A processor sets the size of a processor cache based on an identified workload executing at the processor. The cache size is set in response to the processor exiting a low-power mode. By setting the size of the cache based on the workload, the processor is able to tailor the size of the cache to the characteristics of a particular workload while also reducing, for at least some workloads, the overhead associated with entering or exiting the low-power mode.

Data units are stored in private caches in nodes of a multiprocessor system, each node containing at least one processor (CPU), at least one cache private to the node and at least one cache location buffer (CLB) private to the node. In each CLB location information values are stored, each location information value indicating a location associated with a respective data unit, wherein each location information value stored in a given CLB indicates the location to be either a location within the private cache disposed in the same node as the given CLB, to be a location in one of the other nodes, or to be a location in a main memory. Coherence of values of the data units is maintained using a cache coherence protocol. The location information values stored in the CLBs are updated by the cache coherence protocol in accordance with movements of their respective data units.

Integrated circuits (ICs) employ subsystem shared cache memory for facilitating extension of low-power island (LPI) memory. An LPI subsystem and primary subsystems access a memory subsystem on a first access interface in a first power mode and the LPI subsystem accesses the memory subsystem by a second access interface in the low power mode. In the first power mode, the primary subsystems and the LPI subsystem may send a subsystem memory access request including a virtual memory address to a subsystem memory interface of the memory subsystem to access either data stored in an external memory or a version of the data stored in a shared memory circuit. In the low-power mode, the LPI subsystem sends an LPI memory access request including a direct memory address to an LPI memory interface of the memory subsystem to access the shared memory circuit to extend the LPI memory.

Various embodiments include methods and devices for cache memory power control. Some embodiments may include determining whether a processor is entering a lowest power mode of the processor, and switching a lowest power mode switch control signal to indicate to a cache power switch of the processor switching an electrical connection of a cache memory from a memory power rail to a processor power rail in response to determining that the processor is entering a lowest power mode.

An example device includes a plurality of computational memory banks. Each computational memory bank of the plurality of computational memory banks includes an array of memory units and a plurality of processing elements connected to the array of memory units. The device further includes a plurality of single instruction, multiple data (SIMD) controllers. Each SIMD controller of the plurality of SIMD controllers is contained within at least one computational memory bank of the plurality of computational memory banks. Each SIMD controller is to provide instructions to the at least one computational memory bank.

In general, embodiments of the invention relate tracking the operating temperature of the solid-state memory modules (SSMMs) in order to improve their performance.

Devices and techniques for communicating a programmable atomic operator to a memory controller are described herein. A memory controller can receive a memory request and extract a command indicator that indicates a programmable atomic operator (PAO) command from the memory request. The memory controller can then extract a PAO index from the request and invoke the PAO based on the PAO index.

Techniques are disclosed relating to compression of data stored at different cache levels. In some embodiments, a memory system implements a storage hierarchy that includes first cache circuitry and second cache circuitry at different levels of the hierarchy. Processor circuitry generates write data to be written to the memory system. In some embodiments, first compression circuitry is configured to compress a first block of write data in response to full accumulation of the first block in the first cache circuitry and second compression circuitry is configured to compress a second block of write data in response to full accumulation of the second block in the second cache circuitry. Write circuitry may write the first and second compressed blocks of data in a single combined write to a higher level in the storage hierarchy.

A data fabric routes requests between the plurality of requestors and the plurality of responders. The data fabric includes a crossbar router, a coherent slave controller coupled to the crossbar router, and a probe filter coupled to the coherent slave controller and tracking the state of cached lines of memory. Power state control circuitry operates, responsive to detecting any of a plurality of designated conditions, to cause the probe filter to enter a retention low power state in which a clock signal to the probe filter is gated while power is maintained to the probe filter. Entering the retention low power state is performed when all in-process probe filter lookups are complete.

A cache subsystem is disclosed. The cache subsystem includes a cache configured to store information in cache lines arranged in a plurality of ways. A requestor circuit generates a request to access a particular cache line in the cache. A prediction circuit is configured to generate a prediction of which of the ways includes the particular cache line. A comparison circuit verifies the prediction by comparing a particular address tag associated with the particular cache line to a cache tag corresponding to a predicted one of the ways. Responsive to determining that the prediction was correct, a confirmation indication is stored indicating the correct prediction. For a subsequent request for the particular cache line, the cache is configured to forego a verification of the prediction that the particular cache line is included in the one of the ways based on the confirmation indication.