Abstract: Systems and methods for preferential treatment of a prioritized virtual machine during migration of a group of virtual machines from a first virtualized computing environment to a second virtualized computing environment. A data structure is allocated to store virtual machine migration task attributes that are associated with a plurality of in-process virtual machine migration tasks. As migration proceeds, the migration task attributes in the data structure are updated to reflect ongoing migration task scheduling adjustments and ongoing migration task resource allotments. A user interface or other process indicates a request to prioritize migration of a particular one of the to-be-migrated virtual machines. Based on the request, at least some of the virtual machine migration task attributes are modified to indicate a reduced scheduling priority of some of the to-be-migrated virtual machine migration tasks so as to preferentially deliver computing resources to the prioritized virtual machine migration tasks.

Abstract: In an embodiment, a system and method for supporting a seeding process with suspend and resume capabilities are described. A resumable seeding component in a data seeding module can be used to move data from a source tier to a target tier. A resumption context including a perfect hash function (PHF) and a perfect hash vector (PHV) persists a state of a seeding process at the end of each operation in the seeding process. The PHV represents data segments of the data using the PHF. The resumption context is loaded into memory upon resumption of the seeding process after it is suspended. Information in the resumable context is used to determine a last successfully completed operation, and a last copied container. The seeding process is resumed by executing an operation following the completed operation in the resumable context.

Abstract: In an embodiment, a method for validating data integrity of a seeding process is described. The seeding process for migrating data from a source tier to a target tier persists a perfect hash vector (PHV) to a disk when the seeding process is suspended for various reasons. The PHV includes bits for fingerprints for data segments corresponding to the data, and can be reloaded into memory upon resumption of the seeding process. One or more bits corresponding to fingerprints for copied data segments are reset prior to starting the copy phase in the resumed run. A checksum of the PHV is calculated after the seeding process completes copying data segments in the containers. A non-zero checksum of the PHV indicates that one or more data segments are missing on the source tier or the data segments are not successfully copied to the target tier. The missing data segments and/or one or more related files are reported to a user via a user interface.

Abstract: A semiconductor device capable of suppressing performance degradation and systems using the same are provided. The semiconductor device includes a plurality of processors CPU1 and CPU2, a scheduling device 10 (ID1) connected to the processors CPU1 and CPU2 for controlling the processors CPU1 and CPU2 to execute a plurality of tasks in real time, memories 17 and 18 accessed by the processors CPU1 and CPU2 to store data by executing the tasks, and access monitor circuits 15 for monitoring accesses to the memories by the processors CPU1 and CPU2. When an access to the memory is detected by the access monitor circuit 15, the data stored in the memory 18 is transferred based on the destination information of the data stored in the memory 18.

Abstract: A method for scheduling jobs for the calculator includes measuring core utilization of the second-type processor, when the measured core utilization is less than a reference value, transmitting, by the first-type processor, a job suspension instruction to suspend a first job, which is currently being executed, to the second-type processor, in response to the job suspension instruction, copying data of a region occupied by the first job in a memory of the second-type processor to a main memory, copying data of a second job stored in the main memory to the memory of the second-type processor, and transmitting, by the first-type processor, an instruction to execute the second job to the second-type processor.

Abstract: A micro kernel scheduling method and apparatus are disclosed in embodiments of this disclosure. The method is applied to a software platform and includes: receiving a scheduling instruction for a current micro kernel; and switching the current micro kernel to a target micro kernel. In some embodiments, a micro kernel is switched directly according to a scheduling instruction, and this is completed without any thread of the software platform, which solves the problems in the conventional system of high micro kernel switching cost and poor real-time performance caused by one-to-one correspondence between micro kernels and threads of the software platform.

Abstract: In a multitask computing system, there are multiple tasks include a first task, a second task, and a third task, and the first task has a higher priority than that of the second task and the third task. A method including raising the priority of the second task that shares a first critical section with the first task and is accessing the first critical section when the first task is blocked due to failure to access the first critical section; determining whether there is a third task that shares a second critical section with the second task and is accessing the second critical section; and raising, when the third task is present, the priority of the third task. The techniques of the present disclosure prevent a low-priority third task from delaying the execution of a second task, thus avoiding the priority inversion caused by the delayed execution of a high-priority first task.

