Abstract: An information handling system retrieves a data expiration policy in response to receiving a request from an application, and determines a data expiration value of a data type based on the data expiration policy. If the cached data is not expired based on the data expiration value, then the system collects data from a source based on the request and transmits the data with a response to the application.

Abstract: An information handling system stores telemetry data for the information handling system. A processor collects the telemetry data and determines a target application associated with the telemetry data. The processor sets a quality of service for the target application based on a context of the target application. The processor determines whether a first network path or a failover network path associated with the target application is a preferred network path. In response to the first network path being the preferred network path, the processor provides the telemetry data from the target application over the first network path. In response to the failover network path being the preferred network path, the processors failover the target application to the failover network path. The telemetry data is provided based on the quality of service.

Abstract: An information handling system that includes a processor and a memory coupled to the processor, the memory having program instructions stored thereon that upon execution cause the processor to determine a last audit date of a machine learning model, such as a language model in response to detecting a connection to an edge device. The execution of the program instructions may also cause the processor to determine whether the last audit date exceeds an audit threshold and apply an error correction code to the language model in response to a determination that the last audit date exceeds the audit threshold.

Abstract: A docking station requests first system specific information of an information handling system, in response to detecting a connection of the information handling system to the docking station. Subsequent to the connection, the docking station transmits the first system specific information from the information handling system to a cloud backend for authentication. The cloud backend compares the first system specific information received from the docking station with second system specific information received from the information handling system. The authentication is successful when the first system specific information matches the second system specific information. The docking station powers up an execution unit in response to receipt of information from the cloud backend that the authentication is successful.

Abstract: An information handling system includes a workload predictor, and a workload scheduler. The workload predictor calculates an allocation for a cost of execution of a number of operations per minute for executing an artificial intelligence workload on a first processor a second processor.

Abstract: An information handling system includes a processor and a memory coupled to the processor. The information handling system receives multiple checkpoints generated by a computing device that is executing a workload and is docked at the computing device. In response to detecting that the information handling system is undocked from the computing device, the information handling system receives a checkpoint of the checkpoints from a cloud resource. The checkpoint is transmitted by the computing device to the cloud resource and is generated subsequent to the other checkpoints. In addition, the information handling system selects another information handling system to execute the workload based on the checkpoint.

Abstract: An information handling system includes a processor, a workload profiler, and a workload scheduler. The processor is optimized to execute artificial intelligence workloads. The workload profiler provides a profile for an artificial intelligence workload. The profile provides an affinity of the artificial intelligence workload to be executed on the processor. The workload scheduler schedules the execution of the artificial intelligence workload on the processor based upon the affinity.

Abstract: A docking station includes a processor and a memory coupled to the processor. The docking station may be configured to establish a sideband connection between an information handling system and the docking station subsequent to detecting the information handling system docking at the docking station. The docking station may also execute a workload of the information handling system, subsequent to the establishment of the sideband connection. In addition, the docking station may transmit a notification to resume the workload via the sideband connection subsequent to detecting that the information handling system is undocked from the docking station while performing the executing of the workload.

Abstract: An information handling system selects a docking station to execute a workload. In response to the selection of the docking station, the information handling system configures the docking station to execute the workload using a sideband connection between the information handling system and the docking station. Subsequent to the configuration of the docking station using the sideband connection, the information handling system offloads the workload to the docking station via a primary connection between the information handling system and the docking station. Further, the information handling system receives results of the workload from the docking station via the primary connection.

Abstract: An information handling system that includes a processor and a memory coupled to the processor. The information handling system may retrieve dock information in response to detecting a connection between an information handling system and a docking station. The information handling system may also transmit a first request for a dock firmware based on the dock information of the docking station subsequent to the detecting of the connection between the information handling system and the docking station. In addition, the information handling system may transmit a second request to the docking station to read a firmware block associated with the dock firmware received in response to the first request. Further, the information handling system may generate a hash based on the firmware block received in response to the second request and verify the hash by comparing the hash with a hash value included in the dock firmware.

