Abstract: Processing elements include interfaces that allow direct access to memory banks on one or more DRAMs in an integrated circuit stack. These additional (e.g., per processing element) direct interfaces may allow the processing elements to have direct access to the data in the DRAM stack. Based on the size/type of operands being processed, and the memory bandwidth of the direct interfaces, rate calculation circuitry on the processor die determines the speed each processing element and/or processing nodes within each processing element are operated.

Abstract: Described are self-learning systems and methods for adaptive management of memory resources within a memory hierarchy. Memory allocations associated with different active functions are organized into blocks for placement in alternative levels in a memory hierarchy optimized for different metrics of e.g. cost and performance. A host processor monitors a performance metric of the active functions, such as the number of instructions per clock cycle, and reorganizes the function-specific blocks among the levels of the hierarchy. Over time, this process tends toward block organizations that improve the performance metric.

Abstract: Processing elements include interfaces that allow direct access to memory banks on one or more DRAMs in an integrated circuit stack. These additional (e.g., per processing element) direct interfaces may allow the processing elements to have direct access to the data in the DRAM stack. Based on the size/type of operands being processed, and the memory bandwidth of the direct interfaces, rate calculation circuitry on the processor die determines the speed each processing element and/or processing nodes within each processing element are operated.

Abstract: The embodiments described herein describe technologies for non-volatile memory persistence in a multi-tiered memory system including two or more memory technologies for volatile memory and non-volatile memory.

Abstract: Described are self-learning systems and methods for adaptive management of memory resources within a memory hierarchy. Memory allocations associated with different active functions are organized into blocks for placement in alternative levels in a memory hierarchy optimized for different metrics of e.g. cost and performance. A host processor monitors a performance metric of the active functions, such as the number of instructions per clock cycle, and reorganizes the function-specific blocks among the levels of the hierarchy. Over time, this process tends toward block organizations that improve the performance metric.

Abstract: A memory address and a virtual cache identifier are received in association with a request to retrieve data from a cache data array. Context information is selected based on the virtual cache identifier, the context information indicating a first region of a plurality of regions within the cache data array. A cache line address that includes a first number of bits of the memory address in accordance with a size of the first region is generated and, if the cache data array is determined to contain, in a location indicated by the cache line address, a cache line corresponding to the memory address, the cache line is retrieved from the location indicated by the cache line address.

Abstract: Systems, devices, and methods are disclosed for leveling wear on memory. Such systems, methods, and devices include the memory, one or more wear leveling engines and one or more wear leveling policies, a were leveling mechanism comprising one of the wear leveling engines and one of the wear leveling policies. Further embodiments may include a decision engine having a write traffic signature mechanism wherein the decision engine selects a wear leveling engine and wear leveling policy based upon receiving a write traffic signature of the memory from the write traffic signature mechanism and receiving status data from the memory.