Abstract: An apparatus comprising: a model to generate adjusted tuning parameters of a thread scheduling policy based on a tradeoff indication value of a target system; and a workload monitor to: execute a workload based on the thread scheduling policy; obtain a performance score and a power score from the target system based on execution of the workload, the performance score and the power score corresponding to a tradeoff indication value; compare the tradeoff indication value to a criterion; and based on the comparison, initiate the model to re-adjust the adjusted tuning parameters.

Abstract: Described herein is a system and method for ranking and/or taking an action regarding execution of jobs of a shared computing cluster based upon predicted user impact. Information regarding previous executions of a plurality of jobs is obtained, for example, from job execution log(s). Data dependencies of the plurality of jobs are determined. Job impact of each of the plurality of jobs as a function of the determined data dependencies is calculated. User impact of each of the plurality of jobs as a function of the determined data dependencies, the calculated job impact, and time is calculated. The plurality of jobs are ranked in accordance with the calculated user impact. An action is taken in accordance with the ranking of the plurality of jobs. The action can include automatic scheduling of the jobs and/or providing information regarding the rankings to a user.

Abstract: A semiconductor device capable of executing a plurality of tasks in real time and improving performances is provided. The semiconductor device comprises a plurality of processors and a plurality of DMA controllers as master, a plurality of memory ways as slave, and a real-time schedule unit for controlling the plurality of masters such that the plurality of tasks are executed in real time. The real-time schedule unit RTSD uses the memory access monitor circuit and the data determination register to determine whether or not the input data of the task has been determined, and causes the task determined to have the input data determined to have been determined to be executed preferentially.

Abstract: An apparatus comprising: a processing resource; a memory resource to store instructions executable by the processing resource to: associate a plurality of consumer containers with a data container, wherein the plurality of consumer containers accesses the data container; identify a node of a cloud computing system that hosts the data container; and schedule the plurality of consumer containers to execute on the node based on the association between the plurality of consumer containers and the data container.

Abstract: Some embodiments provide a program that determines a version of a first set of application resources. The program further determines whether a version of a second set of application resources is different and compatible with the version of the first set of application resources. Upon determining that the version of the second set of application resources is different and compatible with the version of the first set of application resources, the program also uses the second set of application resources to generate visualizations of data while downloading the first set of application resources for later use. Upon determining that the version of the second set of application resources is different and not compatible with the version of the second set of application resources, the program further downloads the first set of application resources and uses the first set of application resources to generate visualizations of data.

Abstract: A method of requesting data items from storage. The method comprising allocating each of a plurality of memory controllers a unique identifier and assigning memory transaction requests for accessing data items to a memory controller according to the unique identifiers. The data items are spatially local to one another in storage.

Abstract: A method for conserving resources in a distributed system includes receiving an event-criteria list from a resource controller. The event-criteria list includes one or more events watched by the resource controller and the resource controller controls at least one target resource and is configured to respond to events from the event-criteria list that occur. The method also includes determining whether the resource controller is idle. When the resource controller is idle, the method includes terminating the resource controller, determining whether any event from the event-criteria list occurs after terminating the resource controller, and, when at least one event from the event-criteria list occurs after terminating the resource controller, recreating the resource controller.

Abstract: A computing device includes a plurality of nodes, where a first node operates in accordance with a computing device operation system (OS) and remaining nodes operate in accordance with a custom OS. The remaining nodes include a plurality of sets of processing core resources that process a plurality of sets of threads of an application. The computing device also includes a main memory divided into a computing device memory section and a custom memory section that includes portions logically allocated as a plurality of buffers. The computing device also includes a memory access control module operable to coordinate access to the plurality of buffers by at least some of the plurality of sets of threads in accordance with the custom OS. The computing device also includes disk memory and a disk memory access control module operable to coordinate access to the disk memory in accordance with the computing device OS.

Abstract: A Hyper-Converged Infrastructure (HCI) ephemeral workload/data provisioning system includes a workload system coupled to a plurality of HCI systems by a manager system. The manager system identifies a first ephemeral workload that is provided by the workload system and that is configured to operate on one of the plurality of HCI systems for less than a first time period. In response to identifying the first ephemeral workload, the manager system determines first data that is to-be utilized by the first ephemeral workload and that is stored on a first HCI system that is included in the plurality of HCI systems. In response to determining that the first HCI system includes the first data that is to-be utilized by the first ephemeral workload, the manager system causes the first ephemeral workload to be provisioned on the first HCI system.

