Abstract: In accordance with certain techniques, prefetching operation may be divided into two parts: a trigger part and an execution part, thereby simplifying the prefetching process. Such techniques may further support prefetching of concurrent flows and enhance anti-interference capability. Certain techniques involve receiving a read request for a memory page, and determining whether the read request satisfies a trigger condition of a prefetching operation for the memory page. These certain techniques further involve, in response to the read request satisfying the trigger condition, determining a window size of the prefetching operation based on historical information of historical prefetching operations for the memory page, and triggering, based on the window size, execution of the prefetching operation.

Abstract: A data processing apparatus is provided, comprising controller circuitry. The controller circuitry includes processing circuitry that executes a stream of instructions. Communication circuitry obtains a command from shared storage circuitry to cause the processing circuitry to execute a subset of instructions in the stream of instructions, and proactively transmit additional data to the shared storage circuitry.

Abstract: Methods and systems for aiding users in generating object pattern designs with increased speed. In particular, one or more embodiments train a sequence-based machine-learning model using training objects, each training object including a plurality of regions with a plurality of design elements. One or more embodiments identify a plurality regions of an object with a first region adjacent a second region. One or more embodiments receive a user selection of a design element for populating the first region with a first design element from a plurality of design elements. One or more embodiments identify a second design element from the plurality of design elements based on the first design element using the trained sequence-based machine-learning model. One or more embodiments also populate the second region with one or more instances of the second design element.

Abstract: A computer having a plurality of accounts and a storage device having a host interface, a controller, non-volatile storage media, and firmware. An account is configured with at least a predetermined speed in accessing the non-volatile storage media by allocating a number of input/output submission queues in the buffer area of the host. The number can be determined from a ratio between the predetermined speed configured for the account and a saturated speed of the storage device with sufficient submission queues. Data access requests from the account are evenly distributed to the submission queues allocated for the exclusive use by the account; and the controller, configured via the firmware, processes with equal priority the submission queues configured for the storage device. Thus, the account can have at least the predetermined speed in accessing the non-volatile storage media, regardless of how other accounts access the storage device.

Abstract: Methods that can facilitate more optimized relocation of data associated with a memory are presented. In addition to a memory controller component, a memory manager component can be employed to increase available processing resources to facilitate more optimal execution of higher level functions. Higher level functions can be delegated to the memory manager component to allow execution of these higher level operations with reduced or no load on the memory controller component resources. A uni-bus or multi-bus architecture can be employed to further optimize data relocation operations. A first bus can be utilized for data access operations including read, write, erase, refresh, or combinations thereof, among others, while a second bus can be designated for higher level operations including data compaction, error code correction, wear leveling, or combinations thereof, among others.

Abstract: Electric Grid Analytics Learning Machine, EGALM, is a machine learning based, “brutally empirical” analysis system for use in all energy operations. EGALM is applicable to all aspects of the electricity operations from power plants to homes and businesses. EGALM is a data-centric, computational learning and predictive analysis system that uses open source algorithms and unique techniques applicable to all electricity operations in the United States and other foreign countries.

Abstract: Systems and methods are disclosed herein for selecting a parameter vector from a set of parameter vectors for a neural network and generating a plurality of copies of the parameter vector. The systems and methods generate a plurality of modified parameter vectors by perturbing each copy of the parameter vector with a different perturbation seed, and determine, for each respective modified parameter vector, a respective measure of novelty. The systems and methods determine an optimal new parameter vector based on each respective measure of novelty for each respective one of the plurality of modified parameter vectors, and determine behavior characteristics of the new parameter vector. The systems and methods store the behavior characteristics of the new parameter vector in an archive.

Abstract: Memory augmented neural networks may use one or more neural encoders to transform input data into distributed representations and a memory module to store the representations with individual addresses. Memory augmented neural networks allow for few-shot learning capabilities because latent representations are persistent between training examples and gradient-based updates affect only certain memory locations via content-based lookups. When a query vector is not found in memory and the memory is full, existing memories that are positively associated with a particular representation may be identified, redundant memories may be aged, and updated memories may be generated. These updated memories retain relevant information acquired during training and reduce redundancy in the memories stored using the memory module, thereby improving the efficiency of data storage and reducing overfitting of data typically encountered with existing neural networks using memory modules.

Abstract: The subject disclosure relates to employing grouping and selection components to facilitate a grouping of failure data associated with oil and gas exploration equipment into one or more equipment failure type groups. In an example, a method comprises grouping, by a system operatively coupled to a processor, training data of a set of equipment failure data into one or more failure type groups based on one or more determined failure criteria, wherein the one or more failure type groups represent equipment failure classifications associated with energy exploration processes; and selecting, by the system, first ungrouped data from the set of equipment failure data based on a level of similarity between the first ungrouped data and the training data.

Abstract: A mass storage device for providing persistent storage. The system includes a plurality of instances of virtual flash translation layers, each associated with a namespace and configured to provide, to one or more virtual machines executing in a host connected to the mass storage device, access to read and write operations in the persistent storage.

