Matrix-matrix multiplication on graphics processing unit platform using tiling technique

Today’s hardware platforms have parallel processing capabilities and many programming models been developed. It is necessary to research an efficient implementation of compute-intensive applications using available platforms. Dense matrix-matrix multiplication important kernel that used in applications, while it computationally intensive, especially for large matrix sizes. To improve the performance this kernel, we implement on graphics unit (GPU) platform tiling technique with different tile Our experimental results show approach improves speed by 56.89% (2.32× faster) against straightforward (STF). And size 32 has highest compared other sizes 8 16.