Abstract: Embodiments of the present technology provide non-volatile memory devices comprising memory dies that natively generate “exclusive OR (XOR) data pages” that can be used to recover data pages corrupted by UECC errors. Through memory die native-XOR data page generation, embodiments can recover data pages corrupted by UECC errors more efficiently, more rapidly, and with fewer resources than potential alternative technologies.

Abstract: Systems and methods for using digital triplets to generate a bundle of remediation scripts for healing a system failure is provided. The systems may include a stand-alone embedded internet of things edge artificial intelligence computing device (“EIEAC”) coupled to a computing device and a remote emulator. The EIEAC may send to the remote emulator a file including configuration details of the computing device at a time of a failure of the computing device and computer health data. The remote emulator may feed the file to a machine learning algorithm to generate remedial scripts for healing the system failure. The remote emulator may create a plurality of digital triplets to test the remedial scripts.

Abstract: A fault-tolerant computer system includes a plurality of redundant processor cores configured to simultaneously execute identical sets of processor-executable instructions, and a coprocessor component including a data storage component and a configurable logic region, where the plurality of processor cores are configured with processor-executable instructions to perform operations including configuring the configurable logic region of the coprocessor component with a first coprocessing module, and controlling the first coprocessing module to perform first processing operations on data located in the data storage component. In various embodiments, the redundant processor cores and the coprocessor component may be implemented on an FPGA, and the redundant processor cores may be configured to swap out different coprocessing modules using Partial Reconfiguration (PR) to perform data processing algorithms using hardware acceleration.

Abstract: Aspects of the disclosure provides various systems, apparatuses, and techniques for reducing latencies and power consumption of link training or retraining. In some aspects, the techniques use a specific register to identify the cause of link retraining. Based on the identified reasons of link retraining, the apparatus can selectively skip the initialization of certain redundant lanes of the link. In some aspects, the Universal Chiplet Interconnect Express (UCIe) Link Training and Status State Machine (LTSSM) can be configured to identify whether link retraining is initiated as part of a trainerror or linkerror exit or not. A UCIe device can have a redundant_recovery (RR) register that can be set to different values to identify the cause of link retraining (e.g., due to trainerror/linkerror or not).

Abstract: Aspects of the present disclosure provide a monitoring algorithm that ensures that each step of an automated virtual machine reclamation process executes correctly before moving on to the next step. After each step of the process, some implementations can determine whether the resulting data is correct. If the resulting data is incorrect, some implementations can initially revert any fields updated by the process to their correct value. Some implementations can further decide whether to resubmit the virtual machine for reclamation automatically, or queue it for manual review based on, for example, multiple or repeated failures, server or data center failures, etc. Thus, some implementations can not only automate each step of the reclamation process, but also provide process evaluation and error detection for the reclamation process.

Abstract: A direct-attached storage device software Redundant Array of Independent Disk (RAID) crash dump system includes a chassis housing a software RAID subsystem coupled to each of a plurality of physical storage devices, each of a plurality of controller devices, and an operating system. While in a runtime mode, the software RAID subsystem presents the operating system with a primary controller device from the plurality of controller devices as being connected to a logical storage device provided by the plurality of physical storage devices. In response to entering a crash dump mode from the runtime mode, the software RAID subsystem provides a storage driver subsystem for the primary controller device and uses it to initialize at least one secondary controller device in the plurality of controller devices that controls at least one of the plurality of physical storage devices that provides a boot logical storage subsystem in the logical storage device.

Abstract: A method for protecting a lock data structure, the method includes obtaining, by a compute entity of a storage system, a lock recovery indication and a cycle counter; executing, by the compute entity, at least a part of the current lock recovery process, wherein the executing of the at least part of the current lock recovery process includes (i) determining, by the compute entity, using a compute entity data structure that is indicative of lock fields that represent locks acquired by the compute entity, whether the segment comprised a compute-entity-relevant lock field, wherein the compute-entity-relevant lock field (a) belonged to the segment upon the occurrence of the failure and (b) represents a lock was acquired by the compute entity; and (ii) re-acquiring, by the compute entity, a re-acquired lock that corresponds to the compute-entity-relevant lock field, when it is determined that the segment comprised the compute-entity-relevant lock field.

Abstract: In some embodiments, the present disclosure provides an exemplary method that may include steps of identifying at least one computing specification image within a plurality of computing specification images; monitoring each data agent within the plurality of preinstalled data agents for a predetermined period of time to establish a data agent usage baseline associated with each data agent within the plurality of preinstalled data agents; utilizing a chaos engineering algorithm to dynamically perturb each data agent; calculating a usage test score for each data agent within the plurality of preinstalled data agents; calculating an overall data agent-specific usage score associated with each data agent within the plurality of preinstalled data agents based on the plurality of data agent-specific usage test scores; and rejecting at least one data agent within the plurality of preinstalled data agents from being utilized to launch the instance of the software application.

Abstract: In an embodiment, an apparatus includes: a gearbox including: a housing having an opening; an input pinion disposed in the housing; a moving feature mechanically coupled to the input pinion, the moving feature and the input pinion being operable to convert between power and torque; and first sensors disposed on the moving feature, the first sensors having batteries, where the moving feature is operable to rotate about a common axis, each of the first sensors being exposed by the opening as the moving feature rotates about the common axis.

