David Kanter from the Real World Technologies blog writes about the fine art of predicting GPU application performance:
The key to accurately predicting performance and efficiency is being able to identify and isolate the variables that mostly strongly determine performance and build them into a predictive model. Of course these models vary in complexity; from simple back of the envelop calculations to moderately involved analytic formulas to the cycle accurate simulators that designers rely upon. Performance can be expressed in a fairly simple form with a few variables:
Leave your own comment