Application aware graceful over current protection for multi-socket platforms

A semiconductor apparatus comprising:

• one or more substrates;
• and
• logic coupled to the one or more substrates, wherein the logic is arranged on a primary circuit board and is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:
• receive an indication of a detected over current condition associated with a first voltage regulator on a secondary circuit board in a computing system, wherein the computing system comprises a plurality of circuit boards, each of the plurality of circuit boards including a voltage regulator and a processor coupled to the voltage regulator, wherein the plurality of circuit boards includes the primary circuit board and the secondary circuit board, the primary circuit board having a baseboard management controller (BMC), and wherein the indication is to be received while bypassing the BMC;
• identify a configurable over current protection policy associated with the first voltage regulator;
• automatically take a first protective action based on the configurable over current protection policy, wherein the first protective action includes one or more of a frequency throttle of a first processor on the secondary circuit board in isolation from one or more additional processors in the computing system, or a deactivation of the first processor in isolation from the one or more additional processors, wherein the first protective action is to be communicated to the secondary circuit board while bypassing the BMC, and
• initiate, via a communication from the BMC to a remote administrator, a second protective action based on the configurable over current protection policy, wherein the second protective action includes one or more of a data center fleet manager notification or a migration of a workload from the first processor to at least one of the other processors,
• wherein the first protective action and the second protective action are each responsive to the indication of the detected over current condition.

At least one non-transitory computer readable storage medium comprising a set of executable program instructions, which when executed by a computing system, cause the computing system to:

• receive at a primary circuit board an indication of a detected over current condition associated with a first voltage regulator on a secondary circuit board in the computing system, wherein the computing system comprises a plurality of circuit boards, each of the plurality of circuit boards including a voltage regulator and a processor coupled to the voltage regulator, wherein the plurality of circuit boards includes the primary circuit board and the secondary circuit board, the primary circuit board having a baseboard management controller (BMC), and wherein the indication is to be received while bypassing the BMC;
• identify a configurable over current protection policy associated with the first voltage regulator;
• automatically take a first protective action based on the configurable over current protection policy, wherein the first protective action includes one or more of a frequency throttle of a first processor on the secondary circuit board in isolation from one or more additional processors in the computing system, or a deactivation of the first processor in isolation from the one or more additional processors, wherein the first protective action is to be communicated to the secondary circuit board while bypassing the BMC, and
• initiate, via a communication from the BMC to a remote administrator, a second protective action based on the configurable over current protection policy, wherein the second protective action includes one or more of a data center fleet manager notification or a migration of a workload from the first processor to at least one of the other processors,
• wherein the first protective action and the second protective action are each responsive to the indication of the detected over current condition.

A method comprising:

• receiving at a primary circuit board an indication of a detected over current condition associated with a first voltage regulator on a secondary circuit board in a computing system, wherein the computing system comprises a plurality of circuit boards, each of the plurality of circuit boards including a voltage regulator and a processor coupled to the voltage regulator, wherein the plurality of circuit boards includes the primary circuit board and the secondary circuit board, the primary circuit board having a baseboard management controller (BMC), and wherein the indication is received while bypassing the BMC;
• identifying a configurable over current protection policy associated with the first voltage regulator;
• automatically taking a first protective action based on the configurable over current protection policy, wherein the first protective action includes one or more of a frequency throttle of a first processor on the secondary circuit board in isolation from one or more additional processors in the computing system, or a deactivation of the first processor in isolation from the one or more additional processors, wherein the first protective action is to be communicated to the secondary circuit board while bypassing the BMC, and
• initiating, via a communication from the BMC to a remote administrator, a second protective action based on the configurable over current protection policy, wherein the second protective action includes one or more of a data center fleet manager notification or a migration of a workload from the first processor to at least one of the other processors,
• wherein the first protective action and the second protective action are each responsive to the indication of the detected over current condition.