Various embodiments described herein provide for a memory sub-system read operation or a memory sub-system write operation that can be requested by a host system and involves performing a multi-level (e.g., two-level) pointer dereferencing internally within the memory sub-system. Such embodiments can at least reduce the number of read operations that a host system sends to a memory sub-system to perform a multi-level dereferencing operation.

Various embodiments described herein provide for a memory sub-system read operation or a memory sub-system write operation that can be requested by a host system and involves performing a multi-level (e.g., two-level) pointer dereferencing internally within the memory sub-system. Such embodiments can at least reduce the number of read operations that a host system sends to a memory sub-system to perform a multi-level dereferencing operation.

Described herein are systems and methods for prime and probe attack mitigation. For example, some methods include, responsive to a cache miss caused by a process, checking whether a priority level of the process satisfies a first priority requirement of a first cache block of a cache with multiple ways including cache blocks associated with respective priority requirements; responsive to the priority level satisfying the first priority requirement, loading the first cache block; and, responsive to the priority level satisfying the first priority requirement, updating the first priority requirement to be equal to the priority level of the process.

Described herein are systems and methods for prime and probe attack mitigation. For example, some methods include, responsive to a cache miss caused by a process, checking whether a priority level of the process satisfies a first priority requirement of a first cache block of a cache with multiple ways including cache blocks associated with respective priority requirements; responsive to the priority level satisfying the first priority requirement, loading the first cache block; and, responsive to the priority level satisfying the first priority requirement, updating the first priority requirement to be equal to the priority level of the process.

A method of processing a workload in a graphics processing unit (GPU) may include detecting a work item of the workload in the GPU, determining a cache policy for the work item, and operating at least a portion of a cache memory hierarchy in the GPU for at least a portion of the work item based on the cache policy. The work item may be detected based on information received from an application and/or monitoring one or more performance counters by a driver and/or hardware detection logic. The method may further include monitoring one or more performance counters, wherein the cache policy for the work item may be determined and/or changed based on the one or more performance counters. The cache policy for the work item may be selected based on a runtime learning model.

A method of processing a workload in a graphics processing unit (GPU) may include detecting a work item of the workload in the GPU, determining a cache policy for the work item, and operating at least a portion of a cache memory hierarchy in the GPU for at least a portion of the work item based on the cache policy. The work item may be detected based on information received from an application and/or monitoring one or more performance counters by a driver and/or hardware detection logic. The method may further include monitoring one or more performance counters, wherein the cache policy for the work item may be determined and/or changed based on the one or more performance counters. The cache policy for the work item may be selected based on a runtime learning model.

Exemplary methods, apparatuses, and systems include receiving a read operation directed to an aggressor location. An integrity scan of a victim location of the aggressor location is performed to determine an error value for the victim location. Data from the aggressor location is copied to a cache in response to determining the error value for the victim location satisfies a first error value threshold. The cache is a different type of memory from the aggressor location.

Exemplary methods, apparatuses, and systems include receiving a read operation directed to an aggressor location. An integrity scan of a victim location of the aggressor location is performed to determine an error value for the victim location. Data from the aggressor location is copied to a cache in response to determining the error value for the victim location satisfies a first error value threshold. The cache is a different type of memory from the aggressor location.

Systems, devices and methods are provided for operating a skewed-associative cache in a data processing system and, in particular, for changing address-to-row mappings in a skewed-associative cache.

Systems, devices and methods are provided for operating a skewed-associative cache in a data processing system and, in particular, for changing address-to-row mappings in a skewed-associative cache.