We had an unfinished disccusion in a class on improving performance of matrix multiplication. Many people seem to implement matrix multiplication using rowA * columnB. However, if you change the ...
If you start naively without any library that avoids the problem then memory access is the problem. Have a look at how much effort is needed to avoid the problem, for example with blocking algorithms.
Researchers at MIT's Computer Science & Artificial Intelligence Lab (CSAIL) have open-sourced Multiply-ADDitioN-lESS (MADDNESS), an algorithm that speeds up machine learning using approximate matrix ...