GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing

• URL: http://arxiv.org/abs/2604.16402v1
• Date: Tue, 31 Mar 2026 11:00:10 GMT
• Title: GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
• Abstract summary: We present GRAB-ANNS, a GPU-native graph index for dynamic hybrid search.<n>We show that GRAB-ANNS achieves up to 240.1 times higher query throughput and 12.6 times faster index construction than state-of-the-art CPU-based systems.
• Score: 39.763467046232584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 CPUs, their performance is increasingly constrained by limited memory bandwidth and parallelism. Although GPUs offer massive parallelism and superior memory bandwidth, directly porting CPU-centric hybrid search algorithms to GPUs leads to severe performance degradation due to architectural mismatches, including irregular memory access, branch divergence, and excessive CPU-GPU synchronization. In this paper, we present GRAB-ANNS, a high-throughput, GPU-native graph index for dynamic hybrid search. Our key insight is to rethink hybrid indexing from a hardware-first perspective. We introduce a bucket-based memory layout that transforms range predicates into lightweight bucket selection, enabling coalesced memory accesses and efficient SIMT execution. To preserve global navigability under arbitrary filters, we design a hybrid graph topology that combines dense intra-bucket local edges with sparse inter-bucket remote edges. We further develop an append-only update pipeline that supports efficient batched insertions and parallel graph maintenance on GPUs. Extensive experiments on large-scale datasets show that GRAB-ANNS achieves up to 240.1 times higher query throughput and 12.6 times faster index construction than state-of-the-art CPU-based systems, and up to 10 times higher throughput compared to optimized GPU-native reimplementations, while maintaining high recall.

Related papers

• Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture [13.990684047479578]
  Current oblivious semantic search system, Compass, incurs large overheads.<n>We propose a first-of-its-kind oblivious semantic search system with a heterogeneous CPU-GPU TEE architecture.<n>Hoss achieves 67x speedup while maintaining high recall, with larger gains at scale.
  arXiv  Detail & Related papers  (2026-09-03T22:21:51Z)
• GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions [54.570944939061555]
  We present a comprehensive study of GPU-accelerated graph-based vector search algorithms.<n>We establish a detailed taxonomy of GPU optimization strategies and clarify the mapping between algorithmic tasks and hardware execution units.<n>Our findings offer clear guidelines for designing scalable and robust GPU-powered approximate nearest neighbor search systems.
  arXiv  Detail & Related papers  (2026-02-10T16:18:04Z)
• GPU-Accelerated ANNS: Quantized for Speed, Built for Change [1.8419317899207142]
  Current Approximate nearest neighbor search (ANNS) systems face three key limitations.<n>Current systems lack efficient quantization techniques that reduce data movement without introducing costly random memory accesses.<n>We present Jasper, a GPU-accelerated ANNS system with both high query throughput and upability.
  arXiv  Detail & Related papers  (2026-01-11T19:51:54Z)
• A Parallel CPU-GPU Framework for Cost-Bounded DFS with Applications to IDA* and BTS [13.186524200050957]
  We introduce a method for GPU computations in depth first search.<n>This is used to create algorithms like emphsynchronous IDA*, an extension of the Iterative Deepening A* (IDA*) algorithm.<n>We evaluate the approach on the 3x3's Rubik Cube and 4x4 sliding tile puzzle (STP), showing that GPU operations can be efficiently batched in DFS.
  arXiv  Detail & Related papers  (2025-07-16T05:07:33Z)
• INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing [66.00729477511219]
  Given a function represented as a computation graph, traditional architectures face challenges in efficiently computing its nth-order gradient. We introduce INR-Arch, a framework that transforms the computation graph of an nth-order gradient into a hardware-optimized dataflow architecture. We present results that demonstrate 1.8-4.8x and 1.5-3.6x speedup compared to CPU and GPU baselines respectively.
  arXiv  Detail & Related papers  (2023-08-11T04:24:39Z)
• MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms [28.25823488936712]
  We propose MGG, a novel system design to accelerate full-graph GNNs on multi-GPU platforms. The core of MGG is its novel dynamic software pipeline to facilitate fine-grained computation-communication overlapping within a GPU kernel. MGG outperforms state-of-the-art full-graph GNN systems across various settings.
  arXiv  Detail & Related papers  (2022-09-14T17:32:28Z)
• Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers [65.60007071024629]
  We show that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy. We show experimentally that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy.
  arXiv  Detail & Related papers  (2021-10-13T20:58:15Z)
• DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks [58.48833325238537]
  Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible. In this paper, we presentGNN that optimize the well-known Deep Graph Library (DGL) for full-batch training on CPU clusters. Our results on four common GNN benchmark datasets show up to 3.7x speed-up using a single CPU socket and up to 97x speed-up using 128 CPU sockets.
  arXiv  Detail & Related papers  (2021-04-14T08:46:35Z)
• Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture [19.2129567657739]
  Graph Convolutional Networks (GCNs) are increasingly adopted in large-scale graph-based recommender systems. Current GCN training systems keep the feature table in host memory and rely on the CPU to collect sparse features. This approach, however, puts tremendous pressure on host memory bandwidth and the CPU. We propose a novel GPU-oriented data communication approach for GCN training, where GPU threads directly access sparse features in host memory.
  arXiv  Detail & Related papers  (2021-03-04T21:00:17Z)
• Heterogeneous CPU+GPU Stochastic Gradient Descent Algorithms [1.3249453757295084]
  We study training algorithms for deep learning on heterogeneous CPU+GPU architectures. Our two-fold objective -- maximize convergence rate and resource utilization simultaneously -- makes the problem challenging. We show that the implementation of these algorithms achieves both faster convergence and higher resource utilization than on several real datasets.
  arXiv  Detail & Related papers  (2020-04-19T05:21:20Z)
• MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models [96.1052289276254]
  This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle. Surprisingly, by making a small change to the low-performing solver, we derive the new solver MPLP++ that significantly outperforms all existing solvers by a large margin.
  arXiv  Detail & Related papers  (2020-04-16T16:20:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.