Improved Matrix Multiplication by Changing Loop Order

Matrix multiplication has been implemented in various programming languages, and improved performance reported many articles under settings. is of paramount interest to machine learning, a lightweight matrix-based key management protocol for IoT networks, animation, so on. There always need an terms algorithm implementation. In this work, the authors compared run times matrix popular languages such as C++, Java, Python. This analysis showed that Python’s implementation was poor while Java relatively slower C++ All aforementioned use row-major scheme, hence, there are cache misses encountered when through simple looping. contrast, show by changing loop order, more gains possible. Moreover, we evaluated comparing execution time The observed tremendous due better spatial locality. addition, also parallel version same using OpenMP with eight logical cores achieved speed-up seven serial