Parallel data processing systems and methods using cooperative thread arrays and thread identifier values to determine processing behavior

A processor comprising:

• a processing core including:
• one or more processing engines configured to execute a plurality of threads concurrently;
• and
• a shared memory communicably coupled to the one or more processing engines;
• and
• core interface logic coupled to the processing core, the core interface logic including:
• a launch module configured to initiate concurrent execution by the processing core of a plurality of threads of a thread array, each thread of the thread array being configured to execute a same program on an input data set,
• the launch module being further configured to assign a unique thread identifier value, wherein each unique thread identifier value is unique within the thread array, to each of the threads prior to instructing the processing core to initiate execution of the threads,
• wherein during execution, each thread of the thread array uses the unique thread identifier value assigned thereto as an input to determine a subset of the input data set to process and to compute at least one program-specified function of the unique thread identifier value,
• wherein the plurality of threads includes a first thread configured to execute the same program on a first subset of the input data set and a second thread configured to execute the same program on a second subset of the input data set, and
• wherein data in the first subset overlaps with the second subset.

A method for processing an input data set using a processor configured to execute a plurality of threads concurrently, the method comprising:

• communicating to the processor information defining a thread array having a plurality of threads, each thread being identified by a unique thread identifier to be used to determine respective portions of an input data set to be processed by each respective thread, wherein each unique thread identifier value is unique within the thread array;
• communicating to the processor a same program to be executed by each thread of the thread array on at least a portion of the input data set stored in a shared memory to produce at least a portion of an output data set;
• and
• communicating to the processor an instruction to begin concurrently executing all of the threads of the thread array to process the input data set in the shared memory to produce the output data set,
• wherein the plurality of threads includes a first thread configured to execute the same program on a first portion of the input data set and a second thread configured to execute the same program on a second portion of the input data set, and
• wherein data in the first portion overlaps with the second portion.