DISTRIBUTEDANN: Efficient Scaling of a Single DISKANN Graph Across Thousands of Computers
By: Philip Adams , Menghao Li , Shi Zhang and more
Potential Business Impact:
Finds information super fast in huge data.
We present DISTRIBUTEDANN, a distributed vector search service that makes it possible to search over a single 50 billion vector graph index spread across over a thousand machines that offers 26ms median query latency and processes over 100,000 queries per second. This is 6x more efficient than existing partitioning and routing strategies that route the vector query to a subset of partitions in a scale out vector search system. DISTRIBUTEDANN is built using two well-understood components: a distributed key-value store and an in-memory ANN index. DISTRIBUTEDANN has replaced conventional scale-out architectures for serving the Bing search engine, and we share our experience from making this transition.
Similar Papers
Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN
Distributed, Parallel, and Cluster Computing
Finds information faster across many computers.
Approximate Nearest Neighbor Search of Large Scale Vectors on Distributed Storage
Databases
Finds similar items in huge online lists faster.
Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph
Machine Learning (CS)
Finds information faster on huge computer files.