Power consumption optimized translation of object code partitioned for hardware component based on identified operations

摘要

In the various aspects, a virtual machine operating at the machine layer may use power consumption models to partition object code into portions, identify the relative power efficiencies of the mobile device processors for the various code portions, and route the code portions to the mobile device processors that can perform the operations using the least amount of energy. A dynamic binary translator process may translate the object code portions into an instruction set language supported by the hardware component identified as being preferred. The code portions may be executed and the amount of power consumed may be measured, with the measurements used to generate and/or update performance and power consumption models.

主权项

1. A method for optimizing compiled object code during execution on a computing device, comprising:
analyzing the object code to identify operations required during execution of the object code; partitioning the object code into object code units based on identified operations; translating at least one object code unit into an instruction set supported by a hardware component that is different from a target hardware component for which the object code was compiled; collecting information on an amount of power consumed by the hardware component when executing the instruction set; and using the collected information to optimize the translations of the at least one object code unit based on the amount of power consumed by the hardware component.