Abstract: Systems and methods for firmware-based orchestration of Artificial Intelligence (AI) performance profiles in heterogenous computing platforms are described. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include a heterogeneous computing platform comprising a plurality of devices and a memory having a plurality of sets of firmware instructions, where each of the sets of firmware instructions, upon execution by a respective device among the plurality of devices, enables the respective device to provide a corresponding firmware service, and where at least one of the plurality of devices operates as an orchestrator configured to: deploy or instruct another device among the plurality of devices to deploy an AI model configured to produce an inference based, at least in part, upon context or telemetry data received from a subset of the plurality of devices; and select an AI performance profile based, at least in part, upon the inference.

Abstract: Systems and methods for loading firmware onto an external embedded controller (EC) of a heterogenous computing platform. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include: a heterogeneous computing platform having a Reduced Instruction Set Computer (RISC) processor and a Peripheral Component Interconnect Express (PCIe) controller coupled thereto, and an EC external to the heterogeneous computing platform and coupled to the PCIe controller, wherein the EC is configured to retrieve at least one of: firmware instructions, a configuration setting, or a table, from a PCIe device coupled to the PCIe controller.

Abstract: Presented herein are embodiments for automatically generating a multi-fabric design. In one or more embodiments, a multi-fabric design generator system comprises a plurality of generative machine learning models that, given a graph specification for a desired multi-fabric network, generates a set of preliminary graphs. The preliminary graphs may be input into an ensemble model that comprises a reinforcement learning module, which may be trained to select the best components from the various models to create a tailored design according to specific design criteria and customer requirements or constraints. Thus, given a set of desired requirements (e.g., latency, resistance to congestion, cost, scale, bijection, etc.), the multi-fabric design generator system generates a multi-fabric design that fulfills that set of requirements; thereby providing the ability to generate customized designs for each customer based on their requirements (e.g., technical, business, and regulatory).

Abstract: An information handling system may include memory circuitry comprising a BIOS and a database including a first set of one or more cryptographic keys usable to authenticate code executable by the BIOS; and a physical storage medium other than the memory circuitry, wherein the physical storage medium includes a custom database including a second set of one or more cryptographic keys usable to authenticate code executable by the BIOS. The information handling system is configured to load a BIOS extension into the BIOS by: determining that the first set of one or more cryptographic keys does not include any key usable to authenticate the BIOS extension; determining that the second set of one or more cryptographic keys includes a particular key usable to authenticate the BIOS extension; authenticating the BIOS extension via the particular key; and in response to the authenticating, loading and executing the BIOS extension.

Abstract: A system can receive first input data indicative of first user input identifying a first diagnostic state of a computing system. The system can, based on the first input data, determine a second diagnostic state of the computing system, the second diagnostic state comprising information of the first diagnostic state. The system can present a first indication of the second diagnostic state via a user interface. The system can receive second input data indicative of second user input confirming the second diagnostic state. The system can determine a recommended action based on the second diagnostic state. The system can present a second indication of the recommended action via the user interface.

Abstract: A read-disturb-based logical storage read temperature identification system includes a global read temperature identification subsystem coupled to at least one storage device. Each at least one storage device identifies read disturb information associated with rows provided by the at least one physical block in that storage device from at least one physical block in that storage device, and maps the read disturb information associated with the rows provided by the at least one physical block in that storage device to one or more logical storage elements included in a logical-to-physical storage element mapping for that storage device to generate a local logical storage element read temperature map. Each at least one storage device may then provide its local logical storage element read temperature map to the global read temperature identification subsystem.

Abstract: A method comprises collecting parameters corresponding to processing by a first application programming interface of at least one application programming interface transaction, analyzing the parameters using one or more machine learning algorithms, and predicting, based at least in part on the analyzing, whether the at least one application programming interface transaction is anomalous. In the method, the first application programming interface is designated as being in an anomalous state responsive to predicting that the at least one application programming interface transaction is anomalous. One or more application programming interface requests for the first application programming interface are routed to a second application programming interface responsive to the anomalous state designation.

Abstract: The present disclosure enables proxied device ownership for a secondary processing system by providing a chassis housing a plurality of devices, a secondary processing system, and a central processing system that includes an integrated switch device that is coupled to each of the plurality of devices and the secondary processing system. The central processing system enter a Basic Input/Output System (BIOS) mode in which the central processing system provides a BIOS that is configured to execute instructions and, using the BIOS, receives a transaction that was generated by the secondary processing system and that is directed to a first device that is include in the plurality of devices, and executes the transaction on the first device.

Abstract: In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may determine that the staged job needs to be executed by a baseboard management controller (BMC) while an information handling system (IHS) is held in a power-on self-test; create a hybrid job associated with the staged job; reboot the IHS; launch an IHS firmware application in a pre-boot IHS firmware environment; provide, to the BMC, a command to execute a first portion of the hybrid job; obtain, by the BMC, an authentication key; provide, by the BMC, the authentication key to the non-volatile storage device; execute, by the BMC, the first portion of the hybrid job to configure the non-volatile storage device; and execute, by the IHS firmware application, the second portion of the hybrid job to poll the baseboard management controller for a result status of configuring the non-volatile storage device.

