CABANA : Cluster-Aware Query Batching for Accelerating Billion-Scale ANNS With Intel AMX

Retrieval-augmented generation (RAG) systems increasingly rely on Approximate Nearest Neighbor Search (ANNS) to efficiently retrieve relevant context from billion-scale vector databases. While IVF-based ANNS frameworks scale well overall, the fine search stage remains a bottleneck due to its compute-intensive GEMV operations, particularly under large query volumes. To address this, we propose CABANA , a c luster- a ware query b atching for AN NS a cceleration mechanism using Intel Advanced Matrix Extensions (AMX) that reformulates these GEMV computations into high-throughput GEMM operations. By aggregating queries targeting the same clusters, CABANA enables batched computation during fine search, significantly improving compute intensity and memory access regularity. Evaluations on billion-scale datasets show that CABANA outperforms traditional SIMD-based implementations, achieving up to $32.6\times$32 . 6 ×higher query throughput with minimal overhead, while maintaining high recall rates.