Combined dynamic and static power and performance optimization on data centers

A method of computing, comprising:

• receiving at a remote computing system an incoming task from a local computing device, the remote computing system having plural processors, plural defined processor performance bins, each processor performance bin having a processor performance state, at least one processor being assigned to each of the plural processor performance bins;
• monitoring processor performance metrics of at least one of the processors while the at least one of the processor executes the incoming task and modeling processor power based at least in part on the monitored performance metrics;
• and
• assigning future incoming tasks to one of the processor performance bins based at least in part on the modeled processor power.

A computing system, comprising:

• a decision device operable to define plural processor performance bins, each processor performance bin corresponding to one of multiple processor performance states;
• plural processors coupled to the decision device, each processor having the multiple processor performance states;
• and
• whereby the system includes instructions in a computer readable medium for assigning at least one processor to each of the plural processor performance bins, monitoring processor performance metrics of at least one of the processors while the at least one of the processors executes an incoming task and model processor power based on the monitored performance metrics, and assigning future incoming tasks to one of the processor performance bins based on the modeled processor power.