摘要:
A subpipelined translation embodiment provides binary compatibility between current an future generations of DSPs. When retrieved from memory an entire fetch packet is assigned an operating mode (base instruction set or migrant instruction set) according to the current execution mode. The fetch packets from the instruction memory are parsed into execute packets and sorted by execution unit (dispatched) in a datapath shared by both execution modes (base and migrant). The two execution modes have separate control logic. Instructions from the dispatch datapath are decoded by either base architecture decode logic or the migrant architecture decode logic, depending on the execution mode bound to the parent fetch packet. Code processed by the migrant and base decode pipelines produces machine words that are selected by a multiplexer. The multiplexer is controlled by the operating mode bound to the fetch packet that produced the machine word. The selected machine word controls a global register file, which supplies operands to all hardware execution units and accepts results of all hardware execution units.
摘要:
A general purpose microprocessor architecture enabling more efficient computations of a type in which Boolean operations and arithmetic operations conditioned on the results of the Boolean operations are interleaved. The microprocessor is provided with a plurality of general purpose registers ("GPRs" 102) and an arithmetic logic unit ("ALU" 104), capable of performing arithmetic operations and comparison operations. The ALU has a first input (108) and a second input (110), and an output (112), the first and second inputs receiving values stored in the GPRs. The output stores the results of the arithmetic logic unit operations in the GPRs. At least one of the GPRs is capable of receiving directly from the ALU a result of a Boolean operation. In one embodiment, at least one of the GPRs (PN) capable of receiving directly from the ALU a result of a Boolean operation is configured so as to cause the conditioning of an arithmetic operation of the ALU based on the value stored in the GPR.
摘要:
A method of integrated circuit programmed data processor design includes selecting a benchmark application, selecting an initial set of architecture parameters, reconfiguring a compiler for the selected architecture parameters, compiling the benchmark, reconfiguring a data processor simulator to the selected architecture parameters, running the complied benchmark on the reconfigured simulator, automatically synthesizing an integrated circuit physical layout and evaluating performance of the selected architecture parameters against predetermined criteria. The method varies the selected architecture parameters upon failure to meet criteria until evaluation of the selected architecture parameters meets the criteria. The method selects a number of datapath clusters to avoid too many input/output ports in data registers.