Abstract: Launch configurations of a hardware acceleration device are determined, which minimize hardware thread management overhead in running a program code. Based on received hardware behaviors, the architectural features, the thread resources and the constraints associated with the hardware acceleration device, possible launch configurations and impossible launch configurations are generated. A ranking of at least some of the possible launch configurations may be generated and output, based on how well each of said at least some of the possible launch configurations satisfies at least some of the constraints. Parametric values of said at least some of the possible launch configurations, an explanation why the impossible launch configurations have been determined as being impossible, and one or more strategies for scheduling, latencies and efficiencies associated with the hardware acceleration device, are output.

Abstract: A method comprises obtaining hardware information of a plurality of dedicated processing resources, wherein the plurality of dedicated processing resources comprises a first dedicated processing resource and a second dedicated processing resource, and the hardware information comprises first hardware information of the first dedicated processing resource and second hardware information of the second dedicated processing resource. The method further comprises generating a first task based on the first hardware information and a second task based on the second hardware information, and allocating the first task to the first dedicated processing resource and the second task to the second dedicated processing resource. For task scheduling in heterogeneous dedicated processing resources (for example, accelerator devices) scenario, the method generates corresponding kernel codes according to different hardware capabilities.

Abstract: Coordinated application processing. A method identifies processing engines available for coordinated application processing, distributes to the processing engines an application configured for execution to perform image processing, and distributes images to the processing engines.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing an independent services platform. One of the methods includes maintaining a first software platform system configured to host user-provided computing tasks in a cloud computing environment of a distributed computing system. A services platform system configured to host services in the cloud computing environment of the distributed computing system is also maintained, wherein the second services platform system is configured to provision independent service resources in the underlying cloud computing infrastructure, and launch one or more service instances of the service using the provisioned independent service resources in the underlying cloud computing infrastructure. The second services platform system is configured to receive a bind request from a user and to provide binding information to one or more computing tasks hosted by the first software platform system upon receiving the bind request.

Abstract: A multi-cloud framework is provided for microservice-based applications. An exemplary method comprises maintaining a structural state of an application comprising a plurality of microservices hosted in a plurality of distinct cloud environments. The structural state of the application is maintained over time and comprises, for each microservice, an indication of the cloud environment that hosts the respective microservice. A source code is maintained for each of the plurality of microservices of the application and deployment instructions are maintained for each of the plurality of distinct cloud environments. The plurality of microservices of the application are deployed using the structural state of the application, the source code for each of the plurality of microservices and the deployment instructions for each of the plurality of distinct cloud environments.

Abstract: Systems and methods for policy-based apportionment of input/output operations (IOPS) in computing systems. Embodiments access a policy that specifies IOPS limits. Two or more virtual machines that are associated with the policy and two or more nodes that host those virtual machines are identified. In a first allocation stage, an inter-node policy manager prescribes an initial IOPS limit to the two or more nodes. The allocation amounts sent to the nodes depend at least in part on performance capabilities of respective nodes. In a second allocation stage, for each node that had received a limit amount, that amount is apportioned to the sets of virtual machines that execute on respective host nodes. Each node of the two or more nodes invokes its own node-local IOPS monitoring. Each node reports IOPS usage data to the inter-node policy manager, which in turn adjusts the node-level IOPS apportionments based on the node-level usage.

Abstract: Methods and systems for deploying images to computing systems include predicting an environment for a plurality of processing nodes. Image deployment to the plurality of processing nodes is simulated to determine a subset of the plurality of processing nodes for deployment. One or more images is pre-loaded to the subset of the plurality of processing nodes in advance of a deployment time.

Abstract: Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a compute element and a routing element. Each compute element has memory. Each router enables communication via wavelets with at least nearest neighbors in a 2D mesh. Routing is controlled by respective virtual channel specifiers in each wavelet and routing configuration information in each router. A compute element conditionally selects for task initiation a previously received wavelet specifying a particular one of the virtual channels. The conditional selecting excludes the previously received wavelet for selection until at least block/unblock state maintained for the particular virtual channel is in an unblock state. The compute element executes block/unblock instructions to modify the block/unblock state.

