The disclosure relates to technology for pre-fetching data. An apparatus comprises a processor core, pre-fetch logic, and a memory hierarchy. The pre-fetch logic is configured to generate cache pre-fetch requests for a program instruction identified by a program counter. The pre-fetch logic is configured to track one or more statistics with respect to the cache pre-fetch requests. The pre-fetch logic is configured to link the one or more statistics with the program counter. The pre-fetch logic is configured to determine a degree of the cache pre-fetch requests for the program instruction based on the one or more statistics. The memory hierarchy comprises main memory and a hierarchy of caches. The memory hierarchy further comprises a memory controller configured to pre-fetch memory blocks identified in the cache pre-fetch requests from a current level in the memory hierarchy into a higher level of the memory hierarchy.

A memory device with non-volatile memory and persistent predictive prefetching provides highspeed storage to a computer system. The memory device uses a non-volatile memory to store data and a volatile memory to cache the data from the non-volatile memory. The computer system sends access requests to obtain data in the non-volatile memory. A prediction engine in the memory device receives the access requests. The prediction engine compute access histories based on the access requests and stores them in an access history table. The prediction engine computes prediction of non-volatile memory addresses that will be accessed in the future based on the stored access history table. The prediction engine causes to store the data from the predicted addresses of the non-volatile memory in the volatile memory. The memory device stores the prediction in the non-volatile memory so the past predictions can be used after restarting the computer system.

A data access system including a processor and a storage system including a main memory and a cache module. The cache module includes a FLC controller and a cache. The cache is configured as a FLC to be accessed prior to accessing the main memory. The processor is coupled to levels of cache separate from the FLC. The processor generates, in response to data required by the processor not being in the levels of cache, a physical address corresponding to a physical location in the storage system. The FLC controller generates a virtual address based on the physical address. The virtual address corresponds to a physical location within the FLC or the main memory. The cache module causes, in response to the virtual address not corresponding to the physical location within the FLC, the data required by the processor to be retrieved from the main memory.

A technique is provided for training a prediction apparatus. The apparatus has an input interface for receiving a sequence of training events indicative of program instructions, and identifier value generation circuitry for performing an identifier value generation function to generate, for a given training event received at the input interface, an identifier value for that given training event. The identifier value generation function is arranged such that the generated identifier value is dependent on at least one register referenced by a program instruction indicated by that given training event. Prediction storage is provided with a plurality of training entries, where each training entry is allocated an identifier value as generated by the identifier value generation function, and is used to maintain training data derived from training events having that allocated identifier value. Matching circuitry is then responsive to the given training event to detect whether the prediction storage has a matching training entry (i.e. an entry whose allocated identifier value matches the identifier value for the given training event). If so, it causes the training data in the matching training entry to be updated in dependence on the given training event.

A data prefetching method and apparatus, and related storage device are provided. Data samples are collected. An AI chip trains the data samples to obtain a prefetching model. The AI chip then sends the prefetching model to a processor. The processor reads to-be-read data into a cache based on the prefetching model to reduce the computing burden of the processor.

Systems and methods for determining an access pattern in a computing system. Accesses to a file may contain random accesses and sequential accesses. The file may be divided into multiple regions and the accesses to each region are tracked. The access pattern for each region can then be determined independently of the access patterns of other regions of the file.

An apparatus to facilitate data cache security is disclosed. The apparatus includes a cache memory to store data; and prefetch hardware to pre-fetch data to be stored in the cache memory, including a cache set monitor hardware to determine critical cache addresses to monitor to determine processes that retrieve data from the cache memory; and pattern monitor hardware to monitor cache access patterns to the critical cache addresses to detect potential side-channel cache attacks on the cache memory by an attacker process.

An apparatus includes a processor core and a memory hierarchy. The memory hierarchy includes main memory and one or more caches between the main memory and the processor core. A plurality of hardware pre-fetchers are coupled to the memory hierarchy and a pre-fetch control circuit is coupled to the plurality of hardware pre-fetchers. The pre-fetch control circuit is configured to compare changes in one or more cache performance metrics over two or more sampling intervals and control operation of the plurality of hardware pre-fetchers in response to a change in one or more performance metrics between at least a first sampling interval and a second sampling interval.

A memory system for accelerating graph neural network processing can include an on-host chip memory to cache data needed for processing a current root node. The system can also include a volatile memory interface between the host and non-volatile memory. The volatile memory can be configured to save one or more sets of next root nodes, neighbor nodes and corresponding attributes. The non-volatile memory can have sufficient capacity to store the entire graph data. The non-volatile memory can also be configured to pre-arrange the sets of next root nodes, neighbor nodes and corresponding attributes for storage in the volatile memory.

Aspects of the present disclosure relate to reducing the latency of data deduplication. In embodiments, an input/output (IO) workload received by a storage array is monitored. Further, at least one IO write operation in the IO workload is identified. A space-efficient probabilistic data structure is used to determine if a director board is associated with the IO write. Additionally, the IO write operation is processed based on the determination.