[Paper] Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors

Source: arXiv - 2606.08813v1

Overview

We present HNTL (Hierarchical No-pointer Tangent-Local), the core vector indexing and candidate generation framework of the Aperon vector memory system. Proximity graphs (e.g., HNSW) incur a heavy pointer tax in memory overhead and induce irregular memory accesses that stall CPU pipelines. HNTL resolves this by partitioning the high-dimensional space into local, coherent grains, representing vectors as low-dimensional coordinates on local tangent spaces, and scanning them sequentially using a pointerless Block-SoA (Structure-of-Arrays) layout. On anisotropic manifold data (d=768, N=10,000), local PCA captures 96.3% of the variance, allowing HNTL to achieve a final Rerank Recall@10 of 1.0000 with a candidate pool size of only C=20 vectors. Hardware profiling via Apple kperf CPU Performance Monitoring Unit (PMU) counters demonstrates a 3.61x speedup (4.137 ns/vector vs. 14.951 ns/vector) for our NEON auto-vectorized C++ Block-SoA scan engine over standard pointer-chasing graph traversals, driven by a 3.59x IPC (Instructions Per Cycle) and near-zero L1/L2 data cache misses.

Key Contributions

This paper presents research in the following areas:

• cs.DC
• cs.DB
• cs.IR
• cs.LG

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.DC.

Authors

• Yong Fu

Paper Information

• arXiv ID: 2606.08813v1
• Categories: cs.DC, cs.DB, cs.IR, cs.LG
• Published: June 7, 2026
• PDF: Download PDF