A Small Study of Byte Matrix Multiply It's quite common in machine learning operations to multiply a matrix of unsigned byte by a matrix of signed byte. Don't ask me why, but that's the case. And it turns out it's an interesting computation kernel to optimize, and that's what we're going to discuss in this article. Disclaimer 0: this is not a research paper, it's just a small study. It's very likely that this work is well behind the state-of-the-art research, but it was an interesting trip. Disc...