strategy. In this context, the group byoperation is highly …

Analysis of GPU-Libraries for Rapid Prototy** Database Operations: A look into library support for database operations

HKH Subramanian, B Gurumurthy… - 2021 IEEE 37th …, 2021 - ieeexplore.ieee.org
Using GPUs for query processing is still an ongoing research in the database community
due to the increasing heterogeneity of GPUs and their capabilities (eg, their newest selling …

Out-of-the-box library support for DBMS operations on GPUs

HKH Subramanian, B Gurumurthy, GC Durand… - Distributed and Parallel …, 2023 - Springer
GPU accelerated query execution is still ongoing research in the database community, as
GPUs continue to be heterogeneous in their architectures varying their capabilities (eg, their …

Novel insights on atomic synchronization for sort-based group-by on GPUs

B Gurumurthy, D Broneske, M Schäler… - Distributed and Parallel …, 2023 - Springer
Using heterogeneous processing devices, like GPUs, to accelerate relational database
operations is a well-known strategy. In this context, the group by operation is highly …

[PDF][PDF] Accelerating mono and multi-column selection predicates in modern main-memory database systems.

D Broneske, G Saake, KU Sattler, S Manegold - 2019 - opendata.uni-halle.de
Ever-since, database system engineers are striving for peak performance of their database
operators. However, this goal is a major endeavor since database operators are influenced …

Architecting a pluggable query executor for emerging co-processors

B Gurumurthy - 2024 - repo.bibliothek.uni-halle.de
CPUs are reaching their scaling limitations while data keeps growing rapidly. De-velopers of
CPU-based applications are searching for an alternative processor to further improve their …

Instance-Optimized Data Structures for Membership Queries

KE Vaidya - 2023 - dspace.mit.edu
We are near the end of Moore's law and hardware growth has hit a stagnation. Modern data
processing systems need to continuously improve their performance to match the …