Abstract: A method for processing multiple memory requests in a pipeline. Each memory request is processed in part by a plurality of stages. In a first stage, the memory request is decoded. In a second stage, the address information for the memory request is processed. In a third stage, the data for the memory request is transferred. A request buffer is used to hold each of the memory requests during the processing of each of the memory requests.

Abstract: A computer system includes a processor, a system memory, and an integrated circuit system controller coupled to the processor and the system memory. The system controller includes a system memory controller coupled to the system memory, a processor interface coupled to the processor and an embedded cache memory integrated with the memory controller and the processor interface. The cache memory includes at least one DRAM array, at least one tag memory, and at least one cache memory controller. The cache memory controller initiates an access to either or both the DRAM array and the tag memory, as well as the system memory, before the cache memory controller has determined if the access will result in a cache hit or a cache miss. If the cache memory controller determines that the access will result in a cache hit, data are coupled from the DRAM array to the processor. If the cache memory controller determines that the access will result in a cache miss, data are coupled from the system memory to the processor.

Abstract: In a computer or microprocessor-based system having a plurality of resources making memory requests of a plurality of banks of memory, a switch-based interconnect system allows multiple simultaneous connections between resources and memory banks, maximizing memory throughput and bandwidth concurrency. The invention is particularly useful in devices having embedded banks of memory, where there are no external constraints requiring use of a bus architecture, but can be used with discrete devices as well.

Abstract: An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memory controller that are preferably to be used for all AGP transactions. The AGP uses a graphics address remapping table (GART) for mapping memory. The GART includes page table entries having translation information to remap virtual addresses falling within the GART range to their corresponding physical addresses. In a second embodiment of the invention, a plurality of the memory controllers have an AGP, wherein each of the plurality of the memory controllers supplies a set of registers defining a range of addresses that is preferably used for AGP transactions.

Abstract: A memory controller which has multiple stages of pipelining. A request buffer is used to hold the memory request from the processor and peripheral devices. The request buffer comprises a set of rotational registers that holds the address, the type of transfer and the count for each request. The pipeline includes a decode stage, a memory address stage, and a data transfer stage. Each stage of the pipeline has a pointer to the request buffer. As each stage completes its processing, a state machine updates the pointer for each of the stages to reference a new memory request which needs to be processed.

Abstract: An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memory controller that are preferably to be used for all AGP transactions. The AGP uses a graphics address remapping table (GART) for mapping memory. The GART includes page table entries having translation information to remap virtual addresses falling within the GART range to their corresponding physical addresses. In a second embodiment of the invention, a plurality of the memory controllers have an AGP, wherein each of the plurality of the memory controllers supplies a set of registers defining a range of addresses that is preferably used for AGP transactions.

Abstract: An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memory controller that are preferably to be used for all AGP transactions. The AGP uses a graphics address remapping table (GART) for mapping memory. The GART includes page table entries having translation information to remap virtual addresses falling within the GART range to their corresponding physical addresses. In a second embodiment of the invention, a plurality of the memory controllers have an AGP, wherein each of the plurality of the memory controllers supplies a set of registers defining a range of addresses that is preferably used for AGP transactions.

Abstract: A memory controller which has multiple stages of pipelining. A request buffer is used to hold the memory request from the processor and peripheral devices. The request buffer comprises a set of rotational registers that holds the address, the type of transfer and the count for each request. The pipeline includes a decode stage, a memory address stage, and a data transfer stage. Each stage of the pipeline has a pointer to the request buffer. As each stage completes its processing, a state machine updates the pointer for each of the stages to reference a new memory request which needs to be processed.

Abstract: In a computer or microprocessor system having a plurality of resources making memory requests, a caching system includes a source tag generator which, depending on the embodiment, could reside in the requesting system resource, in a bus arbiter, or in a combination of a bus arbiter and a switch arbiter, or elsewhere. The system also includes cache control circuitry capable of using the source tag to make cacheability decisions. The cache control circuitry, and therefore the cacheability decisions, could be fixed—e.g., by a user—or could be alterable based on a suitable algorithm—similar, e.g., to a least-recently-used algorithm—that monitors cache usage and memory requests. The caching system is particularly useful where the cache being controlled is large enough to cache the results of I/O and similar requests and the requesting resources are I/O or similar resources outside the core logic chipset of the computer system.

Abstract: A method for calibration of memory circuits is provided that adjusts memory circuit output parameters based on data eye measurements. Data eye patterns from the memory circuit outputs are measured by the memory controller for different settings of the memory circuit output parameters. Memory circuit output parameters can be adjusted to settings that correspond to widest average data eye widths, highest average data eye heights, or other suitable criteria.

Abstract: A method for processing multiple memory requests in a pipeline. Each memory request is processed in part by a plurality of stages. In a first stage, the memory request is decoded. In a second stage, the address information for the memory request is processed. In a third stage, the data for the memory request is transferred. A request buffer is used to hold each of the memory requests during the processing of each of the memory requests.

