Tightly coupled processor arrays using coarse grained reconfigurable architecture with iteration level commits

A method for running multiple simultaneous instructions in a course grained reconfigurable architecture having a plurality of processing elements (PEs), the method comprising:

• providing, at each PE, a runtime mechanism for executing program code instructions including a loop, a single PE concurrently running multiple iterations of the same loop and prioritizing execution of instructions such that instructions of an oldest iteration of said same loop for which all data dependencies are satisfied are selected for processing;
• receiving and storing, at a load and storage unit (LSU) having multiple banks of load storage queues (LSQ) operatively coupled with said plurality of PEs, load instructions and store instructions issued by said PEs associated with the multiple iterations;
• synchronizing, at an execution control unit (ECU), operations performed at each said PE and the LSU including tracking of the multiple iterations that have completed, which of the multiple iterations are already running, and which of the multiple iterations are yet to begin, said synchronizing including communicating signals from the ECU to and receiving signals from each PE and LSU for initiating and completing of said multiple iterations on all or a sub-set of the plurality of PEs, wherein the multiple iterations are completed in order, said method further comprising:
• storing, at one or more of a plurality of register files associated with a PE, temporary results of a computation or results of a load and/or store operation, wherein said plurality of register files comprises:
• local register files store variable data that is passed across a commit boundary, a commit boundary being defined a loop entry, iteration boundary, and loop exit points;
• and
• output register files for storing register data that is consumed within a commit boundary, said local register files being organized according to multiple logical banks, said method further comprising:
• configuring one logical bank of said multiple banks to hold data used by all iterations,
• configuring n logical banks of said multiple banks to hold data for n concurrent iterations in flight, and
• configuring one bank for storing data of a last committed iteration, and
• implementing, at said PE, a rotating head pointer to point to a first bank associated with an oldest iteration of an innermost loop, wherein upon committing the oldest iteration, said PE starting a new iteration, and for a new iteration started, a new oldest iteration corresponds to a second bank, and moving said pointer to point to said second bank, wherein said pointer rotates to always point to a bank associated with an oldest iteration amongst said n logical banks.