Standard matrix multiplication with parallel processing Strassen's algorithm for large matrices Automatic optimization between standard and Strassen's algorithm Support for matrices of any size ...

On an NVIDIA C1060 GPU, a speedup of 32% (35%) is obtained for Strassen's 4-level implementation and 33% (36%) for Winograd's variant relative to the sgemm (integer version of sgemm) code in CUBLAS ...

We explored how modern artificial-intelligence (AI) techniques could advance the discovery of matrix multiplication algorithms. Strassen’s work showed that matrix-multiplication algorithms can ...