Empirical evaluation across multiple GPU-accelerated DBMSes

Chu, Hawon; Kim, Seounghyun; Lee, Jooyoung; Suh, Young-Joo

doi:10.1145/3399666.3399907

Cited by 8 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The nature of such distributed queries is task-based and massively parallel. Driven by the demand for faster data processing in corporate contexts, GPU-accelerated database query engines are quickly becoming a popular option due to the substantial speedups they realize over their CPU-based counterparts (Chu et al, 2020). We hypothesized that the incorporation of a recently developed GPU-based query engine based on NVIDIA RAPIDS would offer these performance improvements and enable interactive analysis of our data sets through Jupyter notebooks.…”

Section: Accelerated Distributed Database Queries On Massive Output Datasetsmentioning

confidence: 99%

High-throughput virtual laboratory for drug discovery using massive datasets

Gläser

Vermaas

Rogers

et al. 2021

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

Time-to-solution for structure-based screening of massive chemical databases for COVID-19 drug discovery has been decreased by an order of magnitude, and a virtual laboratory has been deployed at scale on up to 27,612 GPUs on the Summit supercomputer, allowing an average molecular docking of 19,028 compounds per second. Over one billion compounds were docked to two SARS-CoV-2 protein structures with full optimization of ligand position and 20 poses per docking, each in under 24 hours. GPU acceleration and high-throughput optimizations of the docking program produced 350× mean speedup over the CPU version (50× speedup per node). GPU acceleration of both feature calculation for machine-learning based scoring and distributed database queries reduced processing of the 2.4 TB output by orders of magnitude. The resulting 50× speedup for the full pipeline reduces an initial 43 day runtime to 21 hours per protein for providing high-scoring compounds to experimental collaborators for validation assays.

show abstract

Section: Accelerated Distributed Database Queries On Massive Output Datasetsmentioning

confidence: 99%

High-throughput virtual laboratory for drug discovery using massive datasets

Gläser

Vermaas

Rogers

et al. 2021

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

show abstract

“…Обзор индустрии. C ростом вычислительной мощности графических процессоров и появлением более удобного способа их программирования (GPGPU), появились базы данных, использующие оптимизированные под архитектуру графических процессоров алгоритмы типичных операторов реляционной алгебры (например BlazingSQL, OmniSciDB, HeteroDB, Kinetica, SQream DB [1]). Для таких систем типичен механизм использования графического процессора для исполнения большинства DML (data manipulation language) запросов на устройстве.…”

Section: Hybrid Execution Of Queries To Analytical Databasesunclassified

Hybrid Execution of Queries to Analytical Databases

Kurapov

2021

IZVESTIYA SFedU. ENGINEERING SCIENCES

View full text Add to dashboard Cite

show abstract

“…However, their works focused on only a single GPU DBMS or their own prototypes rather than real-world GPU DBMSes. Our recent study raised some performance issues observed from several real-world GPU DBMSes [10]. Nevertheless, none of these works addressed the "economic worth" of utilizing GPU in analytical processing under a low budget circumstance.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Study across GPU DBMSes toward Cost-Effective Analytical Processing

Suh¹,

Kim²,

Lee³

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Young-Kyoon SUH †a) , Member, Seounghyeon KIM †b) , Joo-Young LEE †c) , Hawon CHU †d) , Junyoung AN †e) , and Kyong-Ha LEE † †f) , Nonmembers SUMMARYIn this letter we analyze the economic worth of GPU on analytical processing of GPU-accelerated database management systems (DBMSes). To this end, we conducted rigorous experiments with TPC-H across three popular GPU DBMSes. Consequently, we show that co-processing with CPU and GPU in the GPU DBMSes was cost-effective despite exposed concerns.

show abstract

Empirical evaluation across multiple GPU-accelerated DBMSes

Cited by 8 publications

References 5 publications

High-throughput virtual laboratory for drug discovery using massive datasets

High-throughput virtual laboratory for drug discovery using massive datasets

Hybrid Execution of Queries to Analytical Databases

An Experimental Study across GPU DBMSes toward Cost-Effective Analytical Processing

Contact Info

Product

Resources

About