Title: A Genetic Algorithms Approach to Modeling the Performance of Memory-bound Computations.

Authors: M. Tikir, L. Carrington, E. Strohmaier, A. Snavely

Abstract: Benchmarks that measure memory bandwidth, such as STREAM, Apex-MAPS and MultiMAPS, are increasingly popular due to the "Von Neumann" bottleneck of modern processors which causes many calculations to be memory-bound. We present a scheme for predicting the performance of HPC applications based on the results of such benchmarks. A Genetic Algorithm approach is used to "learn" bandwidth as a function of cache hit rates per machine with MultiMAPS as the fitness test. The specific results are 56 individual performance predictions including 3 full-scale parallel applications run on 5 different modern HPC architectures, with various CPU counts and inputs, predicted within 10% average difference with respect to independently verified runtimes.

Reference: @inproceedings{tikirga2007, Author = {M. Tikir, L. Carrington, E. Strohmaier, A. Snavely}, Booktitle = {Proceedings of SC07, Reno, NV, November 2007}, Title = {A Genetic Algorithms Approach to Modeling the Performance of Memory-bound Computations}, Year = {2007}}