Related papers: Bang for the Buck: Vector Search on Cloud CPUs
The rapid adoption of AI-powered applications demands high-performance, scalable, and efficient cloud database solutions, as traditional architectures often struggle with AI-driven workloads requiring real-time data access, vector search,…
Graph-based indexing is the dominant approach for approximate nearest neighbor search in vector databases, offering high recall with low latency across billions of vectors. However, in such indices, the edge set of the proximity graph is…
CPU-based inference can be an alternative to off-chip accelerators, and vector architectures are a promising option due to their efficiency. However, the large design space of convolutional algorithms and hardware implementations makes it…
Hardware-aware Neural Architecture Search (NAS) technologies have been proposed to automate and speed up model design to meet both quality and inference efficiency requirements on a given hardware. Prior arts have shown the capability of…
CPU is undoubtedly the most important resource of the computer system. Recent advances in software and system architecture have increased processing complexity, as computing is now distributed and parallel. CloudSim represents the…
For the past two decades, the DB community has devoted substantial research to take advantage of cheap clusters of machines for distributed data analytics -- we believe that we are at the beginning of a paradigm shift. The scaling laws and…
Vector search systems are indispensable in large language model (LLM) serving, search engines, and recommender systems, where minimizing online search latency is essential. Among various algorithms, graph-based vector search (GVS) is…
Modern processor architectures, in addition to having still more cores, also require still more consideration to memory-layout in order to run at full capacity. The usefulness of most languages is deprecating as their abstractions,…
The current era of quantum computing has yielded several algorithms that promise high computational efficiency. While the algorithms are sound in theory and can provide potentially exponential speedup, there is little guidance on how to…
Modern database clusters entail two levels of networks: connecting CPUs and NUMA regions inside a single server in the small and multiple servers in the large. The huge performance gap between these two types of networks used to slow down…
Cloud platforms are increasingly being used to run HPC workloads. Major cloud providers offer a wide variety of virtual machine (VM) types, enabling users to find the optimal balance between performance and cost. However, this extensive…
Vector similarity search has become a critical component in AI-driven applications such as large language models (LLMs). To achieve high recall and low latency, GPUs are utilized to exploit massive parallelism for faster query processing.…
Vector processing has become commonplace in today's CPU microarchitectures. Vector instructions improve performance and energy which is crucial for resource-constraint mobile devices. The research community currently lacks a comprehensive…
How can applications be deployed on the cloud to achieve maximum performance? This question has become significant and challenging with the availability of a wide variety of Virtual Machines (VMs) with different performance capabilities in…
Hybrid search, which jointly optimizes vector similarity and structured predicate filtering, has become a fundamental building block for modern AI-driven systems. While recent predicate-aware ANN indices improve filtering efficiency on…
There are now over 20 commercial vector database management systems (VDBMSs), all produced within the past five years. But embedding-based retrieval has been studied for over ten years, and similarity search a staggering half century and…
Retrieval-Augmented Generation is a technology that enhances large language models by integrating information retrieval. In the industry, inference services based on LLMs are highly sensitive to cost-performance ratio, prompting the need…
GPUs offer massive compute parallelism and high-bandwidth memory accesses. GPU database systems seek to exploit those capabilities to accelerate data analytics. Although modern GPUs have more resources (e.g., higher DRAM bandwidth) than…
Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table…
Vertical search engines focus on specific slices of content, such as the Web of a single country or the document collection of a large corporation. Despite this, like general open web search engines, they are expensive to maintain,…