摘要:
A digital system and method of operation is provided in which several processors (740(0)–740(n)) are connected to a shared resource (750). Each processor has an access priority register (1410) that is loaded with an access priority value by software executing on the processor. A memory management unit (MMU) (700) is connected to receive a request address (742) from each respective processor. The MMU has a set of entries that correspond to pages of address space. Each entry provides a set of attributes for the associated page of address space, including an address space priority value 309a. For each request, the MMU accesses an entry corresponding to the request address and provides an address space priority value associated with that requested address space page. Arbitration circuitry (1430) is connected to receive a request signal from each processor along with the access priority value from each access priority register and the address space priority value from each MMU. The arbitration circuitry is operable to schedule access to the shared resource according to higher of the pair of priority values provided by each processor.
摘要:
Methods and apparatuses are disclosed for implementing a processor with a split stack. In some embodiments, the processor includes a main stack and a micro-stack. The micro-stack preferably is implemented in the core of the processor, whereas the main stack may be implemented in areas that are external to the core of the processor. Operands are preferably provided to an arithmetic logic unit (ALU) by the micro-stack, and in the case of underflow (micro-stack empty), operands may be fetched from the main stack. Operands are written to the main stack during overflow (micro-stack full) or by explicit flushing of the micro-stack. By optimizing the size of the micro-stack, the number of operands fetched from the main stack may be reduced, and consequently the processor's power consumption may be reduced.
摘要:
An electronic device that comprises a processor including an individual instruction and a first group of instructions. The device further comprises a memory externally coupled to the processor, as well as a second group of instructions. When executed, the first group of instructions causes the processor to execute the second group of instructions in lieu of the individual instruction.
摘要:
A processor executes an instruction that causes a source data field from a programmable position within a first source register to be copied to a destination register. The instruction is particularly useful for generating media-based bitstreams (e.g., audio, video). In some embodiments, a system (e.g., a communication device such as cellular telephone) includes a processor capable of executing the instruction as described above.
摘要:
A processor executes a load (or store) instruction that permits optional error checking to be performed. Based on a control bit in the load instruction, the processor executes the load instruction by causing contents of a source register to be compared to a predetermined value. If the contents of the source register equals the predetermined value, the processor executes an exception handler. However, if the source register contents differs from the predetermined value, the load instruction causes the processor to cause a data value from memory to be loaded into a destination register
摘要:
A processor that comprises decode logic coupled to a first storage unit and comprising a data structure. The processor also comprises a second storage unit coupled to the decode logic. The decode logic obtains a single instruction from the first storage unit and, if indicated by a first bit in the data structure, processes a group of instructions in lieu of the single instruction, the single instruction requiring an operand. If indicated by a second bit in the data structure, the decode logic obtains the operand from the first storage unit and stores the operand to the second storage unit for use by the group of instructions.
摘要:
Systems, methods, and storage media for accessing indirect memory in Java applications are provided. In some embodiments, a storage medium is provided that comprises Java application software that performs one or more operations on an indirect memory of a device. The software comprises instructions that create an instance of a Java class representing the indirect memory, and instructions that access a memory element of the indirect memory using an element unique identifier (“euid”) of the memory element. Other embodiments provide a method for accessing memory elements of a device that comprises creating an instance of a Java class representing the memory elements, and accessing a memory element of the memory elements using an element unique identifier (“euid”) of the memory element, wherein the memory elements are not mapped into the data memory space of the processor.
摘要:
A multiprocessor system (10) includes a plurality of processing modules, such as MPUs (12), DSPs (14), and coprocessors/DMA channels (16). Power management software (38) in conjunction with profiles (36) for the various processing modules and the tasks to executed are used to build scenarios which meet predetermined power objectives, such as providing maximum operation within package thermal constraints or using minimum energy. Actual activities associated with the tasks are monitored during operation to ensure compatibility with the objectives. The allocation of tasks may be changed dynamically to accommodate changes in environmental conditions and changes in the task list. As each task in a scenario is executed, a control word associated with the task can be used to enable/disable circuitry, or to set circuits to an optimum configuration.
摘要:
A digital system and method of operation is provided in which a method is provided for cleaning a range of addresses in a storage region specified by a start parameter and an end parameter. An interruptible clean instruction (802) can be executed in a sequence of instructions (800) in accordance with a program counter. If an interrupt (804) is received during execution of the clean instruction, execution of the clean instruction is suspended before it is completed. After performing a context switch (810), the interrupt is serviced (820). Upon returning from the interrupt service routine (830, 834), execution of the clean instruction is resumed by comparing the start parameter and the end parameter provided by the clean instruction with a current content of a respective start register and end register used during execution of the clean instruction. If the same, execution of the clean instruction is resumed using the current content of the start register and end register. If different, execution of the clean instruction is restarted by storing the start parameter provided by clean instruction in the start register and by storing the end parameter in the end register. In this manner, no additional context information needs to be saved during a context switch in order to allow the clean instruction to be interruptible. If the interrupt occurred during a non-interruptible instruction, then the instruction is completed before the context switch and a return (830, 832) after the interrupt service routine begins execution at the next instruction (803). Other instructions that perform a sequence of operations can also be made interruptible in a similar manner.
摘要:
A digital system and method of operation is provided in which several processors (590n) are connected to a shared cache memory resource (500). A translation lookaside buffer (TLB) (310n) is connected to receive a request virtual address from each respective processor. A set of address regions (pages) is defined within an address space of a back-up memory associated with the cache and write allocation in the cache is defined on a page basis. Each TLB has a set of entries that correspond to pages of address space and each entry provides a write allocate attribute (550) for the associated page of address space. During operation of the system, software programs are executed and memory transactions are performed. A write allocate attribute signal (550) is provided with each write transaction request. In this manner, the attribute signal is responsive to the value of the write allocation attribute bit assigned to an address region that includes the address of the write transaction request. Write allocation in the cache memory is performed generally in accordance with the write allocate attribute signal. However, write allocation policy circuitry (560) is also provided and operates to refine the operation of the write allocation. Thus, the cache memory is responsive to the write policy circuitry such that write allocation is performed in a selective manner in accordance to the attribute signal for a first write policy state and write allocation is always performed in accordance to the attribute signal for a second write policy state.