However, developing high-performance sparse operators can be difficult and tedious, and existing vendor libraries cannot satisfy the escalating demands from new operators.
Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives.
Experimental results show that MetaSchedule can cover the search space used in the state-of-the-art tensor program optimization frameworks in a modular way.
We show that one cause for such success is due to the fact that the multi-branch architecture is less non-convex in terms of duality gap.
In this paper, we propose an improved residual vector quantization (IRVQ) method, our IRVQ learns codebook with a hybrid method of subspace clustering and warm-started k-means on each stage to prevent performance gain from dropping, and uses a multi-path encoding scheme to encode a vector with lower distortion.
We propose a novel distance to calculate distance between high dimensional vector pairs, utilizing vector quantization generated encodings.
Further, we propose Aggregating-Tree (A-Tree), a non-exhaustive search method using HCLAE to perform efficient ANN-Search.