Abstract: A method of constructing a patient-specific orthopedic implant comprising: (a) comparing a patient-specific abnormal bone model, derived from an actual anatomy of a patient's abnormal bone, with a reconstructed patient-specific bone model, also derived from the anatomy of the patient's bone, where the reconstructed patient-specific bone model reflects a normalized anatomy of the patient's bone, and where the patient-specific abnormal bone model reflects an actual anatomy of the patient's bone including at least one of a partial bone, a deformed bone, and a shattered bone, wherein the patient-specific abnormal bone model comprises at least one of a patient-specific abnormal point cloud and a patient-specific abnormal bone surface model, and wherein the reconstructed patient-specific bone model comprises at least one of a reconstructed patient-specific point cloud and a reconstructed patient-specific bone surface model; (b) optimizing one or more parameters for a patient-specific orthopedic implant to be mounte

Abstract: A battery management system includes: a plurality of slave controllers configured to be respectively connected with a plurality of battery modules to generate battery sensing information related to the respective battery modules; and a master controller connected with an uppermost slave controller from among the slave controllers, wherein each of the slave controllers includes a first receiver and a first transmitter configured to communicate with a preceding slave controller or the master controller and a second receiver and a second transmitter configured to communicate with a following slave controller, and each of the slave controllers is configured to connect the first receiver with the first transmitter or the second receiver with the second transmitter depending on types of diagnosis packets inputted through the first receiver.

Abstract: A mobile device includes a wireless transceiver operative to establish a wireless connection with a connected device. The connected device may be either a peer-to-peer device or an access point. The mobile device also includes a battery monitor and a processor, operatively coupled to the wireless transceiver and to the battery monitor. The processor is operative to obtain a charge level from the battery monitor, and negotiate with a connected device for a transceiver power output level based on the charge level. The processor is also operative to control the wireless transceiver to reduce the wireless transceiver power output to the negotiated transceiver power output level in response to an acknowledgement message from the connected device.

Abstract: A method, computer program product, and a computer system, to store information related to changed data in response to a transaction with a first database of the on-line system requested during a planned period and data in the first database changed by the transaction. In response to a planned event a back-up system with a second database is switched to set up a new connection and a new transaction with the second database, wherein the second database is backup of the first database. The on-line system prevents setting up a new connection to the on-line system and prevents conducting a new transaction with the first database, sends information related to the changed data from the on-line system to the back-up system, and switches to the back-up system for a new connection and for a new transaction. The on-line system synchronizes data between the first database and the second database.

Abstract: A client computing system detects when a problem is encountered with an application and identified problem-specific diagnostic data that is to be collected, given the detected problem. It also identifies one or more problem-specific test or diagnostic analyzers and executes those analyzers to generate additional data. The data that is collected and the data that is generated by the analyzers is packaged and sent to a service computing system for identifying a remedial action that can be performed to address the problem. The remedial action is received and surfaced for the user.

Abstract: Systems and methods are disclosed for debug session management. For example, methods may include receiving a request from a client device and, in response, identifying a set of instructions to be executed, wherein the set of instructions is associated with at least one breakpoint. The methods may include initiating execution of the set of instructions. The methods may include determining, based on a marker, that pausing execution of the set of instructions using a data structure is permitted, and responsive to this determination: pausing execution of the set of instructions before executing an instruction associated with a breakpoint, and updating the marker to indicate that execution of the set of instructions has paused using the data structure.

Abstract: A mechanism is provided in a data processing system for data integrity and acceleration in compressed storage environments in combination with software defined native redundant array of independent disks (RAID). The mechanism receives a data portion to write to storage and divides the data portion into a plurality of chunks. The mechanism performs real-time compression on a given chunk within the plurality of chunks and determines a compression rate for the given chunk. The mechanism determines a RAID level for the given chunk based on a value of the compression rate and stores the given chunk based on the determined RAID level.

Abstract: A method and an apparatus for disconnecting a link between a Peripheral Component Interconnect Express (PCIe) device and a host, and pertains to the field of computer technologies. The PCIe device includes an endpoint (EP) device, and the method includes: obtaining, by the EP device, an error type of an error in transmitting a transaction layer packet (TLP) between the PCIe device and the host; if the error type is a correctable error type specified in the PCIe protocol, collecting, by the EP device, statistics of a duration for which the error type exists; and disconnecting, by the EP device, a link between the PCIe device and the host if the statistics of the duration reaches a preset duration. The apparatus includes an obtaining module, a statistics collection module, and a disconnection module.

Abstract: A continuous anomaly detection service receives data stream and performs continuous anomaly detection on the incoming data streams. This continuous anomaly detection is performed based on anomaly detection definitions, which define a signal used for anomaly detection and an anomaly detection configuration. These anomaly detection definitions can be modified, such that continuous anomaly detection continues to be performed for the data stream and the signal, based on the new anomaly detection definition.

Abstract: A method, computer program product, and a computer system, to store information related to changed data in response to a transaction with a first database of the on-line system requested during a planned period and data in the first database changed by the transaction. In response to a planned event a back-up system with a second database is switched to set up a new connection and a new transaction with the second database, wherein the second database is backup of the first database. The on-line system prevents setting up a new connection to the on-line system and prevents conducting a new transaction with the first database, sends information related to the changed data from the on-line system to the back-up system, and switches to the back-up system for a new connection and for a new transaction. The on-line system synchronizes data between the first database and the second database.

Abstract: Examples disclosed herein relate to a baseboard management controller (BMC) capable of execution while a computing device is powered to an auxiliary state. The BMC is to process an error log according to a deep learning model to determine one of multiple field replaceable units to deconfigure in response to the error condition. The BMC is to deconfigure the field replaceable unit. The computing device is rebooted. In response to the reboot of the computing device the BMC is to determine whether the error condition persists.