This study proposes a method for the detection and correction of errors in the implementation of the matrix multiplication supercomputers due to noise. The proposed method based on a comparison of the results of the two operations with using CUDA-technology. Operations are performed in parallel by the action of the same interference.
Nikolay Ivanovich Korsunov, Igor Sergeevich Konstantinov and Aleksandr Aleksandrovich Nachetov. Error Correction Method Results in a Multiplication of the Supercomputer.
DOI: https://doi.org/10.36478/rjasci.2014.1120.1123
URL: https://www.makhillpublications.co/view-article/1815-932x/rjasci.2014.1120.1123