REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing

• URL: http://arxiv.org/abs/2506.16444v1
• Date: Thu, 19 Jun 2025 16:26:51 GMT
• Title: REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing
• Authors: Kangqi Chen, Andreas Kosmas Kakolyris, Rakesh Nadig, Manos Frouzakis, Nika Mansouri Ghiasi, Yu Liang, Haiyu Mao, Jisung Park, Mohammad Sadrosadati, Onur Mutlu,
• Abstract summary: Large Language Models (LLMs) face an inherent challenge: their knowledge is confined to the data that they have been trained on.<n>Retrieval-Augmented Generation (RAG) complements the static training-derived knowledge of LLMs with an external knowledge repository.<n>We propose REIS, the first ISP system tailored for RAG that addresses these limitations with three key mechanisms.
• Score: 8.574396262432522
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Large Language Models (LLMs) face an inherent challenge: their knowledge is confined to the data that they have been trained on. To overcome this issue, Retrieval-Augmented Generation (RAG) complements the static training-derived knowledge of LLMs with an external knowledge repository. RAG consists of three stages: indexing, retrieval, and generation. The retrieval stage of RAG becomes a significant bottleneck in inference pipelines. In this stage, a user query is mapped to an embedding vector and an Approximate Nearest Neighbor Search (ANNS) algorithm searches for similar vectors in the database to identify relevant items. Due to the large database sizes, ANNS incurs significant data movement overheads between the host and the storage system. To alleviate these overheads, prior works propose In-Storage Processing (ISP) techniques that accelerate ANNS by performing computations inside storage. However, existing works that leverage ISP for ANNS (i) employ algorithms that are not tailored to ISP systems, (ii) do not accelerate data retrieval operations for data selected by ANNS, and (iii) introduce significant hardware modifications, limiting performance and hindering their adoption. We propose REIS, the first ISP system tailored for RAG that addresses these limitations with three key mechanisms. First, REIS employs a database layout that links database embedding vectors to their associated documents, enabling efficient retrieval. Second, it enables efficient ANNS by introducing an ISP-tailored data placement technique that distributes embeddings across the planes of the storage system and employs a lightweight Flash Translation Layer. Third, REIS leverages an ANNS engine that uses the existing computational resources inside the storage system. Compared to a server-grade system, REIS improves the performance (energy efficiency) of retrieval by an average of 13x (55x).

Related papers

• Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation [80.69067017594709]
  Large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks.<n>We propose a novel framework, log-augmented generation (LAG) that directly reuses prior computation and reasoning from past logs at test time.<n>Our method significantly outperforms standard agentic systems that do not utilize logs.
  arXiv  Detail & Related papers  (2025-05-20T14:14:38Z)
• s3: You Don't Need That Much Data to Train a Search Agent via RL [41.21029905607559]
  Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference.<n>We propose s3, a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the searcher using a Gain Beyond RAG reward.
  arXiv  Detail & Related papers  (2025-05-20T09:53:56Z)
• An Adaptive Vector Index Partitioning Scheme for Low-Latency RAG Pipeline [0.6445605125467574]
  Retrieval Augmented Generation (RAG) systems enhance response quality by integrating Large Language Models (LLMs) with vector databases.<n>Existing optimizations for vector search and LLM serving have largely been developed in isolation.<n>This paper introduces VectorLiteRAG, an optimized vector index partitioning mechanism designed for RAG systems.
  arXiv  Detail & Related papers  (2025-04-11T19:18:41Z)
• TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval [10.268774281394261]
  Retrieval-augmented generation (RAG) extends large language models (LLMs) with external data sources to enhance factual correctness and domain coverage.<n>Modern RAG pipelines rely on large datastores, leading to system challenges in latency-sensitive deployments.<n>We propose TeleRAG, an efficient inference system that reduces RAG latency with minimal GPU memory requirements.
  arXiv  Detail & Related papers  (2025-02-28T11:32:22Z)
• Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search [18.419278931226756]
  SOGAIC is a graph-based ANNS index construction system tailored for ultra-large-scale vector databases.<n>The proposed method has been successfully deployed in a real-world industrial search engine, managing over 10 billion daily updated vectors.
  arXiv  Detail & Related papers  (2025-02-28T04:03:23Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• ScalingNote: Scaling up Retrievers with Large Language Models for Real-World Dense Retrieval [72.2676180980573]
  Large Language Models (LLMs) have exhibited superior performance that can be leveraged for scaling up dense retrieval. We propose ScalingNote, a two-stage method to exploit the scaling potential of LLMs for retrieval while maintaining online query latency. Our two-stage scaling method outperforms end-to-end models and verifies the scaling law of dense retrieval with LLMs in industrial scenarios.
  arXiv  Detail & Related papers  (2024-11-24T09:27:43Z)
• RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards [78.74923079748521]
  Retrieval-Augmented Generation (RAG) has proven its effectiveness in mitigating hallucinations in Large Language Models (LLMs) by retrieving knowledge from external resources.<n>Current approaches use instruction tuning to optimize LLMs, improving their ability to utilize retrieved knowledge.<n>We propose a Differentiable Data Rewards ( DDR) method, which trains RAG systems by aligning data preferences between different RAG modules.
  arXiv  Detail & Related papers  (2024-10-17T12:53:29Z)
• MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation [60.04380907045708]
  Retrieval-Augmented Generation (RAG) is considered a promising strategy to address this problem.<n>We propose MemoRAG, a novel RAG framework empowered by global memory-augmented retrieval.<n>MemoRAG achieves superior performances across a variety of long-context evaluation tasks.
  arXiv  Detail & Related papers  (2024-09-09T13:20:31Z)
• Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding [61.45448947483328]
  We introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER)<n>LASER features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens.<n>LASER achieves a 3-5x speedup on public datasets and saves about 67% of computational resources during the online A/B test.
  arXiv  Detail & Related papers  (2024-08-11T02:31:13Z)
• DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems [79.76519917171261]
  This paper addresses the computational overhead and resource inefficiency prevalent in Sequential Recommender Systems (SRSs)<n>We introduce an innovative approach combining pruning methods with advanced model designs.<n>Our principal contribution is the development of a Data-aware Neural Architecture Search for Recommender System (DNS-Rec)
  arXiv  Detail & Related papers  (2024-02-01T07:22:52Z)
• Synergistic Interplay between Search and Large Language Models for Information Retrieval [141.18083677333848]
  InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections. InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-12T11:58:15Z)
• MIX-RS: A Multi-indexing System based on HDFS for Remote Sensing Data Storage [21.033380514644616]
  A large volume of remote sensing (RS) data has been generated with the deployment of satellite technologies. The characteristics of RS data (e.g., enormous volume, large single-file size and demanding requirement of fault tolerance) make the Hadoop Distributed File System (HDFS) an ideal choice for RS data storage. To use RS data, one of the most important techniques is geospatial indexing. We propose a framework called Multi-IndeXing-RS (MIX-RS) that unifies the multi-indexing mechanism on top of the HDFS.
  arXiv  Detail & Related papers  (2022-08-05T05:11:12Z)

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.