Abstract:
An electronic system includes a pipeline having a first number of pipeline stages coupled in series, a pipeline control unit, and a logic engine, wherein each pipeline stage in the pipeline is for outputting data to a next pipeline stage at each cycle of a clock signal. The pipeline control unit is for changing the first number of pipeline stages in the pipeline to a second number of pipeline stages. The logic engine is for performing operations of the electronic system in a first mode by utilizing the pipeline having the first number of pipeline stages and for performing operations of the electronic system in a second mode by utilizing the pipeline having the second number of pipeline stages. A frequency control unit and a voltage control unit, coupled to the pipeline and the logic engine, respectively adjust the frequency and voltage of the electronic system accordingly.
Abstract:
To handle boundary conditions efficiently during bitstream extraction, a predetermined number of bits are extracted from the bitstream register starting from a most significant bit of the bitstream register when an underflow flag is set. The predetermined number equals a predetermined extraction width minus a previous starting position. The bits are stored in a lowest part of a destination register, and the underflow flag is cleared.
Abstract:
A computer system and a method for controlling a processor thereof are provided. A processor management unit (PMU) is programmed by the processor itself or by another processor according to a change of the operating condition of the processor. Then, a notification signal is sent to the PMU by the processor when the processor is entering a standby mode. Upon receiving the notification signal, the PMU adjusts the operating condition of the processor according to the change. Finally, a completion signal is sent by the PMU to the processor after the change of the operating condition of the processor is stabilized. Therefore, the unpredictable behavior caused by premature awakening of the processor during the adjustment of the operating condition can be avoided.
Abstract:
A method of predicting branch instructions and a method of skipping branch instructions for pipelines which need more than one cycle to predict branch direction and branch target addresses in microprocessors and digital signal processors are provided. The address of an instruction executed before the predicted branch is used as an index to enable early branch prediction so that the address of the instruction predicted to be executed immediately after the branch is available earlier, thereby reducing the number of idle or wasted clock cycles.
Abstract:
To handle boundary conditions efficiently during bitstream extraction, a predetermined number of bits are extracted from the bitstream register starting from a most significant bit of the bitstream register when an underflow flag is set. The predetermined number equals a predetermined extraction width minus a previous starting position. The bits are stored in a lowest part of a destination register, and the underflow flag is cleared.
Abstract:
An electronic system includes a pipeline having a first number of pipeline stages coupled in series, a pipeline control unit, and a logic engine, wherein each pipeline stage in the pipeline is for outputting data to a next pipeline stage at each cycle of a clock signal. The pipeline control unit is for changing the first number of pipeline stages in the pipeline to a second number of pipeline stages. The logic engine is for performing operations of the electronic system in a first mode by utilizing the pipeline having the first number of pipeline stages and for performing operations of the electronic system in a second mode by utilizing the pipeline having the second number of pipeline stages. A frequency control unit and a voltage control unit, coupled to the pipeline and the logic engine, respectively adjust the frequency and voltage of the electronic system accordingly.
Abstract:
A method is disclosed for accessing a target register of a plurality of registers. The method includes: receiving an instruction containing a register index field; and mapping the register index field to the target register access index for accessing the target register. A data accessing apparatus corresponding to this method is also disclosed.
Abstract:
An apparatus comprising a first circuit and a second circuit. The first circuit may be configured to transfer data between a plurality of first ports and a second port via a single port memory in response to one or more control signals. The second circuit may be configured to generate the one or more control signals, wherein the memory is time shared among the second port and the plurality of first ports.
Abstract:
An apparatus and method for scheduling execution of multiple threads on a shared processor resource is described in connection with a multithreaded multiprocessor chip. Using a thread selection policy that switches between available threads every cycle to give priority to the least recently executed or scheduled threads, different threads are able to operate in a way that ensures no deadlocks or livelocks while maximizing aggregate performance and fairness between threads. Prioritization is accomplished by monitoring and sorting thread status information for each thread, including speculative states in which a thread may be speculatively scheduled, thereby improving usage of the execution pipeline by switching a thread in with a lower priority.
Abstract:
A method for performing a jump and translation state change procedure at the same time is disclosed. The method includes: carrying out a series of instruction processing in a first function in a first translation state; and executing a jump instruction which jumps to a target address in a second function and initiates and completes a translation state change to a second translation state at the same time; wherein an address of a next instruction after the jump instruction is stored as a return address in a first register.