Lossless tiling in convolution networks—graph metadata generation

A data processing system configured to receive a processing graph of an application, the processing graph having a sequence of processing nodes, the sequence of processing nodes including an input processing node followed by at least one intermediate processing node and at least one output processing node, the input processing node configured to process an input and generate at least one intermediate representation of the input, the intermediate processing node configured to process the intermediate representation and generate at least one further intermediate representation of the input, and the output processing node configured to process the further intermediate representation and generate at least one output representation of the input, comprising:

• graph metadata generation logic configured to analyze the processing graph and generate graph metadata that specifies a target tiling configuration for the output representation to tile the output representation into a set of non-overlapping tiles, a first tiling configuration for the input to tile the input into a first set of overlapping tiles, a second tiling configuration for the intermediate representation to tile the intermediate representation into a second set of overlapping tiles, and a third tiling configuration for the further intermediate representation to tile the further intermediate representation into a third set of overlapping or non-overlapping tiles;
• compile time logic configured to modify the processing graph based on the graph metadata and generate a modified processing graph, wherein the modified processing graph is configured to generate the first set of overlapping tiles in the first tiling configuration, the second set of overlapping tiles in the second tiling configuration by using the first set of overlapping tiles as a first set of tile-by-tile effective receptive fields, the third set of overlapping or non-overlapping tiles in the third tiling configuration by using the second set of overlapping tiles as a second set of tile-by-tile second effective receptive fields, and the set of non-overlapping tiles in the target tiling configuration by using the third set of overlapping or non-overlapping tiles as a third set of tile-by-tile effective receptive fields;
• and
• runtime logic configured with the compile time logic to execute the modified processing graph to execute the application.