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

2025/09/15 by Ockerman, Seth, Gueroudji, Amal, Oh, Song Young +5 · 2 citations
#Databases (cs.DB) #Distributed #FOS: Computer and information sciences #Parallel #and Cluster Computing (cs.DC)

paper · doi:10.48550/arxiv.2509.12384

Abstract

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.

Citations

• HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
• Usability Evaluation of Cloud for HPC Applications
• Quake: Adaptive Indexing for Vector Search
• Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization
• HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
• Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory
• A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
• Introducing the Bacterial and Viral Bioinformatics Resource Center (BV-BRC): a resource combining PATRIC, IRD and ViPR
• Billion-scale similarity search with GPUs
• Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
• Efficient Estimation of Word Representations in Vector Space
• Multidimensional binary search trees used for associative searching

Cited by

• OrchANN: Hierarchical Orchestration for Skewed Out-of-Core Vector Search
• ZeBROD: Zero-Retraining Based Recognition and Object Detection Framework

Related

• Fantasy: Efficient Large-scale Vector Search on GPU Clusters with GPUDirect Async
• Vector-Centric Machine Learning Systems: A Cross-Stack Approach
• A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
• Efficient Vector Search on Disaggregated Memory with d-HNSW
• ESPN: Memory-Efficient Multi-Vector Information Retrieval