摘要:
A computer system including an arrangement for programmably assigning interrupts to a larger set of interrupt channels. The computer system includes a microprocessing unit ("MPU" 102), a peripheral processing unit ("PPU" 110) that communicates with the MPU and a peripheral control unit ("PCU" 112) capable of communicating with the PPU and with at least one associated peripheral device. The PCU has associated therewith a first number, m, of interrupts for signalling to the MPU. The MPU has a second number, n, of interrupt channels over which interrupts are communicable to said MPU. A first register (IN1616) is provided in the PCU for storing a routing value representing the assignment of the m interrupts of the PCU to a selected subset of m channels of the n interrupt channels. A second register (IN1222) is provided in the PPU for storing the routing value. A number, m, connections are provided between the PCU and the PPU for transmitting the m interrupts from the PCU to the PPU. Finally, a logic unit (3820, 3830, 914) is provided that is responsive to the receipt of an interrupt on one of the m connections and to the stored routing value in the second register for communicating an interrupt to the MPU and for identifying to the MPU the m selected interrupt channels to which the communicated interrupt is assigned. Other devices, systems and methods are also disclosed.
摘要:
A programmable interrupt controller for use in computer systems including one or more CPUs is provided. The programmable interrupt controller includes an interrupt request interface, a central interrupt controller, random access memory, and at least one processor interface. The central interrupt controller systematically selects interrupt requests from the interrupt request interface. Information associated with each interrupt request is stored in the random access memory. The central interrupt controller access the information in the random access memory and uses the information and the state of the currently selected interrupt request to determine a next state for the currently selected interrupt request. The information is passed on to the processor interface to determine when and if the interrupt request should issue to one of the CPUs.
摘要:
A programmable interrupt controller for use in a multiprocessing environment that can support a serial bus to send interrupt information to the processors. The interrupt serial bus has a data line to drive all the interrupt information to all the processors and a clock line to synchronize edges for the data stream. A third line, normally tri-stated, may be used to provide a parity error indication for the serial bus. The serial data includes a processor identification, a pin identification and state information. As the programmable interrupt controller sends the interrupt data on the serial bus, all the processors clock the data and check parity. If a processor finds a parity error, it drives the parity error indication low so that the information may be transmitted again. No processor will execute the command contained in the serial message before the time has elapsed for any of the processors to report a parity error. If there is no parity error, the processor accepts and decodes the message and asserts or deasserts the appropriate signal.
摘要:
Storage circuitry (66) may be used to store the values of fuses (77) so that storage circuitry (66) can be read instead of fuses (77). By accessing the fuse values from storage circuitry (66) rather than from fuses (77), there will be no sense current to fuses (77) that may cause marginal fuse blowage for fuses that have not yet been blown. This helps to prevent the situation in which an unblown fuse is erroneously read as having been blown. The use of storage circuitry (66) thus significantly improves the reliability of fuse module (20). For some embodiments, selection storage circuitry (64) may be used to determine whether storage circuitry (66) may be read or whether one of fuses (77) must be read in order to retrieve the desired current fuse value. The fuse value stored in storage circuitry (66) can also be used as direct hardware signals (80).
摘要:
A system for controlling the refresh cycles of a DRAM cell array based upon a temperature measurement. During active mode, a refresh request indication based on a measured temperature is provided to a DRAM controller (e.g. of another integrated circuit die), wherein the DRAM controller initiates a refresh cycle of the DRAM cell array in response thereto. In a self refreshing mode, the DRAM controller does not initiate refresh cycles, but refresh cycles are performed by a controller on the integrated circuit die of the array based upon a temperature measurement.
摘要:
A method and system which will provide data processing systems having memory controllers with the ability to intelligently schedule accesses to system memory. The method and system provide a memory controller having a page-state sensitive memory arbiter. The method and system further include one or more memory state tracking units operably coupled to the page-state sensitive memory arbiter, and the one or more memory state tracking units operably coupled to a system memory. The one or more memory state tracking units operably coupled to a system memory further include the one or more memory state tracking units operably coupled to one or more system memory devices. The method and system track system memory status, monitor pending memory access requests, and schedule one or more pending memory access requests for execution dependent upon the system memory status and the pending memory access requests.
摘要:
A method and system providing a memory controller having a destination-sensitive memory request reordering device. The destination-sensitive memory request reordering device includes a centralized state machine operably connected to one or more memory devices and one or more reorder and bank select engines. The centralized state machine is structured such that control information can be received from at least one of the one or more reorder and bank select engines over the one or more control lines. The centralized state machine is structured such that memory status information can be received from at least one of the one or more reorder and bank select engines over the one or more memory status lines, or such that memory status information can be determined by tracking past memory related activity. Additionally, the centralized state machine is structured to accept memory access requests having associated origin information. The centralized state machine executes the memory access requests based upon the associated origin information and the memory status information. Other embodiments function analogously, with the addition that the centralized state machine incorporates one or more device arbiter and state engines which function as autonomous units generally dedicated to one specific system memory device. The device arbiter and state engines receive identical inputs as discussed for the centralized state machine, except that typically each device arbiter and state engine is dedicated to one particular memory device, and thus generally receives memory status from the memory device with which it is associated via its dedicated memory status line.
摘要:
A method and system for generating and utilizing speculative memory accesses in data processing systems. The method and system provide a memory controller having at least one origin-sensitive speculative memory access request generator. The origin-sensitive speculative memory access request generator is associated with one or more origins of memory access requests. In some embodiments, the origins are buses over which the one or more memory access request travel; in other embodiments the origins are sources of the one or more memory access requests. The origin-sensitive speculative memory access request generator monitors reorder buffers associated with the one or more origins, and in response to space in the reorder buffers generates speculative memory access requests of a type likely to be received by the reorder buffers in the future. The generated origin-related speculative memory access requests are received by a speculative memory access request response buffer checking-and-logic-control unit associated with system memory. The speculative memory access request response buffer checking-and-logic-control unit associated with system memory examines the state of system memory, and, if appropriate, executes some or all of the speculative memory access requests. Subsequent to execution, the responses to the speculative memory access requests are stored in a speculative memory access request response buffer, and thereafter such results are utilized to satisfy non-speculative requests subsequently received.
摘要:
Systems and methods for hardware-based initialization of memory circuitry. In some embodiments, a method may include, after completion and/or independently of an integrity test of a memory circuit, generating a sequence of random logic values using a Built-In-Self-Test (BIST) circuit. The method may further include initializing the memory circuit with the sequence of random logic values using the BIST circuit. In some implementations, the sequence of logic values may be generated using memory circuit identification, chip identification, and/or clock information as a seed state.
摘要:
A power supply voltage for a memory on an integrated circuit is dynamically adjusted during the operating of the memory. The operating of the memory includes powering the memory at a supply voltage. A test memory of the integrated circuit is concurrently powered while operating the memory. The test memory and the memory each include bit cells of a first bit cell configuration type. A voltage level of the supply voltage is adjusted, while operating the memory, based on the testing of the test memory. The voltage level is adjusted with external variations to assume a value that guarantees no failed operation of the memory but also accurately minimizes the supply voltage. The system and method may be implemented with any type of memory. The memory and test memory may be physically implemented either separated or interspersed on the integrated circuit.