Abstract: A data processing system includes at least one processing unit and a memory controller coupled to a system memory. The processing unit includes a processor core and a cache memory including an arithmetic logic unit (ALU). The cache memory is configured to receive, from the processor core, an atomic memory operation (AMO) request specifying a target address of a data granule to be updated by an AMO and a location indication. Based on the location indication having a first setting, the AMO indicated by the AMO request is performed in the cache memory utilizing the ALU. Based on the location indication having a different second setting, the cache memory issues the AMO request to the memory controller to cause the AMO to be performed at the memory controller.

Abstract: A multiprocessor data processing system includes a processor core having a translation structure for buffering a plurality of translation entries. In response to receipt of a translation invalidation request, the processor core determines from the translation invalidation request that the translation invalidation request does not require draining of memory referent instructions for which address translation has been performed by reference to a translation entry to be invalidated. Based on the determination, the processor core invalidates the translation entry in the translation structure and confirms completion of invalidation of the translation entry without regard to draining from the processor core of memory access requests for which address translation was performed by reference to the translation entry.

Abstract: A processor core executes a first instruction indicating a first coherence state update policy that biases the cache memory to retain write authority, thereafter executes a second instruction indicating a second coherence state update policy that biases the cache memory to transfer write authority, and executes a store instruction following the first instruction in program order to generate a store request. A cache memory stores the cache line in association with a coherence state field set to a first modified coherence state. In response to the store request, the cache memory updates data of the cache line. If the store instruction is executed prior to the second instruction, the cache memory refrains from updating the coherence state field, but if the store instruction is executed after the second instruction, the cache memory updates the coherence state field from the first modified coherence state to a second modified coherence state.

Abstract: A data processing system includes multiple processing units all having access to a shared memory. A processing unit includes a processor core that executes memory access instructions including a store-conditional instruction that generates a store-conditional request specifying a store target address and store data. The processing unit further includes a reservation register that records shared memory addresses for which the processor core has obtained reservations and a cache that services the store-conditional request by conditionally updating the shared memory with the store data based on the reservation register indicating a reservation for the store target address. The processing unit additional includes a blocking state machine configured to protect the store target address against access by any conflicting memory access request during a protection window extension following servicing of the store-conditional request.

Abstract: A cache memory stores a cache line associated with a coherence state field set to a first modified coherence state. The cache memory implements a default first coherence state update policy in which the cache memory is biased to retain write authority for the cache line. Responsive to a store request, the cache memory updates data of the cache line. If the store request indicates a change from the default first coherence state update policy, the cache memory updates the coherence state field from the first modified coherence state to a second modified coherence state in which the cache memory is biased to transfer write authority for the cache line. If the store request does not indicate a change from the default first coherence state policy, the cache memory refrains from updating the coherence state field from the first modified coherence state.

Abstract: A cache memory stores a cache line associated with a coherence state field set to a first modified coherence state. The cache memory implements a default first coherence state update policy in which the cache memory is biased to retain write authority for the cache line. Responsive to a store request, the cache memory updates data of the cache line. If the store request indicates a change from the default first coherence state update policy, the cache memory updates the coherence state field from the first modified coherence state to a second modified coherence state in which the cache memory is biased to transfer write authority for the cache line. If the store request does not indicate a change from the default first coherence state policy, the cache memory refrains from updating the coherence state field from the first modified coherence state.

Abstract: A data processing system includes a processor core and a cache memory storing a cache line associated with a coherence state field set to a first of multiple modified coherence states. The processor core executes a store instruction including a field having a setting that indicates a coherence state update policy and, based on the store instruction, generates a corresponding store request including the setting, store data, and a target address. Responsive to the store request, the cache memory updates data of the cache line utilizing the store data. The cache memory refrains from updating the coherence state field based on the setting indicating a first coherence state update policy and updates the coherence state field from the first modified coherence state to a second modified coherence state based on the setting indicating a second coherence state update policy.

Abstract: A processor core executes a first instruction indicating a first coherence state update policy that biases the cache memory to retain write authority, thereafter executes a second instruction indicating a second coherence state update policy that biases the cache memory to transfer write authority, and executes a store instruction following the first instruction in program order to generate a store request. A cache memory stores the cache line in association with a coherence state field set to a first modified coherence state. In response to the store request, the cache memory updates data of the cache line. If the store instruction is executed prior to the second instruction, the cache memory refrains from updating the coherence state field, but if the store instruction is executed after the second instruction, the cache memory updates the coherence state field from the first modified coherence state to a second modified coherence state.

Abstract: A data processing system includes a processor core and a cache memory storing a cache line associated with a coherence state field set to a first of multiple modified coherence states. The processor core executes a store instruction including a field having a setting that indicates a coherence state update policy and, based on the store instruction, generates a corresponding store request including the setting, store data, and a target address. Responsive to the store request, the cache memory updates data of the cache line utilizing the store data. The cache memory refrains from updating the coherence state field based on the setting indicating a first coherence state update policy and updates the coherence state field from the first modified coherence state to a second modified coherence state based on the setting indicating a second coherence state update policy.

Abstract: In at least some embodiments, a processor core generates a store operation by executing a store instruction in an instruction sequence. The store operation is marked as a high priority store operation in response to the store instruction being marked as high priority and is not so marked otherwise. The store operation is buffered in a store queue associated with a cache memory of the processor core. Handling of the store operation in the store queue is expedited in response to the store operation being marked as a high priority store operation and not expedited otherwise.

