In-situ Indexing via Memristive Content-Addressable Memory

2026-06-30

AI Summary

This work addresses the limitations of traditional hash indexing, which is constrained by the “memory wall” and unable to fully exploit the parallelism offered by in-memory computing. The authors propose PATH, a novel architecture that leverages memristor-based content-addressable memory to enable highly parallel in-situ index operations—including insertion, lookup, update, and deletion. By redefining the hash indexing mechanism through ultra-large logical buckets and an in-memory data movement strategy, PATH virtually eliminates hash collision overhead and substantially reduces resizing costs. Experimental results demonstrate that PATH achieves 4.7–7.8× higher insertion throughput, over 14.5× lower tail latency, and more than 61.4% reduction in memory accesses compared to state-of-the-art alternatives.

Abstract

Processing-in-Memory (PIM) is a proven paradigm for overcoming the ``memory wall". However, while data indexing is severely bottlenecked by this same wall, it remains unclear how indexing can effectively benefit from PIM's unique capabilities. We present PATH, an in-situ indexing architecture that bridges this gap by leveraging the massive parallelism and inherent data-movement of PIMs. Specifically, we first reformulate the fundamental indexing operations, namely Insert, Search, Update, and Delete, into highly parallel in-situ content-addressable memory operations executed directly within memory arrays. Taking hash indexes as a typical case, we elaborate how PATH breaks the inherent trade-off among memory accesses, load factor, and process latency in conventional hashing schemes. By adopting ultra-large logical buckets and in-memory moving, PATH virtually eliminates the cost of hash collision resolution and significantly reduces resizing overhead. Compared with state-of-the-art schemes, PATH achieves $4.7-7.8\times$ higher throughput, $>14.5\times$ lower tail latency, and $>61.4\%$ fewer memory accesses under insertions, laying a scalable foundation for next-generation data-centric computing.

Problem

• Processing-in-Memory
• data indexing
• memory wall
• content-addressable memory
• hash indexes

Innovation

• Processing-in-Memory
• In-situ Indexing
• Memristive CAM
• Hash Index
• Data-Centric Computing