摘要:
A computer system having a core logic chipset that functions as a bridge between an Accelerated Graphics Port ("AGP") bus device such as a graphics controller, and a host processor and computer system memory wherein a Graphics Address Remapping Table ("GART table") is used by the core logic chipset to remap virtual memory addresses used by the AGP graphics controller into physical memory addresses that reside in the computer system memory. The GART table enables the AGP graphics controller to work in contiguous virtual memory address space, but actually use non-contiguous blocks or pages of physical system memory to store textures, command lists and the like. The GART table is made up of a plurality of entries, each entry comprising an address pointer to a base address of a memory page, and feature flags that may be used to customize the associated memory page.
摘要:
A computer system having a core logic chipset that functions as a bridge between an Accelerated Graphics Port ("AGP") bus device such as a graphics controller, and a host processor and computer system memory wherein a Graphics Address Remapping Table ("GART table") is used by the core logic chipset to remap virtual memory addresses used by the AGP graphics controller into physical memory addresses that reside in the computer system memory. The GART table enables the AGP graphics controller to work in contiguous virtual memory address space, but actually use non-contiguous blocks or pages of physical system memory to store textures, command lists and the like. The GART table is made up of a plurality of entries, each entry comprising an address pointer to a base address of a page of graphics data in memory, and feature flags that may be used to customize the associated page. The core logic chipset caches a subset of the most recently used GART table entries to increase AGP performance when performing the address translation. The core logic chipset uses a two-level GART cache comprising a plurality of first-level GART caches and a common second level GART cache. Each of the plurality of first-level GART caches are coupled to a respective interface in the computer system and effectively de-couple the different interface GART address translations so that GART cache thrashing and cache arbitration delays are substantially reduced. Separate decoupled first-level GART caches for each interface allow concurrent GART address translations among the different interfaces. Individual first-level GART caches may be fined tuned for each associated interface.
摘要:
A buffer management structure for processing systems is described. In one embodiment, the buffer management structure includes a storage module and a control module. The storage module includes a read position and can store a bit indicating a valid state of a transaction request in a write entry. The control module can receive an invalidation request and modify the bit to indicate an invalid state for the transaction request and discard the transaction request when the transaction request is in the read position.
摘要:
A buffer management structure for processing systems is described. In one embodiment, the buffer management structure includes a storage module and a control module. The storage module includes a read position and can store a bit indicating a valid state of a transaction request in a write entry. The control module can receive an invalidation request and modify the bit to indicate an invalid state for the transaction request and discard the transaction request when the transaction request is in the read position.
摘要:
A transaction generator generates memory transactions identical to processor memory transactions to initialize, rebuild, and verify memory added or replaced during operation of a computer system configured for RAID memory. The transactions read and rewrite the correct value for replaced memory and write a known good value for added memory. Memory writes are verified by a read after the write transaction. The transaction generator is a state machine. A first counter is used for holding memory addresses of the transactions, automatically incrementing after each transaction. A second counter can throttle the generation of transactions by controlling the incrementation speed of the first counter. Transactions generated by the transaction generator have a transaction identifier, selected from a pool of available transaction identifiers. The transactions can complete out of order.
摘要:
A processor-based device having a plurality of memory cartridges secured within a chassis by a lever system. The processor-based device comprises an indication system to indicate memory system operating conditions. Each memory cartridge has a protective assembly to protect memory elements within the memory cartridge when the memory cartridge is removed from the processor-based device. The processor-based device is operable such that at least one memory cartridge may be removed from the processor-based device without affecting operation of the processor-based device.
摘要:
An improved DMA controller having programmable data transfer timings. Not only is the total cycle time programmable, but the active and inactive period of the cycle are also programmable. An active timing register and an inactive timing register are used in conjunction with a countdown timer to determine the active and inactive periods of the data transfer cycle. The active time period is loaded into the timer during the active phase, with the end of the active phase being indicated by the timer timing out. Next, the inactive time period is loaded into the timer, which similarly times out to indicate the end of the inactive phase of the data transfer cycle.
摘要:
A processor-based device having a plurality of memory cartridges secured within a chassis by a lever system. The processor-based device comprises an indication system to indicate memory system operating conditions. Each memory cartridge has a protective assembly to protect memory elements within the memory cartridge when the memory cartridge is removed from the processor-based device. The processor-based device is operable such that at least one memory cartridge may be removed from the processor-based device without affecting operation of the processor-based device.
摘要:
A processor-based device having a plurality of memory cartridges secured within a chassis by a lever system. The processor-based device comprises an indication system to indicate memory system operating conditions. Each memory cartridge has a protective assembly to protect memory elements within the memory cartridge when the memory cartridge is removed from the processor-based device. The processor-based device is operable such that at least one memory cartridge may be removed from the processor-based device without affecting operation of the processor-based device.
摘要:
A point-to-point serial communication link between a system interface unit and a peripheral bus interface unit is provide. The system bus interface unit may interface between a CPU bus and a peripheral bus, such as the PCI bus, and may be referred to as a north bridge. The system interface unit may also interface to main memory and to an advanced graphics port. The peripheral bus interface unit may interface between a first peripheral bus, such as the PCI bus, and a second peripheral bus, such as an ISA bus, and may be referred to as a south bridge. The serial communication link between the system interface unit and the bus interface unit may be a one wire serial bus that uses a bus clock from the first peripheral bus as a timing reference. This clock may be the PCI clock. The serial communication link may use a single pin on the system interface unit and a single pin on the bus interface unit to transfer commands between the interface units. A pull-up device may be provided on the serial communication link to maintain a high voltage level on the link when it is not being driven by one of the bus interface units. The north bridge and south bridge may alternate between sending and receiving commands across the