# D-NOVA: In-Storage Retrieval Accelerator via Dual-Bound 3D NAND-Optimized Similarity Search with Vector Adaptation

arXiv: https://arxiv.org/abs/2607.17538 · HTML: https://mlsanity.com/paper/2607.17538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 85 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [InfoNCE Loss Provably Learns Cluster-Preserving Representations](https://mlsanity.com/paper/2302.07920/) (2023)
- [SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2111.08566/) (2021)
- [CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs](https://mlsanity.com/paper/2308.15136/) (2023)
- [RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving](https://mlsanity.com/paper/2503.14649/) (2025)
- [Pathfinding Future PIM Architectures by Demystifying a Commercial PIM Technology](https://mlsanity.com/paper/2308.00846/) (2023)
- [Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation](https://mlsanity.com/paper/2209.00606/) (2022)
- [AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark](https://mlsanity.com/paper/2412.13102/) (2024)
- [Error Characterization, Mitigation, and Recovery in Flash Memory Based Solid-State Drives](https://mlsanity.com/paper/1706.08642/) (2017)
- [FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing](https://mlsanity.com/paper/2409.10918/) (2024)
- [REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing](https://mlsanity.com/paper/2506.16444/) (2025)
- [Accelerating Large-Scale Graph-based Nearest Neighbor Search on a Computational Storage Platform](https://mlsanity.com/paper/2207.05241/) (2022)
- [Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND](https://mlsanity.com/paper/2312.04257/) (2023)
- [Flexible In-NAND Cryptographic Processing for Secure Flash Storage](https://mlsanity.com/paper/2508.03866/) (2025)
- [FeNOMS: Enhancing Open Modification Spectral Library Search with In-Storage Processing on Ferroelectric NAND (FeNAND) Flash](https://mlsanity.com/paper/2510.10872/) (2025)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances the factual grounding of large language model (LLM) inference by retrieving relevant information from external knowledge bases. However, its dense vector retrieval introduces significant latency and energy overhead, becoming the primary performance bottleneck. Although recent in-storage accelerators aim to reduce data movement, they still rely on host or embedded processors outside the memory, where nearly 70% of the total retrieval time is spent. As a result, they cannot fully overcome the bandwidth limitations, leading to yet another memory bottleneck. To tackle these limitations, we present D-NOVA, a hardware-software co-designed in-storage retrieval accelerator. D-NOVA executes an inverted file (IVF)-based hierarchical retrieval pipeline by deeply embedding the search functionality directly into the NAND memory array. This is achieved by incorporating a new distance metric, Dual-Bound Tight Similarity Sensing (DTS), which is specifically tailored for searching within the NAND string. In addition, we introduce a lightweight contrastive adapter that maps embedding vectors into a DTS-friendly domain, recovering near-software recall while improving performance and energy efficiency. D-NOVA is up to 41.7x faster and 71x more energy-efficient than a CPU baseline, and achieves 12.13x higher throughput while being up to 1.26x more energy-efficient than state-of-the-art in-storage RAG accelerators, demonstrating the potential of fully in-storage vector search for scalable RAG acceleration.