# US 2013/0159744 A1 · Adaptive recovery for parallel reactive power throttling

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2013/0159744 A1
- Document ID: US20130159744A1
- Status: Published application
- Kind: A1
- Application number: 13/706,882
- Filed: 2012-12-06
- Published: 2013-06-20
- Earliest claimed: 2011-12-15
- Assignees: International Business Machines Corporation
- Inventors: Thomas M. GOODING; Brant L. KNUDSON; Cory LAPPI; Ruth J. POOLE; Andrew T. TAUFERNER
- Web page: https://patentgrep.com/patent/US20130159744A1

## CPC

- G06F 1/3234: Power saving characterised by the action undertaken
- G06F 1/206: {comprising thermal management}
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

Power throttling may be used to conserve power and reduce heat in a parallel computing environment. Compute nodes in the parallel computing environment may be organized into groups based on, for example, whether they execute tasks of the same job or receive power from the same converter. Once one of compute nodes in the group detects that a parameter (i.e., temperature, current, power consumption, etc.) has exceeded a first threshold, power throttling on all the nodes in the group may be activated. However, before deactivating power throttling, a plurality of parameters associated with the group of compute nodes may be monitored to ensure they are all below a second threshold. If so, the power throttling for all of the compute nodes is deactivated.

## Claims

### Claim 1

A computer-implemented method of managing a parallel computing system that comprises a plurality of compute nodes, comprising:
monitoring a first parameter associated with at least one of the plurality of compute nodes, wherein the first parameter comprises at least one of: a measured temperature, a measured current, and a measured power consumption, and wherein the plurality of compute nodes in the parallel computing system are coupled for data communications;
upon determining that the first parameter reaches or exceeds a first threshold for the first parameter, transmitting a global interrupt to at least two of the plurality of compute nodes that are configured to reduce power consumption upon receiving the global interrupt, wherein the at least two compute nodes form an operational group that is a subset of the plurality of compute nodes;
after transmitting the global interrupt, determining whether second parameters respectively associated with each of the at least two compute nodes in the operational group reach or fall below a second threshold for the second parameters, wherein the second parameters comprise at least one of: a measured temperature, a measured current, and a measured power consumption; and
after all the second parameters reach or fall below the second threshold, cancelling the global interrupt for the at least two compute nodes in the operational group.

### Claim 2 (depends on 1)

The method of claim 1, wherein each of the at least two compute nodes in the operational group execute a task associated with the same job that is performed by the parallel computing system, wherein a job comprises a plurality of tasks.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first parameter is one of the second parameters.

### Claim 4 (depends on 3)

The method of claim 3, wherein the first threshold is a maximum desired value of the first parameter and wherein the second threshold corresponds to a value that is less than the maximum desired value.

### Claim 5 (depends on 1)

The method of claim 1, wherein the global interrupt is synchronized across the at least two compute nodes via a global clock signal shared between the compute nodes in the operational group such that a hardware element on each of the at least two compute nodes in the operational group idle simultaneously.

### Claim 6 (depends on 5)

The method of claim 5, wherein the hardware element is one of a processor and a memory controller.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
before transmitting the signal that cancels the global interrupt, determining that all the second parameters reach or fall below the second threshold for a plurality of readings measured at sequential times.

### Claim 8 (depends on 1)

The method of claim 1, wherein the plurality of compute nodes are distributed in a plurality of chassis, wherein each chassis is associated with a separate DC power supply.