Abstract: A multiprocessor data processing system includes a processor core having a translation structure for buffering a plurality of translation entries. The processor core receives a sequence of a plurality of translation invalidation requests. In response to receipt of each of the plurality of translation invalidation requests, the processor core determines that each of the plurality of translation invalidation requests indicates that it does not require draining of memory referent instructions for which address translation has been performed by reference to a respective one of a plurality of translation entries to be invalidated. Based on the determination, the processor core invalidates the plurality of translation entries in the translation structure without regard to draining from the processor core of memory access requests for which address translation was performed by reference to the plurality of translation entries.

Abstract: A multiprocessor data processing system includes a processor core having a translation structure for buffering a plurality of translation entries. In response to receipt of a translation invalidation request, the processor core determines from the translation invalidation request that the translation invalidation request does not require draining of memory referent instructions for which address translation has been performed by reference to a translation entry to be invalidated. Based on the determination, the processor core invalidates the translation entry in the translation structure and confirms completion of invalidation of the translation entry without regard to draining from the processor core of memory access requests for which address translation was performed by reference to the translation entry.

Abstract: A data processing system includes multiple processing units all having access to a shared memory. A processing unit of the data processing system includes a processor core including an upper level cache, core reservation logic that records addresses in the shared memory for which the processor core has obtained reservations, and an execution unit that executes memory access instructions including a fronting load instruction. Execution of the fronting load instruction generates a load request that specifies a load target address. The processing unit further includes lower level cache that, responsive to receipt of the load request and based on the load request indicating an address match for the load target address in the core reservation logic, protects the load target address against access by any conflicting memory access request during a protection interval following servicing of the load request.

Abstract: A data processing system includes a plurality of processor cores each having a respective associated cache memory, a memory controller, and a system memory coupled to the memory controller. A zero request of a processor core among the plurality of processor cores is transmitted on an interconnect fabric of the data processing system. The zero request specifies a target address of a target memory block to be zeroed has no associated data payload. The memory controller receives the zero request on the interconnect fabric and services the zero request by zeroing in the system memory the target memory block identified by the target address, such the target memory block is zeroed without caching the zeroed target memory block in the cache memory of the processor core.

Abstract: A data processing system includes a processor core having a shared store-through upper level cache and a store-in lower level cache. The processor core executes a plurality of simultaneous hardware threads of execution including at least a first thread and a second thread, and the shared store-through upper level cache stores a first cache line accessible to both the first thread and the second thread. The processor core executes in the first thread a store instruction that generates a store request specifying a target address of a storage location corresponding to the first cache line. Based on the target address hitting in the shared store-through upper level cache, the first cache line is temporarily marked, in the shared store-through upper level cache, as private to the first thread, such that any memory access request by the second thread targeting the storage location will miss in the shared store-through upper level cache.

Abstract: Reducing translation latency within a memory management unit (MMU) using external caching structures including requesting, by the MMU on a node, page table entry (PTE) data and coherent ownership of the PTE data from a page table in memory; receiving, by the MMU, the PTE data, a source flag, and an indication that the MMU has coherent ownership of the PTE data, wherein the source flag identifies a source location of the PTE data; performing a lateral cast out to a local high-level cache on the node in response to determining that the source flag indicates that the source location of the PTE data is external to the node; and directing at least one subsequent request for the PTE data to the local high-level cache.

Abstract: A processing unit for a data processing system includes a cache memory having reservation logic and a processor core coupled to the cache memory. The processor includes an execution unit that executes instructions in a plurality of concurrent hardware threads of execution including at least first and second hardware threads. The instructions include, within the first hardware thread, a first load-reserve instruction that identifies a target address for which a reservation is requested. The processor core additionally includes a load unit that records the target address of the first load-reserve instruction and that, responsive to detecting, in the second hardware thread, a second load-reserve instruction identifying the target address recorded by the load unit, blocks the second load-reserve instruction from establishing a reservation for the target address in the reservation logic.

Abstract: A data processing system includes a plurality of processing units and a system memory coupled to a memory controller. The system memory includes a persistent memory device and a non-persistent cache interposed between the memory controller and the persistent memory device. The memory controller receives a flush request of a particular processing unit among the plurality of processing units, the flush request specifying a target address. The memory controller, responsive to the flush request, ensures flushing of a target cache line of data identified by target address from the non-persistent cache into the persistent memory device.

Abstract: A set-associative cache memory includes a plurality of ways and a plurality of congruence classes. Each of the plurality of congruence classes includes a plurality of members each belonging to a respective one of the plurality of ways. In the cache memory, a data structure records a history of an immediately previous N ways from which cache lines have been evicted. In response to receipt of a memory access request specifying a target address, a selected congruence class among a plurality of congruence classes is selected based on the target address. At least one member of the selected congruence class is removed as a candidate for selection for victimization based on the history recorded in the data structure, and a member from among the remaining members of the selected congruence class is selected. The cache memory then evicts the victim cache line cached in the selected member of the selected congruence class.

Abstract: Reducing translation latency within a memory management unit (MMU) using external caching structures including requesting, by the MMU on a node, page table entry (PTE) data and coherent ownership of the PTE data from a page table in memory; receiving, by the MMU, the PTE data, a source flag, and an indication that the MMU has coherent ownership of the PTE data, wherein the source flag identifies a source location of the PTE data; performing a lateral cast out to a local high-level cache on the node in response to determining that the source flag indicates that the source location of the PTE data is external to the node; and directing at least one subsequent request for the PTE data to the local high-level cache.