Systems, methods, and apparatuses relating to in-network storage for a configurable spatial accelerator are described. In one embodiment, a configurable spatial accelerator includes a plurality of processing elements; a circuit switched interconnect network between the plurality of processing elements to receive an input of a dataflow graph comprising a plurality of nodes, wherein the dataflow graph is to be overlaid into the circuit switched interconnect network and the plurality of processing elements with each node represented as a dataflow operator in the plurality of processing elements, and the plurality of processing elements are to perform an operation by a respective, incoming operand set arriving at each of the dataflow operators of the plurality of processing elements; and an in-network storage element of the circuit switched interconnect network comprising a queue coupled to an output queue of a first processing element, and a controller that switches the in-network storage element into a first mode that provides a value stored in the queue of the in-network storage element by the output queue of the first processing element to an input queue of a second processing element when a configuration value is a first value, and into a second mode that bypasses the queue of the in-network storage element and provides a value from the output queue of the first processing element to the input queue of the second processing element when the configuration value is a second value.

Example implementations relate to memory read requests. For example, an implementation may include tracking progress of an iterative write sequence to write data to a memory element of a memory module. A received read request is detected to be addressed to a memory bank that includes the memory element undergoing the iterative write sequence. Based on the tracked progress, a time is determined to interrupt the iterative write sequence with insertion of the read request. The time aligns between operations of the iterative write sequence and data is returned within a predetermined read latency.

Various embodiments are directed to providing integrity protection for a system management mode. During initialization, a hash value of a system management mode control routine may be determined. Subsequently, during operation, the hash value may be compared to a hash value of a system management mode control routine to be executed. The system management mode control routine to be executed may be determined to be authentic if the hash values are the same.

An integrated circuit (IC) can include a command queue having a plurality of slots corresponding to commands from a host processor for execution by a plurality of compute units of the IC and a command request register having a plurality of locations corresponding to the plurality of slots in the command queue. The command request register is configured to generate an interrupt indicating a new command stored within the command queue. The IC can include a controller configured to, in response to the interrupt from the command request register, determine a selected compute unit that is idle from the plurality of compute units to execute the new command. The IC can also include a compute unit direct memory access circuit configured to provide the new command to the available compute unit.

A memory system is disclosed, which relates to technology for implementing data communication between memory devices. The memory system includes a plurality of memory devices and a memory controller. The memory devices allow a data packet composed of data and header information to be directly communicated between the memory devices. The memory controller transmits the data packet to a source memory device from among the plurality of memory devices, and receives the data packet from a last memory device from among the plurality of memory devices. Each of the memory devices hashes the header information such that the data is accessed, using a result of the hash, in address regions located at different positions.

A data storage device may include: a storage; and a controller configured to control data input/output on the storage according to a request transferred from a host device, and provide at least some of read data to the host device before a preset read timeout threshold time is completely consumed, when an interrupt event occurs before a processing of a read request of the host device is completed.

Various systems and methods for computer memory management are described herein. A system includes a memory controller to: monitor utilization of a memory device, the memory device used with a memory compression technique; determine that the utilization of the memory device violates a threshold; and initiate a system interrupt to provoke a response, responsive to the utilization of the memory device violating the threshold.

Methods and apparatuses for IBI handling are provided. The apparatus includes at least one processing unit, a host controller configured to communicate with at least one slave via an I3C link and configured to enter into a low-power mode. The I3C link includes a serial clock (SCL) line and a serial data (SDA) line. The apparatus further includes an IBI detection module configured to detect while the host controller is in the low-power mode, on the SDA line, an in-band interrupt (IBI) request from the at least one slave and a processing unit interrupt control module configured to signal a processing unit interrupt to the at least one processing unit based on information of the IBI request, in the case the host controller is in the low-power mode, in response to the IBI detection module detecting the IBI request.

Based on a command to interrupt operation of a selected one or more of a plurality of data storage drives coupled to two or more storage controllers, two or more signals are sent from the two or more storage controllers via two or more data busses associated with and coupled to the respective two or more controllers. The selected data storage drive receives the two or more signals via the two or more data busses. Based on determining that the two or more signals agree, the operation of the selected drive is interrupted.

An interrupt controller, and method of operation of such an interrupt controller, are provided. The interrupt controller has an interrupt source interface for receiving interrupts from one or more interrupt sources, and a plurality of output interfaces, where each output interface is associated with a processing device that can execute an interrupt service routine to process an interrupt request issued to that processing device. The interrupt source interface has transaction generation circuitry to generate, for each received interrupt, an original transaction to represent the interrupt and a duplicate transaction to represent the interrupt. Buffer circuitry then buffers the original transaction and the duplicate transaction for each received interrupt, and selection circuitry is provided for selecting transactions from the buffer circuitry, and for routing each selected transaction for receipt by the output interface identified by an address portion of the selected transaction. Each output interface has queue storage comprising a plurality of queue entries, where each queue entry is allocated to a transaction received by the output interface and is used to store interrupt identifying information provided by a data portion of the transaction. The queue storage is arranged to maintain duplication tracking information to identify when both the original transaction and its associated duplicate transaction have been received by the output interface. Each output interface inhibits issuing an output signal that would cause an interrupt request for the original transaction to be sent to the associated processing device, until the duplication tracking information identifies that both the original transaction and the associated duplicate transaction have been received by that output interface. This provides an efficient functional safety compliant design for an interrupt controller.