Jaewook Shin, Mary W. Hall, Jacqueline Chame, Chun Chen, Paul D. Hovland. Autotuning and Specialization: Speeding up Matrix Multiply for Small Matrices with Compiler Technology. In Ken Naono, Keita Teranishi, John Cavazos, Reiji Suda, editors, Software Automatic Tuning, From Concepts to State-of-the-Art Results. pages 353-370, Springer, 2010. [doi]
Abstract is missing.