Systems, methods, and computer-readable media are disclosed for an improved database. The systems, methods, and computer-readable media described herein may enhance the response time of databases and improve user experiences. In an example method described herein, a database monitoring system may receive instructions to perform one or more data monitoring operations comprising counting an occurrence of a first value within at least a portion of items stored in a database. The method may include determining a length of a first window of time and fetching, from a first location of a data store of the database, data indicative of a total count of the occurrence of the first value at a time associated with the beginning of the first window of time. In turn, the monitoring system may store data representing the first count in the first memory.

The technology disclosed relates to streamlined analysis of security posture of a cloud environment. In particular, the disclosed technology relates to accessing permissions data and access control data for pairs of compute resources and storage resources in the cloud environment, tracing network communication paths between the pairs of the compute resources and the storage resources based on the permissions data and the access control data, accessing sensitivity classification data for objects in the storage resources, qualifying a subset of the pairs of the compute resources and the storage resources as vulnerable to breach attack based on an evaluation of the permissions data, the access control data, and the sensitivity classification data against a set risk criterion, and generating a representation of propagation of the breach attack along the network communication paths, the representation identifying relationships between the subset of the pairs of the compute resources and the storage resources.

A technique relates to flash-optimized data layout of a dataset for queries. Selection columns are stored in flash memory according to a selection optimized layout, where the selection optimized layout is configured to optimize predicate matching and data skipping. The selection optimized layout, for each selection column, is formed by storing a selection column dictionary filled with unique data values in a given selection column, where the unique data values are stored in sorted order in the selection column dictionary. Row position designations are stored corresponding to each row position that the unique data values are present within the given selection column, without duplicating storage of any of the unique data values that occur more than once in the given selection column.

Described herein is a graphics processing unit (GPU) comprising a first processing cluster to perform parallel processing operations, the parallel processing operations including a ray tracing operation and a matrix multiply operation; and a second processing cluster coupled to the first processing cluster, wherein the first processing cluster includes a floating-point unit to perform floating point operations, the floating-point unit is configured to process an instruction using a bfloat16 (BF16) format with a multiplier to multiply second and third source operands while an accumulator adds a first source operand with output from the multiplier.

Embodiments are generally directed to thread group scheduling for graphics processing. An embodiment of an apparatus includes a plurality of processors including a plurality of graphics processors to process data; a memory; and one or more caches for storage of data for the plurality of graphics processors, wherein the one or more processors are to schedule a plurality of groups of threads for processing by the plurality of graphics processors, the scheduling of the plurality of groups of threads including the plurality of processors to apply a bias for scheduling the plurality of groups of threads according to a cache locality for the one or more caches.

Embodiments of the present disclosure provide a system for accelerated data search of a database storage system. The system includes a host device including a database storage engine; and a memory system including a controller and a memory device, which includes a plurality of pages storing multiple records. The controller includes a page processing accelerator configured to: read, from the plurality of pages, multiple pages in response to a filtered read command; filter particular pages among the multiple pages based on a column full search condition, the filtered pages including entries satisfying the column full search condition; and transfer, to the host device, information regarding the filtered pages.

Systems, apparatuses and methods may provide for technology that includes a single server to store a portion of a temporal graph to a first memory of the single server, and store a second portion of the temporal graph to a second memory of the single server, wherein an access rate of the first memory is greater than an access rate of the second memory, and wherein a capacity of the second memory is greater than a capacity of the first memory. The single server may also retrieve vertices of the second portion in response to a selectivity of an input query exceeding a cost model threshold.

Described approaches provide for effectively and scalably using multiple GPUs to build and probe hash tables and materialize results of probes. Random memory accesses by the GPUs to build and/or probe a hash table may be distributed across GPUs and executed concurrently using global location identifiers. A global location identifier may be computed from data of an entry and identify a global location for an insertion and/or probe using the entry. The global location identifier may be used by a GPU to determine whether to perform an insertion or probe using an entry and/or where the insertion or probe is to be performed. To coordinate GPUs in materializing results of probing a hash table a global offset to the global output buffer may be maintained in memory accessible to each of the GPUs or the GPUs may compute global offsets using an exclusive sum of the local output buffer sizes.

A data pre-processing architecture may include an interface and a pruning logic configured to receive, via the interface, at least one filter value from a query processor; use the at least one filter value to scan rows or columns of a data table stored in a memory; generate a selection indicator identifying a set of rows or columns of the data table where the at least one filter value resides; and provide to the query processor a filtered output based on the selection indicator.

The technology disclosed relates to streamlined analysis of security posture of a cloud environment. In particular, the disclosed technology relates to a system that analyzes data posture in a cloud environment database using a snapshot of the database. A computer-implemented method includes receiving a request to access a database in the cloud environment, wherein the database includes a first authentication requirement. The method includes identifying a snapshot of the database, wherein the snapshot includes a second authentication requirement that is different than the first authentication requirement. The method includes accessing the snapshot using the second authentication requirement, generating a representation of the database using the snapshot, and generating a data posture analysis result indicative of a data posture of the database based on scanning the representation of the database.