Abstract: A memory controller includes a first arbiter for selecting memory commands for dispatch to a memory over a first channel, a second arbiter for selecting memory commands for dispatch to the memory over a second channel, and a test circuit. The test circuit generates a respective testing sequence of read commands and write commands for each of the first channel and second channel, and causes the testing sequences to be transmitted over the first and second channels at least partially overlapping in time without selection by the first or second arbiters.

Abstract: A shared data transfer clock is used among double data rate memory ranks. A memory controller processes incoming memory access commands destined for at least one of a plurality of double data rate memory ranks and determines when a target DDR memory rank is out of synchronization with respect to the shared data transfer clock and a memory clock. In response to determining that the target DDR memory rank is out of synchronization, the memory controller determines whether the non-target DDR memory rank is out-of-synchronization with respect to the shared data transfer clock and the memory clock, and issues a data transfer clock synchronization command to the target DDR memory rank in response to determining that the non-target DDR memory rank is out-of-synchronization with respect to the shared data transfer clock and the memory clock.

Abstract: A shared data transfer clock is used among double data rate memory ranks. A memory controller processes incoming memory access commands destined for at least one of a plurality of double data rate memory ranks and determines when a target DDR memory rank is out of synchronization with respect to the shared data transfer clock and a memory clock. In response to determining that the target DDR memory rank is out of synchronization, the memory controller determines whether the non-target DDR memory rank is out-of-synchronization with respect to the shared data transfer clock and the memory clock, and issues a data transfer clock synchronization command to the target DDR memory rank in response to determining that the non-target DDR memory rank is out-of-synchronization with respect to the shared data transfer clock and the memory clock.

Abstract: A method for throttling a bus, e.g. a memory bus, may be used to compensate for potential inaccuracy of feedback information received for monitored characteristics, e.g. temperature, reported by sensors configured in monitored devices, e.g. memory devices, accessed through the bus. For example, in case of a memory bus, a memory controller may be configured to throttle the memory bus in a way that maximizes system performance while ensuring that the memory devices keep operating within their thermal limits. Readings obtained from the memory, or from close proximity to the memory, may indicate whether the temperature of the memory has crossed over one or more designated trip points, and one or more algorithms may be executed to perform throttling according to the readings and based on fixed and dynamic throttling modes.

Abstract: A memory loopback system and method including an address/command transmit source configured to transmit a command and associated address through an address/command path. A transmit data source is configured to transmit write data associated with the command through a write path. Test control logic is configured to generate gaps between successive commands. A loopback connection is configured to route the write data from the write path to a read path. A data comparator is configured to compare the data received via the read path to a receive data source and generate a data loopback status output. Pattern generation logic can be configured to generate a loopback strobe, the loopback strobe being coupled to the read path. The pattern generation logic may be configured to synthesize a read strobe based on the test control logic and to use the synthesized read strobe as the loopback strobe.

Abstract: A memory loopback system and method including an address/command transmit source configured to transmit a command and associated address through an address/command path. A transmit data source is configured to transmit write data associated with the command through a write path. Test control logic is configured to generate gaps between successive commands. A loopback connection is configured to route the write data from the write path to a read path. A data comparator is configured to compare the data received via the read path to a receive data source and generate a data loopback status output. Pattern generation logic can be configured to generate a loopback strobe, the loopback strobe being coupled to the read path. The pattern generation logic may be configured to synthesize a read strobe based on the test control logic and to use the synthesized read strobe as the loopback strobe.

Abstract: A dynamic random access memory (DRAM) controller may comprise two sub-controllers, each capable of handling a respective N-bit interface (e.g. 64-bit interface). Each sub-controller may also be configurable to be (2*N)-bit (e.g. 128-bit) capable with respect to control logic, for controlling a logical 128-bit data path. In ganged mode, each sub-controller may logically operate as if it were handling data in 128-bit chunks, (i.e. handling the entire 128-bit data path), while actual full bandwidth may be achieved by having one of the sub-controllers operate on commands and a first N-bit portion of each (2*N)-bit chunk of data, and having the other sub-controller operate on a “copy” of the commands with a corresponding remaining N-bit portion of each (2*N)-bit chunk of data.

