Sizing and insertion of decoupling capacitance
AssigneeIntel Corporation
InventorQing Zhu
Life of this patent
Estimating the term…
Loading patent…
AssigneeIntel Corporation
InventorQing Zhu
Estimating the term…
A method and apparatus for allocating decoupling capacitance in a power grid is provided. A power grid model of an RLC network is evaluated to identify the power nodes that have peak voltages exceeding a minimum voltage threshold and a maximum voltage threshold. For each noisy node that violates the thresholds, a decoupling capacitor is inserted. The power grid is once again re-evaluated to determine of any of the power nodes still violate the voltage thresholds. For those violating power nodes, the size of the decoupling capacitor is incremented. This process of incrementing the size of the decoupling capacitance and re-evaluating the power grid is repeated until all the power nodes are within a noise budget or the noise level for each power node is within the thresholds. The decoupling capacitance is then re-evaluated as it is iteratively decremented while maintaining the power noise within the thresholds. This method of inserting and sizing decoupling capacitance allows the power noise thresholds, to be satisfied while optimizing the size of the decoupling capacitance.
A method, comprising:
A method, comprising:
A computer readable medium containing instructions which, when executed in a processing system, causes the processing system to perform a method for inserting decoupling capacitance, comprising:
An apparatus comprising
An apparatus, comprising:
An apparatus comprising
Dependencies are inferred from the claim text.