Abstract: Disclosed herein are system, method, and computer program product embodiments for providing a data model API to customizable live applications in a cloud collaboration platform. The cloud collaboration platform may provide data storage, a data model, and an application programming interface to embedded third-party live applications to allow the live applications to securely create, store, and access data within the cloud collaboration platform. The data model allows records stored in the cloud collaboration platform to sync independently, merge intelligently, and function offline.

Abstract: Systems, apparatuses and methods may provide for technology that detects a tensor operation in an application, wherein the tensor operation has an unspecified tensor input size, determines the input tensor size at runtime, and selects a partition configuration for the tensor operation based at least in part on the input tensor size and one or more runtime conditions. In one example, the technology searches a lookup table for the input tensor size and at least one of the runtime condition(s) to select the partition configuration.

Abstract: Various embodiments relate generally to data science and data analysis, computer software and systems, including a subset of intermediary executable instructions constituting an communication interface between various software and/or hardware platforms, and, more specifically, to an automated application interface governance platform to automate development, maintenance, and governance functions for application interfaces, such as harmonizing, validating, and/or replicating application program interfaces (“APIs”). For example, a method may include identifying a subset of application interfaces, synthesizing a data structure for each application interface, analyzing the data structure against other data structures to identify duplicative portions among multiple data structures, substituting a reference to a location into a portion of multiple application interfaces.

Abstract: A reminder method, system, and computer program product include collecting information and an activity of a user, determining an optimum time to send the reminder to the user based on the information and the activity of the user and an optimal platform to deliver the reminder to the user based on the information and the activity of the user.

Abstract: Systems, methods, and software described herein provide enhancements for the deployment and management of converged resources across satellites, aircraft, and ground-based nodes to perform user tasks and applications. In one implementation, a system includes a first physical node that monitors sensor data to determine when the sensor data qualifies for an operation triggering event. Once the sensor data qualifies for the operation triggering event, the first physical node may generate and communicate a notification to a second physical node to initiate a new operation to support the triggering event.

Abstract: A system includes a memory buffer, a first data processor, a second data processor, and a controller. The first data processor performs a write operation to write data into the memory buffer and provides a first reference indicating a status or progress of the write operation. The controller provides a second reference indicating a buffer block in the memory buffer. The second data processor receives the first reference and the second reference, uses a threshold and the first reference to determine whether the buffer block contains enough data to be processed by the second data processor, obtains data to be processed from the buffer block using the second reference if the buffer block contains enough data to be processed, and processes the data obtained from the buffer block.

Abstract: A method for messaging in a hybrid multi-cloud computing environment may include receiving, from a multi-cloud controller, a message. The hybrid multi-cloud computing environment may include multiple cloud platforms hosted on private, on premise infrastructure as well as public, third-party infrastructure. The multi-cloud controller may send the message to control an operation of the cloud platform. In response to receiving the message from the multi-cloud controller, the message may be deposited in message queue. The cloud platform may send a request to retrieve data destined for the cloud platform. The message from the message queue may be sent to the cloud platform in response to the request. Related systems and articles of manufacture, including computer program products, are also provided.

Abstract: According to a method of transforming a message passing interface (MPI) program, an MPI function is parsed such that a computer may directly access data created by another computer through a memory when an MPI parallel program is executed on a computer system for distributed processing, a network function corresponding to the MPI function is created for network communication, and a bus line function is created for directly accessing the memory through a bus line.

Abstract: Described are methods, apparatus and computer programs for managing persistence within a data processing system such as a messaging system, database system or file system. The method for managing persistence includes a deferred evaluation (230,330,430) of at least one criterion associated with costs and/or benefits of saving to persistent storage, instead of persistence behaviour being fully predefined. The evaluation may be performed when a disk write is about to be performed (240,340,440), or at various times during processing of a data update and at various points within a data processing network. In a messaging solution, the method for managing persistence includes a dynamic evaluation (230,330,430) of costs and/or benefits of saving to persistent storage, with the evaluation being performed at various points in the messaging network after the message has been created and sent by the originating entity.

