摘要:
A system and method for seamlessly reprogramming clock frequencies includes a phase locked loop (PLL) that generates CPU and double data rate (DDR) clocks. A crystal is used to generate a reference clock. The CPU clock and the reference clock are inputs to a first multiplexer, and the DDR clock and reference clock are inputs to a second multiplexer. In normal operation the multiplexers provide the CPU and DDR clock signal as outputs. To reprogram the clock frequencies and reset the PLL, (1) the reference clock signal is selected to be the output of both multiplexers, so the device is running on the internal reference clock. The mux switching is synchronized with the CPU and DDR clock signals. (2) The PLL is reprogrammed, its internal voltage-controlled oscillator is reset, and the PLL is restarted at the new desired frequency. (3) When the new PLL frequency output is stable, the multiplexers are switched back to the PLL-generated CPU and DDR clocks, synchronously with the reference clock signal.
摘要:
A system and method for seamlessly reprogramming clock frequencies includes a phase locked loop (PLL) that generates CPU and double data rate (DDR) clocks. A crystal is used to generate a reference clock. The CPU clock and the reference clock are inputs to a first multiplexer, and the DDR clock and reference clock are inputs to a second multiplexer. In normal operation the multiplexers provide the CPU and DDR clock signal as outputs. To reprogram the clock frequencies and reset the PLL, (1) the reference clock signal is selected to be the output of both multiplexers, so the device is running on the internal reference clock. The mux switching is synchronized with the CPU and DDR clock signals. (2) The PLL is reprogrammed, its internal voltage-controlled oscillator is reset, and the PLL is restarted at the new desired frequency. (3) When the new PLL frequency output is stable, the multiplexers are switched back to the PLL-generated CPU and DDR clocks, synchronously with the reference clock signal.
摘要:
A system and method to support programmable prefetching of one or more lines of instructions or data into cache storage of a computer system is disclosed. A secondary cache is used to avoid the transfer of a line that is currently being used by the processor. Sequential prefetching is made possible by presetting control registers.
摘要:
A method and system for performing digital signal processing operations in a computer system are disclosed. In addition to the ability to perform DSP operation on a new hardware platform, this method and system allow the dynamic and global control of saturation and left shifting prior to accumulation.
摘要:
A method and system for performing digital signal processing operations in a computer system are disclosed. Digital Signal Processing operations such as multiply and add (MADD) or multiply and subtract (MSUB) can be performed by general-purpose microprocessors. The DSP operations are directed to n-bit operands that are in m-bit registers. The register size (m) may be a multiple of the operand size (n). For example, the DSP operations may utilize 32-bit registers with 16-bit or 8-bit operands, or the DSP operations may utilize 64-bit registers with 32-bit, 16-bit, or 8-bit operands.
摘要:
One or more methods and systems of reducing the size of memory used in implementing a predictive scheme for executing conditional branch instructions are presented. In one embodiment, a conditional branch instruction addresses a first bit array and a second bit array of a branch history table. The branch history table comprises a first bit array and a second bit array in which the second bit array contains a fraction of the number of entries of said first bit array. In one or more embodiments, the size of the branch history table is reduced by at least twenty five percent, resulting in a reduction of memory required for implementing the predictive scheme.
摘要:
A first thread processor of a multi-thread processor system is operable to execute a first process, and a second thread processor of the multi-thread processor system is operable to execute a second process. A control register is operable to store priority information that is individually associated with at least one of the first thread processor and the second thread processor. The priority information identifies a prioritization of the first thread processor and/or a restriction on the second thread processor in a use of a shared hardware resource during execution of at least one of the first process and the second process.
摘要:
A system and method for interrupt distribution in a multithread processor are disclosed. A connection between an interrupt and a set of thread processors can be programmed. When the interrupt is executed, the set of thread processors are affected. While executing the thread processor tasks, the connection may be reprogrammed to interrupt another set of thread processors.
摘要:
One or more methods and systems of improving the performance of consecutive data stores into a cache memory are presented. In one embodiment, the method comprises writing data into a data array associated with at least a first store instruction while accessing a tag in a tag array associated with at least a second store instruction. In one embodiment, the method of processing consecutive data stores into a cache memory comprises updating a first data in a cache memory while concurrently looking up or identifying a second data in the cache memory. In one embodiment, a system for improving the execution of data store instructions of a CPU comprises a pipelined buffer using a minimal number of data entries, a data array used for updating data associated with a first store instruction, and a tag array used for looking up data associated with a second store instruction.
摘要:
One or more methods and systems of improving the performance of consecutive data stores into a cache memory are presented. In one embodiment, the method comprises writing data into a data array associated with at least a first store instruction while accessing a tag in a tag array associated with at least a second store instruction. In one embodiment, the method of processing consecutive data stores into a cache memory comprises updating a first data in a cache memory while concurrently looking up or identifying a second data in the cache memory. In one embodiment, a system for improving the execution of data store instructions of a CPU comprises a pipelined buffer using a minimal number of data entries, a data array used for updating data associated with a first store instruction, and a tag array used for looking up data associated with a second store instruction.