In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

A method for protecting a reconfigurable digital integrated circuit includes multiple parallel processing channels each comprising an instance of a functional logic block and an error detection unit, the method comprising the successive steps of: activating the error detection unit in order to detect an error in at least one processing channel, executing the data replay mechanism, and then activating the error detection unit in order to detect an error in at least one processing channel, if an error is detected again, executing a self-test on each processing channel, for each processing channel, if the self-test does not detect any error, executing the data replay mechanism for this processing channel, if the self-test detects an error, reconfiguring that part of the configuration memory associated with this processing channel.

In some examples, a system receives first measurements of data items used by a build server in building an executable program, the data items copied from a data repository to a storage partition that is separate from the data repository, and the storage partition to store the data items relating to building the executable program by the build server. The system determines, based on the first measurements and according to a policy specified for the storage partition, whether a corruption of the data items used by the build server in building the executable program has occurred.

A method for facilitating data synchronization across a plurality of platforms is provided. The method includes retrieving a change event, the change event corresponding to an event stream from a first platform; parsing the change event to identify a record and a data operation; examining a synchronization database to determine whether a corresponding record is persisted in a database of a second platform; inserting the record into the synchronization database when the corresponding record is not persisted in the platform, the inserted record including a change indicator; and updating, by using the synchronization database, the database of the second platform to include the record.

In one embodiment, a system for managing a virtualization environment includes a set of host machines, each of which includes a hypervisor, virtual machines, and a virtual machine controller, and a data migration system configured to identify one or more existing storage items stored at one or more existing File Server Virtual Machines (FSVMs) of an existing virtualized file server (VFS). For each of the existing storage items, the data migration system is configured to identify a new FSVMs of a new VFS based on the existing FSVM, send a representation of the storage item from the existing FSVM to the new FSVM, such that representations of storage items are sent between different pairs of FSVMs in parallel, and store a new storage item at the new FSVM, such that the new storage item is based on the representation of the existing storage item received by the new FSVM.

Techniques are provided for storing a row address of a defective row of memory cells to a bank of non-volatile storage elements (e.g., fuses or anti-fuses). After a memory device has been packaged, one or more rows of memory cells may become defective. In order to repair (e.g., replace) the rows, a post-package repair (PPR) operation may occur to replace the defective row with a redundant row of the memory array. To replace the defective row with a redundant row, an address of the defective row may be stored (e.g., mapped) to an available bank of non-volatile storage elements that is associated with a redundant row. Based on the bank of non-volatile storage elements the address of the defective row, subsequent access operations may utilize the redundant row and not the defective row.

To be able to support the efficient handling of problems during maintenance. A management board determines an accomplishment sequence of handling manipulation for failures on a maintenance target. The management board includes a CPU, memory, and a storage device. The memory or the storage device stores: condition information associating the handling manipulation with a condition concerning at least accomplishment or non-accomplishment of the manipulation; and failure handling information that associates a failure occurring on the maintenance target with the handling manipulation. The CPU is configured to determine the accomplishment sequence of the handling manipulations so that multiple handling manipulations for multiple failures occurring on the maintenance target satisfy the condition.

To improve the reliability of nodes that are utilized by a cloud computing provider, information about the entire lifecycle of nodes can be collected and used to predict when nodes are likely to experience failures based at least in part on early lifecycle errors. In one aspect, a plurality of failure issues experienced by a plurality of production nodes in a cloud computing system during a pre-production phase can be identified. A subset of the plurality of failure issues can be selected based at least in part on correlation with service outages for the plurality of production nodes during a production phase. A comparison can be performed between the subset of the plurality of failure issues and a set of failure issues experienced by a pre-production node during the pre-production phase. A risk score for the pre-production node can be calculated based at least in part on the comparison.

Requests are received for handling by a cloud computing environment which are then executed by the cloud computing environment. While each request is executing, performance metrics associated with the request are monitored. A vector is subsequently generated that encapsulates information associated with the request including the text within the request and the corresponding monitored performance metrics. Each request is then assigned (after it has been executed) to either a normal request cluster or an abnormal request cluster based on which cluster has a nearest mean relative to the corresponding vector. In addition, data can be provided that characterizes requests assigned to the abnormal request cluster. Related apparatus, systems, techniques and articles are also described.

Methods, systems, and devices for reporting control information errors are described. A state of a memory array may be monitored during operation. After detecting an error (e.g., in received control information), the memory device may enter a first state (e.g., a locked state) and may indicate to a host device that an error was detected, the state of the memory array before the error was detected, and/or at least a portion of a control signal carrying the received control information. The host device may diagnose a cause of the error based on receiving the indication of the error and/or the copy of the control signal. After identifying and/or resolving the cause of the error, the host device may transmit one or more commands (e.g., unlocking the memory device and returning the memory array to the original state) based on receiving the original state from the memory device.