摘要:
A high performance Local Bus Peripheral Interface (LBPI) for a computer local bus and its high performance peripheral interface(s) uses a pipelined architecture to increase the use of the available data transfer bandwidth. In one embodiment, the LBPI can be selectably configured to couple on the host side to either a VL bus or PCI bus. The LBPI maintains a countdown of the number of words of a data sector already transferred and/or "snoops" the peripheral device commands from the computer to predict the occurrence of subsequent read data transfers commands. The Controlling State Machine also "snoops" the peripheral device commands to maintain its record of the operating parameters of the peripheral devices and also keeps track of which of the devices is currently active. In one embodiment, the LBPI supports DMA and PIO data transfers on the peripheral side. In another embodiment, the LBPI translates memory data transfers into IO data transfers to improve efficiency of IO data transfers. A DMA Timeout Counter is used during DMA mode data transfer operations to prevent the system from indefinitely waiting for an appropriate DMA Request Signal from a selected peripheral. During a DMA mode data transfer operation, forced interrupts may be generated and transmitted to the host in order to emulate a PIO mode data transfer operation. During a DMA mode data transfer operation, an imposed status or "Fake 3F6" register is utilized to transmit status information to the host system.
摘要:
Systems and methods of managing power provide for placing a processor in a non-snoopable state, where the processor is associated with a system memory. One or more data transfers between a controller and the system memory can be serviced while the processor is in the non-snoopable state. In one embodiment, it is determined that the processor has flushed an internal cache of the processor to the system memory before placing the processor in the non-snoopable state.
摘要:
Embodiments of the present invention provide a method and apparatus for conserving power in an electronic device. In particular, embodiments of the present invention dynamically place the memory in self-refresh and chipset clock circuits in power down mode while keeping the isochronous streams (such as display) updated and servicing bus master cycles in a power savings mode.
摘要:
A circuit for monitoring future Universal Serial Bus (USB) activities is described. Specifically, the circuit may comprise a Direct Memory Access (DMA) engine schedule prefetcher. The DMA engine schedule prefetcher accesses linked list schedule structures in main memory. The structures are checked for future frames where the linked list has USB activity scheduled. A periodic DMA engine subsequently accesses main memory only during frames where USB traffic is scheduled.
摘要:
A selectable control over multiple clock frequency/voltage level combinations that can be activated in a processor. A table can be placed in hardware that defines multiple combinations of CPU clock frequency and CPU operating voltage. By placing the table in hardware, it can be assured that all the various combinations will work for the particular processor device. Software can then be used to select a combination from this table, to control the actual frequency/voltage combination that is being implemented at a given time. This allows dynamic control over the power/performance tradeoff, so that the system can see maximum power savings consistent with acceptable performance, as operating and environmental considerations continue to change the most desirable selections.
摘要:
A method and apparatus for facilitating direct access to computer resources by a peripheral device while the computer's CPU is in a sleeping state. A peripheral device having a circuit to detect the power management state of a central processor, a first interface to couple the device to the central processor if the circuit detects the first power management state, and a second interface to couple the device to a peripheral device if the circuit detects the second power management state.
摘要:
A device controller can have multiple device performance states (DPS), which represent different levels of performance vs. power consumption during operation. The device controller can include a DPS status register that can be read by a processor, to indicate the current DPS, and a DPS control register that can be written by the processor, to change the current DPS to a desired DPS. The controller may also have a processor performance state (PPS) status register which can be used to affect the desired choice of DPS based on the performance state of the processor. Each of the registers can be accessed by the device driver for that device controller. The DPS of multiple devices can be coordinated to achieve an improved system-level reduction in power consumption, while maintaining sufficient operational capability.
摘要:
A high performance Local Bus Peripheral Interface (LBPI) for a computer local bus and its high performance peripheral interface(s), using a pipelined architecture to increase the use of the available data transfer bandwidth. To accomplish the above, the LBPI, which is coupled between the computer local bus and the peripheral interface(s), is provided a pipelined architecture which includes a Read Ahead Buffer, a Read Ahead Counter, a Data Out Latch, and a Controlling State Machine with a Configuration Register. In one embodiment, the LBPI can be selectably configured to couple on the host side to either a VL bus or PCI bus. Efficiency of Read-Ahead operations is further enhanced by maintaining a countdown of the number of words of a data sector already transferred and/or "snooping" the peripheral device commands from the computer to intelligently predict the occurrence of subsequent read data transfers commands. The Controlling State Machine also "snoops" the peripheral device commands to maintain its record of the operating parameters of the peripheral devices and also keeps track of which of the devices is currently active. In one embodiment, the LBPI supports DMA and PIO data transfers on the peripheral side. In another embodiment, the LBPI translates memory data transfers into IO data transfers to improve efficiency of IO data transfers. A DMA Timeout Counter is used during DMA mode data transfer operations to prevent the system from indefinitely waiting for an appropriate DMA Request Signal from a selected peripheral. During a DMA mode data transfer operation, forced interrupts may be generated and transmitted to the host in order to emulate a PIO mode data transfer operation. During a DMA mode data transfer operation, an imposed status or "Fake 3F6" register is utilized to transmit status information to the host system.