Described herein is a method for tracking changes to memory locations made by an application. In one embodiment, the application decides to start tracking and sends a list of virtual memory pages to be tracked to an operating system via an interface. The operating system converts the list of virtual memory pages to a list of physical addresses and sends the list of physical addresses to a hardware unit which performs the tracking by detecting write backs on a coherence interconnect coupled to the hardware unit. After the application ends tracking, the application requests a list of dirty cache lines. In response to the request, the operating system obtains the list of dirty cache lines from the hardware unit and adds the list to a buffer that the application can read. In other embodiments, the operating system can perform the tracking without the application making the request.

An information handling system may include a host system and a management controller configured to provide out-of-band management of the information handling system. The management controller may be configured to: receive, from a management console, a request to establish virtual media for the host system; cause the requested virtual media to be mounted as a drive accessible to the host system; receive read requests from the host system for data associated with the mounted drive; and cache data from the virtual media in a local cache such that at least some of the read requests from the host system are serviceable via the local cache instead of via a network request to the management console.

An accelerator and a system for accelerating operations are disclosed. A respective apparatus comprises an interface configured to couple the apparatus to an interconnect, a plurality of processing modules, each processing module configured to process data, a control module configured to control processing of each of the plurality of processing modules, and a cache module configured to store at least a portion of data processed by at least one of the plurality of processing modules. Each processing module includes a processing core configured to process data by performing an operation on the data using a plurality of processing elements, an input control unit configured to retrieve data via the interface and data stored in the cache module and to provide the retrieved data to the processing core, and an output control unit configured to provide data processed by the processing core to the interface and the cache module.

Described is a data cache with prediction hints for a cache hit. The data cache includes a plurality of cache lines, where a cache line includes a data field, a tag field, and a prediction hint field. The prediction hint field is configured to store a prediction hint which directs alternate behavior for a cache hit against the cache line. The prediction hint field is integrated with the tag field or is integrated with a way predictor field.

A memory device provides for a multiple-port read operation, and includes an array of bitcells and a control circuit. Each bitcell of the array includes a write wordline port and a first read wordline port. The control circuit provides an output to the write wordline port, and includes as inputs a write select port and a second read wordline port. In a write mode, the control circuit couples the write select port to the output and disables the second read port. In a read mode, the control circuit couples the second read wordline port to the output and disables the write select port, thereby enabling a multiple-port read operation to the array of bitcells.

Described is a data cache with prediction hints for a cache hit. The data cache includes a plurality of cache lines, where a cache line includes a data field, a tag field, and a prediction hint field. The prediction hint field is configured to store a prediction hint which directs alternate behavior for a cache hit against the cache line. The prediction hint field is integrated with the tag field or is integrated with a way predictor field.

A high bandwidth memory system. In some embodiments, the system includes: a memory stack having a plurality of memory dies and eight 128-bit channels; and a logic die, the memory dies being stacked on, and connected to, the logic die; wherein the logic die may be configured to operate a first channel of the 128-bit channels in: a first mode, in which a first 64 bits operate in pseudo-channel mode, and a second 64 bits operate as two 32-bit fine-grain channels, or a second mode, in which the first 64 bits operate as two 32-bit fine-grain channels, and the second 64 bits operate as two 32-bit fine-grain channels.

The present disclosure includes apparatuses and methods related to a memory device as the store to program instructions. An example apparatus comprises a memory device having an array of memory cells and sensing circuitry coupled to the array. The sensing circuitry includes a sense amplifier and a compute component configured to implement logical operations. A memory controller, coupled to the array and the sensing circuitry is configured to receive a block of instructions including a plurality of program instructions. The memory controller is configured to store the block of instructions in the array and retrieve program instructions to perform logical operations on the compute component.

A high bandwidth memory system. In some embodiments, the system includes: a memory stack having a plurality of memory dies and eight 128-bit channels; and a logic die, the memory dies being stacked on, and connected to, the logic die; wherein the logic die may be configured to operate a first channel of the 128-bit channels in: a first mode, in which a first 64 bits operate in pseudo-channel mode, and a second 64 bits operate as two 32-bit fine-grain channels, or a second mode, in which the first 64 bits operate as two 32-bit fine-grain channels, and the second 64 bits operate as two 32-bit fine-grain channels.

The present invention discloses a multi-core interconnection bus, including a request transceiver module adapted to receive a data request from a processor core, and forward the data request to a snoop and caching module through a request execution module, where the data request includes a request address; the snoop and caching module adapted to look up cache data validity information of the request address, acquire data from a shared cache, and sequentially return the cache data validity information and the data acquired from the shared cache to the request execution module; and the request execution module adapted to determine, based on the cache data validity information, a target processor core whose local cache stores valid data, forward the data request to the target processor core, and receive returned data; and determine response data from the data returned by the target processor core and that returned by the snoop and caching module, and return, through the request transceiver module, the response data to the processor core that initiates the data request. The present invention also discloses a corresponding inter-core communication method and a multi-core processor.