Compiler Techniques for Mapping Program Code to a High Performance, Power Efficient, Programmable Image Processing Hardware Platform

A machine readable storage medium having stored thereon program code that when processed by a computing system causes the computing system to perform a method, comprising:

• compiling program code targeted for an image processor having programmable stencil processors, each stencil processor comprising two-dimensional execution lane and shift register circuit structures, the program code to implement a directed acyclic graph and being comprised of multiple kernels that are to execute on respective ones of said stencil processors, wherein the compiling comprises:
• a) determining that at least one of the kernels is more computationally intensive than another one of the kernels;
• b) in response to a) above performing any of:
• horizontal fusion of kernels;
• vertical fusion of kernels;
• fission of one of the kernels into multiple kernels;
• spatial partitioning of a kernel into multiple spatially partitioned kernels;
• splitting the directed acyclic graph into multiple directed acyclic graphs.

A machine readable storage medium having stored thereon program code that when processed by a computing system causes the computing system to perform a method, comprising:

• compiling program code targeted for an image processor having programmable stencil processors, each stencil processor comprising two-dimensional execution lane and shift register circuit structures, the program code to implement a directed acyclic graph and being comprised of multiple kernels that are to execute on respective ones of said stencil processors, wherein the compiling comprises:
• a) determining that the program code has resource requirements that exceed the image processor's memory capacity;
• b) in response to a) above performing any of:
• fission of one of the kernels into multiple kernels;
• spatial partitioning of a kernel into multiple spatially partitioned kernels;
• splitting the directed acyclic graph into multiple directed acyclic graphs.