A CCD-level, workload-aware thread orchestration framework for in-memory vector ANNS delivers up to 3.7x higher throughput and 30-90% lower P50/P999 latency on multi-core CPUs by improving cache use and load balance.
iQAN: Fast and Accurate Vector Search with Efficient Intra-Query Parallelism on Multi- Core Architectures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CCD-Level and Load-Aware Thread Orchestration for In-Memory Vector ANNS on Multi-Core CPUs
A CCD-level, workload-aware thread orchestration framework for in-memory vector ANNS delivers up to 3.7x higher throughput and 30-90% lower P50/P999 latency on multi-core CPUs by improving cache use and load balance.