Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ockerman, Seth, Gueroudji, Amal, Oh, Song Young, Underwood, Robert, Chia, Nicholas, Chard, Kyle, Ross, Robert, Venkataraman, Shivaram
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915558321029120
author Ockerman, Seth
Gueroudji, Amal
Oh, Song Young
Underwood, Robert
Chia, Nicholas
Chard, Kyle
Ross, Robert
Venkataraman, Shivaram
author_facet Ockerman, Seth
Gueroudji, Amal
Oh, Song Young
Underwood, Robert
Chia, Nicholas
Chard, Kyle
Ross, Robert
Venkataraman, Shivaram
contents Vector databases have rapidly grown in popularity, enabling efficient similarity search over data such as text, images, and video. They now play a central role in modern AI workflows, aiding large language models by grounding model outputs in external literature through retrieval-augmented generation. Despite their importance, little is known about the performance characteristics of vector databases in high-performance computing (HPC) systems that drive large-scale science. This work presents an empirical study of distributed vector database performance on the Polaris supercomputer in the Argonne Leadership Computing Facility. We construct a realistic biological-text workload from BV-BRC and generate embeddings from the peS2o corpus using Qwen3-Embedding-4B. We select Qdrant to evaluate insertion, index construction, and query latency with up to 32 workers. Informed by practical lessons from our experience, this work takes a first step toward characterizing vector database performance on HPC platforms to guide future research and optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12384
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant
Ockerman, Seth
Gueroudji, Amal
Oh, Song Young
Underwood, Robert
Chia, Nicholas
Chard, Kyle
Ross, Robert
Venkataraman, Shivaram
Distributed, Parallel, and Cluster Computing
Databases
Vector databases have rapidly grown in popularity, enabling efficient similarity search over data such as text, images, and video. They now play a central role in modern AI workflows, aiding large language models by grounding model outputs in external literature through retrieval-augmented generation. Despite their importance, little is known about the performance characteristics of vector databases in high-performance computing (HPC) systems that drive large-scale science. This work presents an empirical study of distributed vector database performance on the Polaris supercomputer in the Argonne Leadership Computing Facility. We construct a realistic biological-text workload from BV-BRC and generate embeddings from the peS2o corpus using Qwen3-Embedding-4B. We select Qdrant to evaluate insertion, index construction, and query latency with up to 32 workers. Informed by practical lessons from our experience, this work takes a first step toward characterizing vector database performance on HPC platforms to guide future research and optimization.
title Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant
topic Distributed, Parallel, and Cluster Computing
Databases
url https://arxiv.org/abs/2509.12384