Individual power cycle control of accelerator modules configured on a node
AssigneeMicrosoft Technology Licensing, LLC
InventorsSagar Chandrakan Pawar, Kai Li, Karunakara Kotary, Santosh Srinivas Rao Deshpande
Life of this patent
Estimating the term…
Abstract
Disclosed herein is a system for implementing a management controller on a node, or network server, that is dedicated to monitoring the individual health of a plurality of accelerator modules configured on the node. Based on the monitored health, the management controller is configured to implement autonomous power cycle control of individual accelerator modules. The autonomous power cycle control is implemented without violating the requirements of standards established for accelerator modules (e.g., OPEN COMPUTE PROJECT requirements, PERIPHERAL COMPONENT INTERCONNECT EXPRESS (PCIe) interface requirements).
Claims20
A method implemented by a management controller configured to monitor a health of an individual accelerator module of a plurality of accelerator modules configured on a node and to power cycle the individual accelerator module, the method comprising:
- receiving a first signal that identifies the individual accelerator module;
- determining that the first signal indicates an error impacting the individual accelerator module;
- in response to determining that the first signal indicates the error impacting the individual accelerator module, sending, via an I2C bus that connects the management controller and the individual accelerator module, a second signal to power cycle the individual accelerator module without power cycling other accelerator modules of the plurality of accelerator modules to a General-Purpose Input-Output expander;
- and
- instructing the General-Purpose Input-Output expander to generate and send an asynchronous power cycle signal to the individual accelerator module, and not the other accelerator modules, via a switched OR gate of a multiplexer/demultiplexer.
A baseboard management controller configured to monitor a health of an individual accelerator module of a plurality of accelerator modules configured on a node and to power cycle the individual accelerator module by performing operations comprising:
- receiving a first signal that identifies the individual accelerator module;
- determining that the first signal indicates an error impacting the individual accelerator module;
- and
- in response to determining that the first signal indicates the error impacting the individual accelerator module, sending, via a bus that connects the baseboard management controller and the individual accelerator module, a second signal to power cycle the individual accelerator module without power cycling other accelerator modules of the plurality of accelerator modules.
A method implemented by a management controller configured to monitor a health of an individual accelerator module of a plurality of accelerator modules configured on a node and to power cycle the individual accelerator module, the method comprising:
- receiving a first signal that identifies the individual accelerator module;
- determining that the first signal indicates an error impacting the individual accelerator module;
- and
- in response to determining that the first signal indicates the error impacting the individual accelerator module, sending, via a bus that connects the management controller and the individual accelerator module, a second signal to power cycle the individual accelerator module without power cycling other accelerator modules of the plurality of accelerator modules.
Dependencies are inferred from the claim text.