Abstract: A method may include receiving first and second application programming interface (API) specifications. The method may include comparing first and second API Specification according to a set of criteria. Responsive to the first and second criteria being identical, the method may include identifying first and second objects. Responsive to the first and second criteria being identical, the method may include classifying a type of the first and second objects and associating one or more parameters in the first and second objects with a consolidated object. The one or more parameters in the first and second objects may be associated with the consolidated object based on the type of the first and second object. The method may include generating a consolidated specification that includes the consolidated object and a description of the one or more parameters of the first and second objects that are associated with the consolidated object in a single API specification.

Abstract: An information handling system (IHS), baseboard management controller (BMC) and method are provided for preventing critical operations when power shutdown is predicted. A service processor of a BMC of the IHS executes a predicted power operation (PPO) utility to monitor health data from physical memory devices of memory of the IHS. Based on the health data, the service processor predicts that at least one of the physical memory devices will fail, causing a power shutdown of the IHS. To prevent any critical operation that is executed by a host processing subsystem of the IHS being adversely affected by the shutdown, the service processor of the BMC updates information contained in a PPO software sensor to indicate the predicted power down.

Abstract: Input on a plurality of attributes of a computing environment is provided to a machine learning module to produce an output value that comprises a risk score that indicates a likelihood of a potential malfunctioning occurring within the computing environment. A determination is made as to whether the risk score exceeds a predetermined threshold. In response to determining that the risk score exceeds a predetermined threshold, an indication is transmitted to indicate that potential malfunctioning is likely to occur within the computing environment. A modification is made to the computing environment to prevent the potential malfunctioning from occurring.

Abstract: Feedback relating to errors in memory operations on a plurality of memory cells is received by a memory sub-system. At least one processing level corresponding to a program distribution is updated based on the feedback to adjust an error measure between pages of the plurality of memory cells and to adjust a read window budget within a page of the plurality of cells. The updating of the at least one processing level is based on information for the at least one processing level that is stored in a data-structure.

Abstract: A method and system for intelligently resolving failures recurring in information technology (IT) environments. Specifically, the method and system disclosed herein may be directed to the resolution of persistently-occurring failures observed in data backup and/or data recovery operations. Further, resolution of any given persistently-occurring failure may entail the identification of zero, one, or more solutions (e.g., patches and/or other instructions) based on the analyses of failure-related information and host-related configuration information using machine learning and/or artificial intelligence paradigms. In cases where zero solutions are identified, the conventional and manual investigative route by way of support ticketing may be pursued.

Abstract: Embodiments of the present disclosure provide methods, apparatus, and computer storage media for application error diagnosis. The method of application error diagnosis may include obtaining information related to an error in an application, generating a code of the information related to the error in the application, determining a similarity between the code and at least one predetermined code, wherein the at least one predetermined code is being associated with a known software bug. The method further includes determining at least one software bug related to the error in the application by comparing the similarity with a predetermined threshold.

Abstract: Provided is an apparatus and method for diagnosing a communication fault. The apparatus includes a first slave module, a second slave module and a master module. The first slave module receives a synchronization signal through the first communication line and a first output signal through the second communication line, and transmits an input signal through the third communication line. The second slave module receives synchronization signal through the first communication line, and transmits a comparison signal to the master module through the third communication line when the second slave module receives a second output signal through the second communication line. The master module transmits the synchronization signal, the first output signal and the second output signal, and diagnose a communication fault by comparing a value of the comparison signal with a predetermined reference value or a value of the input signal.

Abstract: A method of facilitating prediction of a disk failure The method includes obtaining operation information and failure information associated with a plurality of disks, wherein the plurality of disks comprising a first set of disks indicated by the failure information as having a failure and a second set of disks indicated by the failure information as having no failure; determining validity of the failure information associated with a first set of disks based on system context information related to the storage system comprising the first set of disks; and in response to determining that the failure information associated with at least one of the first set of disks is valid, generating a machine learning model based on the operation information and the failure information associated with the first set of disks.

