Online Performance Projection for Clusters with Heterogeneous GPUs
|Title||Online Performance Projection for Clusters with Heterogeneous GPUs|
|Publication Type||Conference Paper|
|Year of Publication||2013|
|Conference Name||19th IEEE International Conference on Parallel and Distributed Systems|
|Conference Location||Seoul, KOR|
We present a fully automated approach to project the relative performance of an OpenCL program over different GPUs. Performance projections can be made within a small amount of time, and the projection overhead stays relatively constant with the input data size. As a result, the technique can help runtime tools make dynamic decisions about which GPU would run faster for a given kernel. Usage cases of this technique include scheduling or migrating GPU workloads over a heterogeneous cluster with different types of GPUs.