Ensuring the appropriate utilization of system resources using weighted workload based, time-independent scheduling, including: receiving an I/O request associated with an entity; determining whether an amount of system resources required to service the I/O request is greater than an amount of available system resources in a storage system; responsive to determining that the amount of system resources required to service the I/O request is greater than the amount of available system resources in the storage system: queueing the I/O request in an entity-specific queue for the entity; detecting that additional system resources in the storage system have become available; and issuing an I/O request from an entity-specific queue for an entity that has a highest priority, where a priority for each entity is determined based on the amount of I/O requests associated with the entity and a weighted proportion of resources designated for use by the entity.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing data on a memory controller. One of the methods comprises obtaining a first request and a second request to access respective data corresponding to the first and second requests at a first memory device of the plurality of memory devices; and initiating interleaved processing of the respective data; receiving an indication to stop processing requests to access data at the first memory device and to initiate processing requests to access data at a second memory device, determining that the respective data corresponding to the first and second requests have not yet been fully processed at the time of receiving the indication, and in response, storing, in memory accessible to the memory controller, data corresponding to the requests which have not yet been fully processed.

Systems, apparatuses, and methods for implementing memory request priority assignment techniques for parallel processors are disclosed. A system includes at least a parallel processor coupled to a memory subsystem, where the parallel processor includes at least a plurality of compute units for executing wavefronts in lock-step. The parallel processor assigns priorities to memory requests of wavefronts on a per-work-item basis by indexing into a first priority vector, with the index generated based on lane-specific information. If a given event is detected, a second priority vector is generated by applying a given priority promotion vector to the first priority vector. Then, for subsequent wavefronts, memory requests are assigned priorities by indexing into the second priority vector with lane-specific information. The use of priority vectors to assign priorities to memory requests helps to reduce the memory divergence problem experienced by different work-items of a wavefront.

Systems, apparatuses, and methods for implementing memory request priority assignment techniques for parallel processors are disclosed. A system includes at least a parallel processor coupled to a memory subsystem, where the parallel processor includes at least a plurality of compute units for executing wavefronts in lock-step. The parallel processor assigns priorities to memory requests of wavefronts on a per-work-item basis by indexing into a first priority vector, with the index generated based on lane-specific information. If a given event is detected, a second priority vector is generated by applying a given priority promotion vector to the first priority vector. Then, for subsequent wavefronts, memory requests are assigned priorities by indexing into the second priority vector with lane-specific information. The use of priority vectors to assign priorities to memory requests helps to reduce the memory divergence problem experienced by different work-items of a wavefront.

A non-volatile storage system includes: a host and a storage device. The host includes a submission queue memory, a completion queue memory, and a read/write data memory, and the storage device includes: a controller configured to concurrently communicate with the read/write data memory and with at least one of the submission queue memory and the completion queue memory; and a memory device configured to communicate with the controller.

A non-volatile storage system includes: a host and a storage device. The host includes a submission queue memory, a completion queue memory, and a read/write data memory, and the storage device includes: a controller configured to concurrently communicate with the read/write data memory and with at least one of the submission queue memory and the completion queue memory; and a memory device configured to communicate with the controller.

The present disclosure includes apparatuses and methods related to a memory protocol with command priority. An example apparatus can execute a command that includes a read identification (RID) number based on a priority assigned to the RID number in a register. The apparatus can be a non-volatile dual in-line memory module (NVDIMM) device.

The present disclosure includes apparatuses and methods related to a memory protocol with command priority. An example apparatus can execute a command that includes a read identification (RID) number based on a priority assigned to the RID number in a register. The apparatus can be a non-volatile dual in-line memory module (NVDIMM) device.

Methods, systems, and devices for quality-of-service information for a multi-memory system are described. An interface controller may receive a first command from a host device during a set of clock cycles. The first command may be received over a command bus that includes a pin, such as a command select pin configured for double data rate signaling. The interface controller may decode the first command based on a state of the command select pin during at least one clock cycle of the set of clock cycles. And the interface controller may determine quality-of-service information for a second command based on decoding the first command and on information, such as a plurality of bits, included in the first command.

Memory device might include a controller configured to cause the memory device to determine whether the memory device is waiting to initiate a next phase of an access operation, and in response to determining that the memory device is waiting to initiate the next phase, determine whether there is sufficient available current budget to initiate the next phase in a selected operating mode in response to at least the priority token of the memory device, an expected peak current magnitude for the next phase in the selected operating mode, and additional expected peak current magnitudes for other memory devices. In response to determining that there is sufficient available current budget to initiate the next phase in the selected operating mode, the memory device might output the expected peak current magnitude for the next phase in the selected operating mode from the memory device.