Data processing architecture and related procedures and hardware improvements

A data processing system configured to perform data processing of a data flow application, said data processing system comprising:

• a control processor having access to memory;
• and
• a plurality of programmable Processing Elements, PEs, organized in multiple clusters, each cluster comprising a multitude of said programmable PEs, the functionality of each programmable Processing Element being defined by internal microcode in a microprogram memory associated with the Processing Element,
• wherein said multiple clusters of programmable Processing Elements are arranged in a Network on Chip, NoC, connected to said control processor, which is provided as a central hub, i.e. a root, for the Network on Chip, and said multiple clusters of programmable Processing Elements being arranged at peripheral nodes, also being referred to as cluster nodes, of the Network on Chip;
• wherein each cluster further includes a Cluster Controller, CC, and an associated Cluster Memory, CM, shared by the multitude of programmable Processing Elements within the cluster;
• wherein said memory accessible by said control processor includes object code, created by a compiler, and the control processor is configured to access the object code from said memory and execute the object code for controlling the data processing of the data flow application including controlling transfers of information between the root and the clusters of said Network on Chip, whereby said control processor is configured to control, when executing said object code, transfer of:
• i) microcode, ii) input data, and iii) application parameters for the data flow application to selected locations in said Cluster Memories, and transfer intermediate data or results from the Cluster Memories;
• wherein the Cluster Controller of each cluster is configured for controlling loading of microcode from the associated Cluster Memory into the microprogram memories of at least part of the Processing Elements within the cluster;
• wherein said control processor is configured to command at least selected clusters to start processing the input data, using the microcode and application parameters that they have received;
• wherein each Processing Element includes one or more arithmetic units, and each Processing Element is configured to execute the microcode in its microprogram memory to control the execution, by one or more of the arithmetic units within the Processing Element, of a dedicated part of the arithmetic work of the data processing of the data flow application to be performed by the Processing Element.