Abstract: A memory controller which has multiple stages of pipelining. A request buffer is used to hold the memory request from the processor and peripheral devices. The request buffer comprises a set of rotational registers that holds the address, the type of transfer and the count for each request. The pipeline includes a decode stage, a memory address stage, and a data transfer stage. Each stage of the pipeline has a pointer to the request buffer. As each stage completes its processing, a state machine updates the pointer for each of the stages to reference a new memory request which needs to be processed.

Abstract: A computer system includes a processor, a system memory, and an integrated circuit system controller coupled to the processor and the system memory. The system controller includes a system memory controller coupled to the system memory, a processor interface coupled to the processor and an embedded cache memory integrated with the memory controller and the processor interface. The cache memory includes at least one DRAM array, at least one tag memory, and at least one cache memory controller. The cache memory controller initiates an access to either or both the DRAM array and the tag memory, as well as the system memory, before the cache memory controller has determined if the access will result in a cache hit or a cache miss. If the cache memory controller determines that the access will result in a cache hit, data are coupled from the DRAM array to the processor. If the cache memory controller determines that the access will result in a cache miss, data are coupled from the system memory to the processor.

Abstract: In a computer or microprocessor-based system having a plurality of resources making memory requests of a plurality of banks of memory, a switch-based interconnect system allows multiple simultaneous connections between resources and memory banks, maximizing memory throughput and bandwidth concurrency. The invention is particularly useful in devices having embedded banks of memory, where there are no external constraints requiring use of a bus architecture, but can be used with discrete devices as well.

Abstract: An architecture for storing, addressing and retrieving graphics data from one of multiple memory controllers. In a first embodiment of the invention, one of the memory controllers having an accelerated graphics port (AGP) includes a set of registers defining a range of addresses handled by the memory controller that are preferably to be used for all AGP transactions. The AGP uses a graphics address remapping table (GART) for mapping memory. The GART includes page table entries having translation information to remap virtual addresses falling within the GART range to their corresponding physical addresses. In a second embodiment of the invention, a plurality of the memory controllers have an AGP, wherein each of the plurality of the memory controllers supplies a set of registers defining a range of addresses that is preferably used for AGP transactions.

Abstract: A memory controller which has multiple stages of pipelining. A request buffer is used to hold the memory request from the processor and peripheral devices. The request buffer comprises a set of rotational registers that holds the address, the type of transfer and the count for each request. The pipeline includes a decode stage, a memory address stage, and a data transfer stage. Each stage of the pipeline has a pointer to the request buffer. As each stage completes its processing, a state machine updates the pointer for each of the stages to reference a new memory request which needs to be processed.

Abstract: A bus arbitration regulates access to a common bus by a plurality of devices by assigning each device a priority rank. A current weighted bandwidth of each device is set equal to a desired weighted bandwidth. A request to access the common bus is granted to the device having the highest priority rank among a set of requesting devices. The current weighted bandwidth the first device is decremented. The priority rank of the serviced device is set equal to a lowest value if its current weighted bandwidth is equal to a minimum value. The priority rank of a set of devices which previously had a lower priority rank than the first device is increased. The current weighted bandwidth of the serviced device is set equal to the desired weighted bandwidth. After a number of bus transactions have been completed, the desired weighted bandwidth of the devices may be adjusted to based upon system performance.

Abstract: In a computer system, the operating speed of the memory module interface is selected in accordance with information stored in serial presence detect EEPROMs, such as the number of memory modules coupled to a memory controller of the computer system. The memory controller has clocks of various frequencies available to it to drive the memory modules. The most optimal clock is preferably chosen based on at least the number or other characteristics, such as speed, of memory modules. This permits the memory modules to be driven with a higher speed clock when, for example, there are fewer than the maximum number of memory modules present in the system.

Abstract: In a computer or microprocessor system having a plurality of resources making memory requests, a caching system includes a source tag generator which, depending on the embodiment, could reside in the requesting system resource, in a bus arbiter, or in a combination of a bus arbiter and a switch arbiter, or elsewhere. The system also includes cache control circuitry capable of using the source tag to make cacheability decisions. The cache control circuitry, and therefore the cacheability decisions, could be fixed—e.g., by a user—or could be alterable based on a suitable algorithm—similar, e.g., to a least-recently-used algorithm—that monitors cache usage and memory requests. The caching system is particularly useful where the cache being controlled is large enough to cache the results of I/O and similar requests and the requesting resources are I/O or similar resources outside the core logic chipset of the computer system.

Abstract: A memory controller which has multiple stages of pipelining. A request buffer is used to hold the memory request from the processor and peripheral devices. The request buffer comprises a set of rotational registers that holds the address, the type of transfer and the count for each request. The pipeline includes a decode stage, a memory address stage, and a data transfer stage. Each stage of the pipeline has a pointer to the request buffer. As each stage completes its processing, a state machine updates the pointer for each of the stages to reference a new memory request which needs to be processed.