Lossless compression of HNSW proximity graph indexes cuts ANN search memory via SIMD codecs
_reachsumit · x · 2026-10-29
A new paper proposes losslessly compressing HNSW edge lists for approximate nearest neighbor search: node IDs are reordered offline so they compress better, then decoded with fast SIMD integer codecs. The approach cuts index memory while preserving search quality, with paper and code released.
- Target: HNSW proximity graph indexes
- Method: offline ID reordering + SIMD integer codecs
- Result: lossless compression, lower memory footprint
More from Infra
- Short seller claims Cerebras wafers degrade after ~2 years, undermining its business — himanshustwts · 2026-10-29
- Apple's RAM upgrade pricing: 512GB costs a staggering $13,950 over base — firstadopter · 2026-10-29
- AI data center gas buildout could cost over $5.6 billion a year in health impacts — AINowInstitute · 2026-10-29
- Report: 177GW of planned gas plants to power US AI data centers, ~80% gas-fired — AINowInstitute · 2026-10-29
- Analysts split on Google's merchant TPU: $100B vs $252.7B by 2028 forecasts — Beth_Kindig · 2026-10-29
- Gemini 4 Carbon costs $7.76 per task, 23% less than Claude Opus 5.5 at same intelligence — ArtificialAnlys · 2026-10-29