Abstract: Timing delays in a double data rate (DDR) dynamic random access memory (DRAM) controller (114, 116) are trained. A left edge of passing receive enable delay values is determined (530). A final value of a receive data strobe delay value and a final value of a transmit data delay value are trained (540). A right edge of passing receive enable delay values is determined using a working value of the receive data strobe delay (550); and a final receive enable delay value intermediate between the left edge of passing receive enable delay values and the right edge of passing receive enable delay values is set (560).

Abstract: A DRAM controller may be configured to re-order read/write requests to maximize the number of page hits and minimize the number of page conflicts and page misses. A three-level prediction algorithm may be performed to obtain auto-precharge prediction for each read/write request, without having to track every individual page. Instead, the DRAM controller may track the history of page activity for each bank of DRAM, and make a prediction to first order based history that is not bank based. The memory requests may be stored in a queue, a specified number at a time, and used to determine whether a page should be closed or left open following access to that page. If no future requests in the queue are to the given bank containing the page, recent bank history for that bank may be used to obtain a prediction whether the page should be closed or left open.

Abstract: Timing delays in a double data rate (DDR) dynamic random access memory (DRAM) controller (114, 116) are trained. A left edge of passing receive enable delay values is determined (530). A final value of a receive data strobe delay value and a final value of a transmit data delay value are trained (540). A right edge of passing receive enable delay values is determined using a working value of the receive data strobe delay (550); and a final receive enable delay value intermediate between the left edge of passing receive enable delay values and the right edge of passing receive enable delay values is set (560).

Abstract: A DRAM controller may comprise two sub-controllers, each capable of handling a respective N-bit interface (e.g. 64-bit interface). Each sub-controller may also be configurable to be (2*N)-bit (e.g. 128-bit) capable with respect to control logic, for controlling a logical 128-bit data path. In ganged mode, each sub-controller may logically operate as if it were handling data in 128-bit chunks, (i.e. handling the entire 128-bit data path), while actual full bandwidth may be achieved by having one of the sub-controllers operate on commands and a first N-bit portion of each (2*N)-bit chunk of data, and having the other sub-controller operate on a “copy” of the commands with a corresponding remaining N-bit portion of each (2*N)-bit chunk of data. Once the BIOS has configured and initialized the two DRAM controllers to operate in ganged mode, the BIOS and all software may no longer need to be aware that two memory controllers are used to access a single (2*N)-bit wide channel.

Abstract: A DRAM controller may be configured to re-order read/write requests to maximize the number of page hits and minimize the number of page conflicts and page misses. A three-level prediction algorithm may be performed to obtain auto-precharge prediction for each read/write request, without having to track every individual page. Instead, the DRAM controller may track the history of page activity for each bank of DRAM, and make a prediction to first order based history that is not bank based. The memory requests may be stored in a queue, a specified number at a time, and used to determine whether a page should be closed or left open following access to that page. If no future requests in the queue are to the given bank containing the page, recent bank history for that bank may be used to obtain a prediction whether the page should be closed or left open.

Abstract: A method for throttling a bus, e.g. a memory bus, may be used to compensate for potential inaccuracy of feedback information received for monitored characteristics, e.g. temperature, reported by sensors configured in monitored devices, e.g. memory devices, accessed through the bus. For example, in case of a memory bus, a memory controller may be configured to throttle the memory bus in a way that maximizes system performance while ensuring that the memory devices keep operating within their thermal limits. Readings obtained from the memory, or from close proximity to the memory, may indicate whether the temperature of the memory has crossed over one or more designated trip points, and one or more algorithms may be executed to perform throttling according to the readings and based on fixed and dynamic throttling modes.

