Perceptron Learning for Predicting the Behavior of Conditional Branches Conference Paper

abstract

• Branch prediction, i.e., predicting the outcome of a conditional branch instruction, is essential to the performance of current and future microprocessors. We show how perceptrons can be used to improve the state of the art in branch prediction. We explore the unusual challenges this domain presents for neural systems, and we show why other neural methods, such as back-propagation, provide no additional accuracy in this context. Finally, we identify other areas where neural systems can be applied to microprocessor implementation.

name of conference

• IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)

authors

• Jimenez, Daniel

published proceedings

• IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)

author list (cited authors)

• Jimnez, D. A., & Lin, C.

citation count

• 8

complete list of authors

• Jiménez, Daniel A||Lin, Calvin

publication date

• January 2001

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

keywords

• Basic Behavioral And Social Science
• Behavioral And Social Science
• Neurosciences

Digital Object Identifier (DOI)

• 10.1109/ijcnn.2001.938494

start page

• 2122

end page

• 2127

volume

• 3

URL

• http://dx.doi.org/10.1109/ijcnn.2001.938494