摘要:
A method and apparatus for communicating commands and/or data between two different time domains. In one embodiment, multiple memory commands are placed into one or more FIFOs in a manner that specifies the delays that must take place between execution of the different commands. Along with the commands, delay information is placed into the FIFOs, specifying the number of clock cycles, or other form of time delay, that must elapse between execution of a command and execution of a subsequent command. This delay information is used to delay the execution of the subsequent command for the specified time period, while minimizing or eliminating any excess delays. Cue information can also be placed into the FIFOs with the commands to specify which commands must wait for other commands before beginning execution. The delay and cue information is determined and created in the time domain that initiates the transfers. The delays and cueing are executed in the other time domain. Although the different commands may be delivered through different FIFOs and can therefore have unpredictable arrival times with respect to each other, the delay and cueing information maintains the proper execution order and timing between the commands. Interactive control logic at the output of each FIFO uses the timing data to maintain execution in the proper order and with the proper inter-command delays.
摘要:
An apparatus and method for transferring units of information between clock domains. A respective set of N units of information is loaded from an output circuit in a first clock domain into a storage circuit in a second clock domain during each cycle of the first clock domain. Each set of N units is selected by the output circuit to include (1) units of information that have previously loaded into the storage circuit and that will not be output from the storage output from the storage circuit prior to the storage circuit being loaded with a subsequent set of N units of information, and (2) a complement number of units of information that have not previously been loaded into the storage circuit.
摘要:
An apparatus and method for transferring units of information between clock domains. A respective set of N units of information is loaded from an output circuit in a first clock domain into a storage circuit in a second clock domain during each cycle of the first clock domain. Each set of N units is selected by the output circuit to include (1) units of information that have previously been loaded into the storage circuit and that will not be output from the storage circuit prior to the storage circuit being loaded with a subsequent set of N units of information, and (2) a complement number of units of information that have not previously been loaded into the storage circuit.
摘要:
A first-in first-out buffer (FIFO) with multiple outputs. The FIFO has an input for writing data into the FIFO. The FIFO has multiple outputs for reading the data out of the FIFO. Each output is independent from the other outputs, and can be used to read data from a different address at a different time using a different clock signal. In one embodiment, the FIFO is implemented as a storage array with circular pointers to repeatedly loop through the addressable locations. It includes a write pointer to indicate which address represents the input. It includes multiple read pointers to indicate which addresses represent the outputs. Overrun prevention logic is used to assure that the write pointer will not cause new data to be written into any address that has not been read by all outputs, and to assure that data will not be read from any address that has not been written into.
摘要:
A self-synchronizing method and apparatus for exiting a dynamic random access memory from a low power state is provided. The exit from the low power state is initiated. After the expiration of an exit delay period, a first quiet time is sent on a column-access pin. A second quiet time is sent on a row-access pins to reset the memory. The first quiet time and the second quiet time are not necessarily concurrent.
摘要:
In an embodiment, a memory interface may send an indication that a request is being sent. The indication may be sent to a non-volatile memory via a point-to-point bus between a memory interface and the non-volatile memory. The memory interface may send the request to the non-volatile memory via the bus. The request may include an address that may be used to identify a location for storing or reading data. The non-volatile memory may acquire the request from the bus and process the request. After processing the request, the non-volatile memory may send an indication to the memory interface that indicates the non-volatile memory has a response to send to the memory interface. The memory interface may grant access to the bus to the non-volatile memory. After being granted access to the bus, the non-volatile memory may send the response to the memory interface.
摘要:
A memory system and a method for controlling power states of a memory device, or a portion thereof, are provided. The memory system includes memory devices, such as DRAMs, a memory controller, chip select lines, and logic for detecting chip select signals from the chip select lines. Each memory device, or a portion therein, is connected to the memory controller by a chip select line. Each chip select line allows the transmission of a chip select signal to a corresponding memory device, or a corresponding portion of the memory device, to select the corresponding memory device, or a portion thereof, to receive commands. Logic is provided to detect the chip select signal. When the logic detects a chip select signal provided to a corresponding memory device, or a portion thereof, that is in a power state lower than its idle state, the memory device, or a portion thereof, is automatically moved from the lower power state to a higher power state.
摘要:
A memory containing a plurality of memory banks and a plurality of sense amplifiers. Also, the memory device contains a multiplexer and logic. The logic receives a refresh request for one of the plurality of memory banks and instructs the multiplexer to select one of the plurality of sense amplifiers in response to the refresh request.
摘要:
An apparatus and method for accessing a memory. A source address that includes a page address and a page offset is received. The page address requires translation in order to form a first address that can be used to transfer data from a row of memory cells into a sense amplifier array in a memory. The page address is compared to contents of one or more page registers to determine if the data is present in the sense amplifier array as a result of a previous memory access. A second address is asserted to access a portion of the data if the data is determined to be present in the sense amplifier array.
摘要:
Embodiments provide access to a memory over a high speed serial link at slower speeds than the high speed serial links regular operation. An embodiment may comprise a memory apparatus with a differential receiver coupled to a protocol recognition circuit, a low speed receiving circuit that has a first receiver coupled with a first input of the differential receiver and a second receiver coupled with a second input of the differential receiver, wherein the low speed receiving circuit is coupled with the protocol recognition circuit, allowing the first and second receivers to access the protocol recognition block at a different frequency than the differential receiver.