METHOD FOR THE COMPUTATION OF A NARROW BIT WIDTH LINEAR ALGEBRA OPERATION

 Status:
Published
 Priority date:
 Inventor:
Osman UnsalAdrian Cristal Kestelman
 Applicant:
Barcelona Supercomputing Center

Abstract

The present invention relates to a method for computing a linear algebra operation of two operands or arrays comprising one or more narrow bit width elements with a digital circuit. The method uses the principle of binary segmentation to reduce the computation overhead of linear algebra operations like linear convolution and inner product of operands such as vectors with narrow bit width components. The invention is also directed to a digital circuit configured to execute the method.