This project implements high-performance dense-dense, dense-sparse, and sparse-sparse matrix multiplication using C++ with configurable multi-threading, SIMD optimizations, and cache miss minimization ...

In intelligent connected vehicle applications, tasks, such as path planning and health management involve numerous matrix operations, particularly matrix multiplication. Due to limited resources, ...

Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in ...