Abstract: A method includes varying a number of clock characteristics of each a plurality of memory devices of a memory concurrently, determining a fitness of the memory for each variation of the number of clock characteristics, selecting a particular variation of the number of clock characteristics based on the determined fitness of the memory for the particular variation, changing a setting in each of the plurality of memory devices corresponding to the particular variation to generate an additional variation of the number of clock characteristics, and determining a fitness of the memory for the additional variation.

Abstract: The subject disclosure relates to employing grouping and selection components to facilitate a grouping of failure data associated with oil and gas exploration equipment into one or more equipment failure type groups. In an example, a method comprises grouping, by a system operatively coupled to a processor, training data of a set of equipment failure data into one or more failure type groups based on one or more determined failure criteria, wherein the one or more failure type groups represent equipment failure classifications associated with energy exploration processes; and selecting, by the system, first ungrouped data from the set of equipment failure data based on a level of similarity between the first ungrouped data and the training data.

Abstract: Methods, apparatus, and machine-readable mediums are described for selecting a training set from a larger data set. Samples are divided into a training set and a validation set. Each set meets one or more conditions. For each class to be modeled, multiple training sets are created. Models are trained on each of the multiple training sets. A size of samples for each class is determined based upon the trained models. A training data set that includes a number of samples based upon the determined size of samples is created.

Abstract: A method and system for improving a stochastic control problem policy, the method including a sampling device obtaining data representing sample Boltzmann machine configurations, obtaining a stochastic control problem's initialization data and initial policy; assigning representative data of initial coupler weights and node biases and the Boltzmann machine's transverse field strength to the sampling device; until a stopping criterion is met, generating a present-epoch state-action pair, amending, sampling for the present-epoch state-action pair, approximating a present-epoch state-action Q-function value, obtaining a future-epoch state-action pair through a stochastic state process including a stochastic optimization test on all state-action pairs to provide the action at the future-epoch and update the future-epoch state's policy; amending the representative data, sampling for the future-epoch state-action pair, obtaining a future-epoch state-action Q-function value, updating each weight and bias and providi

Abstract: System and method for automatic entity relationship (ER) model generation for services as software is disclosed. ER model generation by automated knowledge acquisition is disclosed, and automation of knowledge generation process is disclosed. Information extraction process is automated and multilevel validation of information extraction process is provided. System comprises training module to train information extraction model, and knowledge generation module for population of ER model. Standard Operators are generated based on the ER model so generated (populated). Context aware entity extraction is implemented for the ER model generation. System and method leverages existing ER model to make the system self-learning and intelligent, and provides common platform for knowledge generation from different data sources comprising documents, database, website, web corpus, and blog.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving data at a secondary storage volume from a primary storage volume. In response to receiving a read request: a request is sent for at least a portion of the data corresponding to the read request in response to determining that at least a portion of the data corresponding to the read request is not in any of the regions in the secondary storage volume. The at least a portion of the data corresponding to the read request is received, and further stored in one or more regions in the secondary storage volume. Furthermore, a message is sent indicating that the one or more regions in the secondary storage volume in which the data was stored contain the at least a portion of the data corresponding to the read request received, the message being for updating a primary record.

Abstract: A data backup system can be implemented in a data storage enclosure that houses a backup controller. The backup controller may be connected to a storage media and a backup media via a switch. The backup media can be resassigned from an unavailable condition to an available condition by the backup controller in response to predicted degradation in the storage media. The backup media may be connected to a root complex of the backup controller via a backup partition and selection feature.

Abstract: A data processing system includes a processor and a local storage device connected to the processor. The data processing system is operated to identify one or more downloads for downloading to the local storage device. The system determines the amount of available space within the local storage device, selects a download from the identified download(s) that is smaller than the amount of available space within the local storage device, and downloads the selected download to the data processing system. The selected download is then stored in the local storage device, whilst not marking the space occupied by the selected download as being used.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving existing data at a secondary storage volume in a secondary system from a primary storage volume in a primary system. In response to receiving a write request at the secondary system: a determination is made as to whether data corresponding to the write request will fully overwrite one or more of the regions in the secondary storage volume. A request is sent to the primary system for existing data corresponding to the secondary storage volume in response to determining that the data corresponding to the write request will not overwrite a portion of a region in the secondary storage volume. The requested existing data is received, and merged with the data corresponding to the write request. The merged data is further written to the one or more respective regions in the secondary storage volume.

Abstract: Techniques and mechanisms for providing termination for a plurality of chips of a memory device. In an embodiment, a memory device is an integrated circuit (IC) package which includes a command and address bus and a plurality of memory chips each coupled thereto. Of the plurality of memory chips, only a first memory chip is operable to selectively provide termination to the command and address bus. Of the respective on-die termination control circuits of the plurality of memory chips, only the on-die termination control circuit of the first memory chip is coupled via any termination control signal line to any input/output (I/O) contact of the IC package. In another embodiment, the plurality of memory chips are configured in a series with one another, and wherein the first memory chip is located at an end of the series.