Abstract: A combination of memory units and dataflow processing units is disclosed for computation. A first memory unit is interposed between a first dataflow processing unit and a second dataflow processing unit. Operations for a dataflow graph are allocated across the first dataflow processing unit and the second dataflow processing unit. The first memory unit passes data between the first dataflow processing unit and the second dataflow processing unit to execute the dataflow graph. The first memory unit is a high bandwidth, shared memory device including a hybrid memory cube. The first dataflow processing unit and second dataflow processing unit include a plurality of circular buffers containing instructions for controlling data transfer between the first dataflow processing unit and second dataflow processing unit. Additional dataflow processing units and additional memory units are included for additional functionality and efficiency.

Abstract: Techniques are disclosed for multithreaded data flow processing within a reconfigurable fabric. Code is obtained for performing data manipulation within a reconfigurable fabric. The code is segmented into a plurality of data manipulation operations. A first segment from the segmenting is allocated to a first set of processing elements within a plurality of processing elements comprising a reconfigurable fabric. A second segment from the segmenting is allocated to a second set of processing elements within the reconfigurable fabric. The first segment is executed on the first set of processing elements while the second segment is executed on the second set of processing elements. The first kernel and the second kernel comprise multithreaded operation.

Abstract: Techniques are disclosed for remote usage of machine learned layers by a second machine learning construct. Layers determined within a first machine learning construct are sent to the second construct. A first data group is obtained in a first locality. The first data group is applied to a first localized machine learning construct. A first set of convolutional layers is determined within the first localized machine learning construct based on the first data group, where the first set of convolutional layers comprises a first data flow graph machine. Similarity is adjudicated between the first localized machine learning construct and a second localized machine learning construct. The first set of convolutional layers is sent to the second localized machine learning construct, based on the similarity that was adjudicated meeting a threshold. A second data group is analyzed by the second localized machine learning construct using the first set of convolutional layers.

Abstract: A combination of memory units and dataflow processing units is disclosed for computation. A first memory unit is interposed between a first dataflow processing unit and a second dataflow processing unit. Operations for a dataflow graph are allocated across the first dataflow processing unit and the second dataflow processing unit. The first memory unit passes data between the first dataflow processing unit and the second dataflow processing unit to execute the dataflow graph. The first memory unit is a high bandwidth, shared memory device including a hybrid memory cube. The first dataflow processing unit and second dataflow processing unit include a plurality of circular buffers containing instructions for controlling data transfer between the first dataflow processing unit and second dataflow processing unit. Additional dataflow processing units and additional memory units are included for additional functionality and efficiency.