MULTITHREADED SIMD PARALLEL PROCESSOR WITH LAUNCHING OF GROUPS OF THREADS

In a multithreaded processing core, groups of threads are launched in parallel for single-instruction, multiple-data (SIMD) execution by a set of parallel processing engines. Thread-specific input data for threads in a new SIMD group can be loaded directly into the local register files used by the parallel processing engines, or the data can be accumulated in a buffer until a launch condition is satisfied. When the launch condition is satisfied, the entire group is launched. Various launch conditions can be defined, including but not limited to full population of the SIMD group, a change in data processing conditions, or a timeout.