Algebraic enhancements for GEMM & AI accelerators

Caffe for Sparse Convolutional Neural Network

Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)

Implementation of convolution layer in different flavors

Winograd Convolution in Julia with CUDA kernels

Winograd Convolution Implementation using by cpp

Supplementary materials for the paper "Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution" (Emelin et al., 2021)

The fast transformation algorithm for transposed convolutional layers

A series of programs that enable one's investigations in the algebraic complexity theory such as matrix multiplication algorithms, primality tests, algebraic complexity, sorting algorithms etc. Each algorithm is accompanied by a comparative time complexity analysis and a class of test cases and test suites.

winograd 1d convolution using by cuda