A device architecture includes a spatially reconfigurable array of processors, such as configurable units of a CGRA, having spare homogenous subarrays, and a parameter store on the device which stores parameters that tag one or more elements as unusable. Configuration data is distributed using a statically reconfigurable bus system, to implement the pattern of placement of configuration data, in dependence on the tagged elements. As a result, a spatially reconfigurable array having unusable elements can be repaired.

A method includes: receiving control data at a first data selector of a plurality of data selectors, in which the control data comprises (i) a configuration registry address specifying a location in a configuration state registry and (ii) configuration data specifying a circuit configuration state of a circuit element of a computational circuit; transferring the control data, from the first data selector, to an entry in a trigger table registry; responsive to a first trigger event occurring, transferring the configuration data to the location in the configuration state registry specified by the configuration registry address; and updating a state of the circuit element based on the configuration data.

Techniques for denoising an electromagnetic signal are disclosed. The techniques utilize an antenna, a weight adaptation component, a reservoir computer including a computer interpretable neural network, a delay embedding component, and an output layer computer. The techniques include passively acquiring an electromagnetic signal by the antenna, producing a plurality of reservoir state values by the reservoir computer based on the electromagnetic signal, collecting the plurality of reservoir state values by the delay embedding component into a historical record, determining a plurality of reservoir state value weights by the weight adaptation component based at least in part of the historical record, scaling, by the plurality of reservoir state value weights, to produce a plurality of output values, the plurality of reservoir state values by the output layer computer, and outputting the plurality of output values, where the scaling occurs over a plurality of clock cycles of a clock for the system.

Techniques for denoising an electromagnetic signal are disclosed. The techniques utilize an antenna, a weight adaptation component, a reservoir computer including a computer interpretable neural network, a delay embedding component, and an output layer computer. The techniques include passively acquiring an electromagnetic signal by the antenna, producing a plurality of reservoir state values by the reservoir computer based on the electromagnetic signal, collecting the plurality of reservoir state values by the delay embedding component into a historical record, determining a plurality of reservoir state value weights by the weight adaptation component based at least in part of the historical record, scaling, by the plurality of reservoir state value weights, to produce a plurality of output values, the plurality of reservoir state values by the output layer computer, and outputting the plurality of output values, where the scaling occurs over a plurality of clock cycles of a clock for the system.

An image processing device configured to process image data obtained externally, the image processing device including a preprocessing circuit configured to carry out preprocessing during image processing; and a circuit configuration controller configured to carry out partial reconfiguration of the preprocessing circuit; the preprocessing circuit including: a plurality of arithmetic converter circuits configured to perform arithmetic computations on image data to convert the image data; and a timing control circuit provided between each one in the plurality of arithmetic converter circuits connected in order of processing, the timing control circuit configured to secure the reliable exchange of data; and the circuit configuration controller partially reconfiguring at least one arithmetic converter circuit in the plurality of arithmetic converter circuits while not partially reconfiguring the timing control circuit.

Processors, systems and methods are provided for thread level parallel processing. A processor may comprise a plurality of processing elements (PEs) that each may comprise a configuration buffer, a sequencer coupled to the configuration buffer of each of the plurality of PEs and configured to distribute one or more PE configurations to the plurality of PEs, and a gasket memory coupled to the plurality of PEs and being configured to store at least one PE execution result to be used by at least one of the plurality of PEs during a next PE configuration.

Processors, systems and methods are provided for thread level parallel processing. A processor may comprise a plurality of processing elements (PEs) that each may comprise a configuration buffer, a sequencer coupled to the configuration buffer of each of the plurality of PEs and configured to distribute one or more PE configurations to the plurality of PEs, and a gasket memory coupled to the plurality of PEs and being configured to store at least one PE execution result to be used by at least one of the plurality of PEs during a next PE configuration.

Processors, systems and methods are provided for thread level parallel processing. A processor may comprise a plurality of processing elements (PEs) that each may comprise a configuration buffer, a sequencer coupled to the configuration buffer of each of the plurality of PEs and configured to distribute one or more PE configurations to the plurality of PEs, and a gasket memory coupled to the plurality of PEs and being configured to store at least one PE execution result to be used by at least one of the plurality of PEs during a next PE configuration.

Methods, systems, and devices for data processing are described. In some systems, data pipelines may be implemented to handle data processing jobs. To improve data pipeline flexibility, the systems may use separate pipeline and policy declarations. For example, a pipeline server may receive both a pipeline definition defining a first set of data operations to perform and a policy definition including instructions for performing a second set of data operations, where the first set of data operations is a subset of the second set. The server may execute a data pipeline based on a trigger (e.g., a scheduled trigger, a received message, etc.). To execute the pipeline, the server may layer the policy definition into the pipeline definition when creating an execution plan. The server may execute the execution plan by performing a number of jobs using a set of resources and plugins according to the policy definition.

A data processing system includes an array of reconfigurable units and a compiler configured to generate a pipeline of n computational nodes related to a dataflow graph, interleaved between n+1 buffers on the array of reconfigurable units. Each computational node is coupled to perform calculations based on data received from an immediately preceding buffer of the n+1 buffers and store results of the calculations into an immediately following buffer of the n+1 buffers after a latency. The compiler is further configured to remove a buffer of the n+1 buffers from the pipeline based on a comparison of the latencies of the computational nodes. A corresponding method is also disclosed herein.