You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-512 and Arm NEON & SVE 📐
Repository for the paper "Odyssey: A Journey in the Land of Distributed Data Series Similarity Search", Manos Chatzakis, Panagiota Fatourou, Eleftherios Kosmas, Themis Palpanas and Botao Peng, PVLDB 2023
The Similarity Search Tree is an efficient method for indexing high dimensional feature vectors. The main objective of this data structure is to obtain the nearest neighbors given a certain query vector in a reasonable amount of time. In this project, the k-NN algorithm was adapted for supporting image retrieval.
SING is an in-memory index that uses the GPU's parallelization opportunities (as well as SIMD, multi-core and multi-socket), in order to accelerate similarity search.