Abstract: A docking station requests first system specific information of an information handling system, in response to detecting a connection of the information handling system to the docking station. Subsequent to the connection, the docking station transmits the first system specific information from the information handling system to a cloud backend for authentication. The cloud backend compares the first system specific information received from the docking station with second system specific information received from the information handling system. The authentication is successful when the first system specific information matches the second system specific information. The docking station powers up an execution unit in response to receipt of information from the cloud backend that the authentication is successful.

Abstract: An information handling system that includes a processor and a memory coupled to the processor, the memory having program instructions stored thereon that upon execution cause the processor to determine a last audit date of a machine learning model, such as a language model in response to detecting a connection to an edge device. The execution of the program instructions may also cause the processor to determine whether the last audit date exceeds an audit threshold and apply an error correction code to the language model in response to a determination that the last audit date exceeds the audit threshold.

Abstract: An information handling system that includes a processor and a memory coupled to the processor. The information handling system may receive data inputs from a plurality of computing monitors. The information handling system may also generate a heat map based on the data inputs from the computing monitors, and the heat map is generated according to a first element and a second element. In addition, the information handling system may determine whether to route execution of a workload within an information handling system or to an external computing device based on the heat map as indicated by a value at an intersection of the first element and the second element. Further, the information handling system may also route the execution of the workload to either within the information handling system or the external computing device according to the value at the intersection.

Abstract: An information handling system includes a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution may cause the information handling system to determine whether to offload an artificial intelligence workload to another information handling system. The information handling system may also be configured to determine whether the other information handling system is associated with a workspace reservation, in response to a determination to offload the artificial intelligence workload to the other information handling system. In addition, the information handling system may be configured to offload the artificial intelligence workload to the other information handling system, in response to a determination that the other information handling system is associated with the workspace reservation.

Abstract: An information handling system includes an embedded controller that communicates with multiple components. The embedded controller receives complete collection rules for a collection of data associated with the components of the information handling system. The embedded controller begins an execution of a telemetry service. During the execution of the telemetry service, the embedded controller collects data associated with the components based on the complete collection rules. The embedded controller provides the collected data to a requesting component.

Abstract: An information handling system, comprising a memory and a processor to communicate with the memory. The processor is configured to determine whether a current boot process of the information handling system is a first boot process. If the current boot process is the first boot process, then determine whether a record in an SPI image is to be updated based on a lookup table. The processor is also configured to update the record in the SPI image based on data included in the lookup table. Subsequent to the update of the record, the processor is configured to proceed with execution of the current boot process of the information handling system.

Abstract: An information handling system determines a data collection frequency according to a data collection policy, wherein the data collection frequency is based on a data type of the data to be collected and a data collection interface. The system collects the data according to the data collection frequency associated with the data type of the data and the data collection interface, and transmits the data to a requesting information handling system.

Abstract: A remote compute device stores a first workgroup table. The first workgroup table identifies similarly profiled information handling systems for a first workgroup. A processor receives a telemetry data request from an application and determines a plurality of data sets within the telemetry data request. The processor determines a distribution of the data sets among the similarly profiled information handling systems of the first workgroup. The processor provides a different data set to a different information handling system of the first similarly profiled information handling systems. The processor receives collected data from each of the first similarly profiled information handling systems of the first workgroup and combines the collected data into complete collected data set. The processor provides the complete collected data set to the application.

Abstract: An information handling system includes a cooling device, a cooling device controller, and a cooling level estimator. The cooling device cools the information handling system. The cooling device controller controls a level of cooling for the information handling system based on a cooling profile provided by a cooling table. The cooling level estimator determines status information for the information handling system, and provides a quality of service (QOS) level indication to the cooling device controller. The cooling device controller modifies the cooling profile based on the QoS level indication.

Abstract: An information handling system generates a data tolerance policy with a data tolerance value for a data type. If a data collection request meets a set of criteria that includes whether a number of active data collection policies exceeds a threshold, then the system modifies the data tolerance value of the data type in the data tolerance policy. The system instruments data according to a modified data tolerance value, the data collection request, and the data tolerance policy.