Abstract: An apparatus for providing packets in a peripheral interface circuit of an I/O node of a computer system. The apparatus includes a buffer that may be configured to accumulate data received on a first bus. The apparatus further includes a control unit coupled to the buffer which may be configured to transmit a data packet containing a first number of bytes of the data in response to detecting that any of the bytes of the data is invalid. The control unit may be further configured to transmit the data packet containing a second number of bytes of the data in response to detecting that all of the bytes are valid.

Abstract: A method and apparatus for reducing latency in a peripheral interface circuit of an I/O node of a computer system. The apparatus includes a buffer coupled to a control unit. The buffer may be configured to receive data on a first bus and the control unit may be configured to generate a first command type in response to receiving a first quantity of data having invalid bytes within the buffer. The control unit may be further configured to generate a second command type in response to a receiving within the buffer a second quantity of data having no invalid bytes. Further, in response to receiving a particular transaction type, the control unit may be configured to generate the second command type before the first quantity of data is received within the buffer.

Abstract: An apparatus for reordering graphics responses in a peripheral interface circuit for an I/O node of a computer system. The apparatus includes a data buffer and a control unit. The data buffer includes a first plurality of storage locations each corresponding to one of a plurality of tag values. The data buffer may receive a plurality of data packets associated with the graphics transactions. The data buffer may also store the data packets in the storage locations according to tag values. The control unit includes a storage unit having a second plurality of locations. Each of the locations in the storage unit corresponds to one of the tag values and may provide an indication of whether a given data packet has been stored in the data buffer. The control unit may further determine an order in which the plurality of data packets is read from the data buffer.

Abstract: An apparatus for reordering packet transactions within a peripheral interface circuit. The apparatus includes a source tagging unit and a control unit. The source tagging unit may be configured to generate a plurality of tag values each corresponding to one of a plurality of packet commands. The control unit may include a first storage unit including a first plurality of locations and a second storage unit including a second plurality of locations. Each of the locations corresponds to one of the plurality of tag values. Each of the first plurality of locations may provide an indication of whether a given tag value corresponds to a first packet command in a given data stream. A first given location of the second plurality of locations corresponds to the tag value indicated by the first storage unit and stores a tag value of a second packet command in the given data stream.

Abstract: An apparatus for initiating partial transactions in a peripheral interface circuit for an I/O node of a computer system. An apparatus for performing partial transfers on a peripheral bus in response to a request for a stream of data includes a data buffer coupled to a control unit. The data buffer may be configured to store one or more data packets each containing data forming a portion of the data stream. The control unit may be configured to determine the presence of data packets stored in the data buffer that collectively contain a sequence of data forming a portion of the data stream. The control unit may be further configured to cause the sequence of data to be conveyed on the peripheral bus.

Abstract: A method and apparatus for handling split response transactions within a peripheral interface of an I/O node of a computer system. An apparatus includes a first buffer circuit coupled to receive packet commands from a requesting node. The first buffer circuit may include a plurality of buffers each corresponding to a respective virtual channel of a plurality of virtual channels for storing selected packet commands that belong to the respective virtual channel. The apparatus also includes a bus interface circuit which may be configured to cause a bus cycle corresponding to a given packet command stored within the first buffer circuit to be initiated upon a peripheral bus. Further, the apparatus includes a second buffer circuit coupled to store the given packet command in response to receiving a split response from a target of the bus cycle.

Abstract: A buffer circuit for rotating outstanding transactions. A buffer circuit includes a buffer and a command update circuit. The buffer may be configured to store packet commands that belong to a respective virtual channel of a plurality of virtual channels. The packets may be stored in the buffer to await transmission upon a peripheral bus. Once a given packet is selected for transmission, a peripheral bus cycle corresponding to the given packet command may be generated upon the peripheral bus. The command update circuit may be configured to generate a modified packet command in response to receiving a partial completion indication associated with the peripheral bus cycle. The command update circuit may also be configured to cause the modified packet command to be stored within the buffer.