Data employed in computations is processed so that during computations more of the data can be fit into or maintained in a smaller but higher speed memory than an original source of the data. More specifically, a sensitivity value is determined for various items of the data which reflect the number of bits in the data items that are not garbage bits, and only information in the data items that are indicated by the sensitivity value to not be garbage bits are necessarily effectively retained. At least the information that is not garbage bits and the corresponding associated sensitivity are packed together. The results of computations that are performed using the data items as at least one of the operands for the computation are associated with a sensitivity that is derived from the individual sensitivities of the operands used in the computation.

A processing system includes a system interconnect, a processor coupled to communicate with other components in the processing system through the system interconnect, distributed general purpose registers (GPRs) in the processing system wherein a first subset of the distributed GPRs is located in the processor and a second subset of the distributed GPRs is located in the processing system and external to the processor, and a first set of conductors directly connected between the processor and the second subsets of the distributed GPRs. An instruction execution pipeline in the processor accesses any register in the first and second subsets of the distributed GPRs as part of the processor's GPRs during instruction execution in the processor, in which the second subset of the distributed GPRs is accessed through the first conductor.

A memory attachment and routing chip includes a single die having a set of external ports; at least one memory attachment interface comprising a memory controller to attach to external memory, and a fabric core in which routing logic is implemented. The routing logic can (i) receive a first packet of a first type from a first port of the set of ports, the first type of packet being a memory access packet with a memory address which lies in a range of memory addresses associated with the memory attachment and routing chip, detect the memory address and route the packet of the first type to the memory attachment interface. The routing logic can (ii) receive a second packet of a second type, the second type of packet being an inter-processor packet comprising a destination identifier identifying a processing chip external to the memory attachment.

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.

A flash memory device includes a plurality of memory planes each contains arrays of memory cells; a host interface for accessing the plurality of memory planes by an external host; and a controller connected to the plurality of memory planes via a memory interface and controlling the host interface for accessing the plurality of memory planes. The controller is configured to perform: receiving one or more commands on the host interface from the external host; determining whether to perform asynchronous multi-plane independent (AMPI) read operation corresponding to the commands; and after determining to start the AMPI read operation, accessing the memory planes in parallel according to the commands, and completing the AMPI read operation using an order of the commands determined based on an indicator signal provided to the controller to correspond to a sequence of the commands received on the host interface.

A processing system includes a system interconnect, a processor coupled to communicate with other components in the processing system through the system interconnect, distributed general purpose registers (GPRs) in the processing system wherein a first subset of the distributed GPRs is located in the processor and a second subset of the distributed GPRs is located in the processing system and external to the processor, and a first set of conductors directly connected between the processor and the second subsets of the distributed GPRs. An instruction execution pipeline in the processor accesses any register in the first and second subsets of the distributed GPRs as part of the processor's GPRs during instruction execution in the processor, in which the second subset of the distributed GPRs is accessed through the first conductor.

Technology described herein provides an improved system architecture for offloading infrastructure tasks using a multi-root switch with logic to route, via a switch, application data in a data transfer message between a physical storage device and a host system, the host system interfacing with a virtual function of an IPU, by remapping a transaction identifier field in the data transfer message between a first transaction identifier associated with the virtual function and a second transaction identifier associated with the physical storage device, where the physical storage device is managed by the IPU, and where to route the application data between the host system and the physical storage device includes to bypass temporary storage of the application data in a memory local to the IPU. In some examples a remapping table holds the first transaction identifier and the second transaction identifier.

A processing apparatus is described. The apparatus includes a plurality of processing cores, including a first processing core and a second processing core a first field programmable gate array (FPGA) coupled to the first processing core to accelerate execution of graphics workloads processed at the first processing core and a second FPGA coupled to the second processing core to accelerate execution of workloads processed at the second processing core.

A memory controller includes a clock generator to generate a first clock signal and a timing circuit to generate a second clock signal from the first clock signal. The second clock signal times communications with any of a plurality of memory devices in respective ranks, including a first memory device in a first rank and a second memory device in a second rank. The timing circuit is configured to adjust a phase of the first clock signal, when the memory controller is communicating with the second memory device, based on calibration data associated with the second memory device and timing adjustment data associated with feedback from at least the first memory device.

Disclosed are a storage device and method, an electronic device, and a storage medium. The device includes: a first splitting logical module for splitting a first access command into at least two second access commands based on an access address of the first access command; and at least two storage array modules, each of which is configured to perform a corresponding access operation based on one of the at least two second access commands of the first splitting logical module. According to the embodiments, the first access command with relatively long burst is split into second access commands with smaller granularity, and the at least two storage array modules are parallel accessed, whereby the at least two storage array modules can respond in parallel, effectively reducing response time of the first access command and access time of each master when parallel access of masters exists, then improving access efficiency.