Abstract: Embodiments are described for operating a device management bus coupled to a remote access controller and a managed device. The remote access controller detects an inoperable state of the bus and determines a FRU (Field Replaceable Unit) memory is accessible on the managed device. A predefined reset indicator is written to the FRU memory. The managed device monitors for the reset indicator being written to a specified location in FRU memory. Upon detecting the reset indicator in FRU memory, the managed device resets a bus controller coupled to the device management bus and transmits a reset notification on the device management bus. The remote access controller may include an I2C shim that controls access to an I2C multiplexer utilized for transmitting I2C commands from a service processor and an I2C coprocessor, preventing certain inoperable bus states due to concurrent operation of the I2C multiplexer by the I2C coprocessor and the service processor.

Abstract: Among other things, embodiments of the present disclosure relate to detecting performance degradation in database systems. Other embodiments may be described and/or claimed.

Abstract: Techniques are disclosed for performing dump collection on a computing system. One technique includes detecting an error event on the computing system. After detecting the error event, a subset of hardware registers associated with the error event are determined. One or more hardware units within the computing system to capture data from are determined from a set of rules that specify an association between the one or more hardware units and the subset of hardware registers associated with the error event. Data is captured from each of the one or more hardware units.

Abstract: A computer-implemented method includes detecting that a first script has been modified to an updated script and that the first script is currently running. A data key point is selected from among a set of data key points available in the first script. At the selected data key point in the first script, a current state of the first script is saved in a storage object external from the first script, responsive to detecting that the first script has been modified. An execution point is selected in the updated script. The current state of the first script is loaded into the updated script. The updated script is run from the execution point, with the current state of the first script.

Abstract: A method and associated apparatus is disclosed for processing data by means of an error code, wherein the error code has an H-matrix with n columns and m rows, wherein the columns of the H-matrix are different, wherein component-by-component XOR sums of adjacent columns of the H-matrix are different from one another and from all columns of the H-matrix and wherein component-by-component XOR sums of nonadjacent columns of the H-matrix are different from all columns of the H-matrix and from all component-by-component XOR sums of adjacent columns of the H-matrix.

Abstract: Selective use of a software path and hardware path help to provide fine-grained T10-PI support while maintaining IO operation efficiency for single IO read/write commands transferring multiple data segments. NVMe hardware capability (i.e. the hardware path) is always utilized for CPU-intensive CRC verification. NVMe hardware capability is utilized for application tag and reference tag verification whenever possible. Software running on a computing node (i.e. the software path) is used for application tag and reference tag verification and replacement when those functions cannot be implemented by the NVMe hardware.

Abstract: The present invention concerns an anti-tearing protection system (1) for a non-volatile memory (3) comprising a first memory block (5) and a second memory block (7), the first and second memory blocks (5, 7) being arranged to store a data set comprising user data and an error detection code obtained based on the user data. The first and second memory blocks (5, 7) can be read in a first read mode for determining logic states of data elements comprised in the data set according to the first read mode. The user data in a respective memory block are considered to be correct according to the first read mode if its error detection code equals a first given value. The first and second memory blocks (5, 7) can further be read in a second read mode for determining the logic states of the data elements comprised in data set according to the second read mode.

Abstract: In one embodiment, a method includes receiving data comprising a plurality of data elements; creating a binary sequence comprising a plurality of bonus bits using a first binary sequence generator; using a first exclusive-or module to provide a XOR calculation using bits of each data element of the data with a bonus bit from the binary sequence; passing each data element along with its corresponding parity bit to an input of a data path; receiving each data element along with its corresponding parity bit at an output of the data path; creating the binary sequence using a second binary sequence generator; using a second XOR module to XOR together bits of each data element along with its corresponding parity bit and a bonus bit from the binary sequence to produce a result; and analyzing the result to determine whether an error has occurred to the data in the data path.

Abstract: A data storage device is provided. The data storage device includes a flash memory and a controller. The flash memory includes a plurality of blocks for storing data and each block includes a plurality of pages. The controller is configured to convert a host read command into a read-operation instruction to the flash memory to perform a default read operation to read page data from the flash memory. The default read operation has a default read threshold voltage. In response to a failure of the default read operation, the controller is configured to sequentially perform a read operation on the flash memory using a read threshold voltage with respect to each entry of a plurality of entries in a read-retry table, and replace the default read threshold voltage with the read threshold voltage corresponding to the read operation being successfully performed.