Abstract: A secure multi-Basic Input/Output System (BIOS)-image system includes a BIOS storage system having a first BIOS storage region and a second BIOS storage region. A first BIOS image is stored in the first BIOS storage region and is configured to utilize a plurality of initialization drivers during a first initialization process. A BIOS subsystem is coupled to the BIOS storage system. The BIOS subsystem receives second BIOS storage region write-enablement information and, in response, enables writing to the second BIOS storage region. Subsequent to enabling writing to the second BIOS storage region, the BIOS subsystem writes a second BIOS image to the second BIOS storage region. The BIOS subsystem may then use the second BIOS image that was written to the second BIOS storage region to perform a second initialization process that utilizes a subset of the plurality of initialization drivers.

Abstract: An information handling system includes a memory, a baseboard management controller (BMC), and a basic input/output system (BIOS). The memory stores a secure boot policy for a plurality of input/output (I/O) devices in the information handling system. The BMC performs a firmware update for a first I/O device of the I/O devices. In response to the firmware update being completed successfully, the BMC creates a system management task. During a next boot after the creation of the system management task, the BIOS detects the system management task. The BIOS calculates a new hash value for a firmware image of the firmware update. The BIOS replaces a previous hash value with the new hash value in the secure boot policy.

Abstract: An information handling system may include a processor, a management controller communicatively coupled to the processor for out-of-band management of the information handling system, and configured to determine if the information handling system is docked to a docking station, boot the information handling system from a personal image local to the information handling system if the information handling system is undocked from the docking station, and boot the information handling system from an enterprise image stored on the docking station if the information handling system is docked to the docking station.

Abstract: A device including first firmware of a first type and second firmware of a second type different from the first type. The first firmware configures the device to be installed into a first information handling system associated with the first type. The second firmware configures the device to be installed into a second information handling system associated with the second type. The device is configured to receive a firmware commit command that command includes either a first indication to commit the first firmware, or a second indication to commit the second firmware, but not both indications. The device further determines that the firmware commit command includes the first indication and locks the device to use the first firmware and not the second firmware, and determines that the firmware commit command includes the second indication and locks the device to use the second firmware and not the first firmware.

Abstract: If a critical event occurs during a boot process, an information handling system may analyze firmware associated with the critical event to determine whether the firmware is unified extensible firmware interface compliant. In response to determining that the firmware is not unified extensible firmware interface compliant, the system may retrieve a rule associated with the firmware, and apply one or more actions to the information handling system based on the rule.

Abstract: In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may receive, by a parent process of a child process, first information indicating that the child process ceased executing; determine, by an analyzer of the parent process, a reason that the child process ceased executing; determine, by the parent process, a first numerical weight associated with the reason; determine, by the parent process, that the first numerical weight is above a threshold numerical value; restart, by the parent process, execution of the child process; determine, by a loss function, a second numerical weight associated with the reason; receive, by the parent process, second information indicating that the child process has ceased executing; determine, by the analyzer, the reason that the child process ceased executing; and determine, by the parent process, that the second numerical weight is not above the threshold numerical value.

Abstract: The technology described herein is directed towards determining a datacenter's power consumption of its devices at the workload level, from which an objective carbon footprint impact score can be determined. Devices can include servers, network devices such as switches, and storage devices. For a group of workloads at a location, workload power consumption values can be determined based on collected power-related workload metrics data. The power consumption values are used in determining per-workload carbon footprint values for the workloads based on the location. One or more actions can be taken to modify the respective carbon footprint values, e.g., moving a workload to a different location, changing device hardware, and so on.

Abstract: A system and method for predicting remaining battery life for a portable information handling systems include determining power consumption for an OLED display based on an on pixel ratio (OPR) for each pixel. When a user starts a session of an application and a file, file metadata may be used to search a database storing OPR profiles, with each OPR profile including one or more time series associated with one or more instances of the application executing the file. For static files, a time series in an OPR profile may be used to predict power consumption and calculate battery life. For dynamic files, periodically measuring OPR data may be used to predict power consumption. For some dynamic files, historic OPR values and periodic measurements may be used to predict power consumption. The user may be provided with a list of files usable during the calculated battery life.

Abstract: An information handling system includes a memory and a processor coupled to the memory. The processor is configured to detect, during execution of a video game application, a gameplay event associated with the video game application. The processor is further configured to determine a mechanical resistance setting associated with an input device of a game controller and to determine one or more positions of the input device at which the mechanical resistance setting is to be applied. The mechanical resistance setting is associated with the gameplay event. The processor is further configured to send, to the game controller, a control signal indicating a configuration of the input device. The configuration is associated with the mechanical resistance setting and the one or more positions.