Abstract: A method of controlling power states in a memory device includes determining if a power-down command is received. A first lower power state is entered if the power-down command is received and the memory device is in a first state. A second lower power state is entered if the power-down command is received and if the memory device is in a second state. The second lower power state is lower than the first lower power state. The memory device remains in a normal operation power state if the power-down command is not received.

Abstract: Apparatus and method to carry out refresh operations on rows of memory cells within a memory device independently of a memory controller during times when there is no activity on a memory bus coupling the memory device to the memory controller that involves the memory device.

Abstract: A method of controlling power states in a memory device includes determining if a power-down command is issued. A first lower power state is entered if the power-down command is issued and the memory device is in a first state. A second lower power state is entered if the power-down command is issued and if the memory device is in a second state. The second lower power state is lower than the first lower power state. The memory device remains in a normal operation power state if the power-down command is not issued.

Abstract: A memory controller apparatus and method for automatically detecting whether a particular memory unit location is unpopulated or populated with synchronous dynamic random access memories (DRAMs), or asynchronous fast page (FP) DRAMs or extended data out (EDO) DRAMs are disclosed. Logic in the memory controller detects a memory device type by writing a first data item to the memory device using at least a minimum common asynchronous memory write protocol meeting the write timing requirements of all asynchronous memory device types. An attempt is then made to read the first data from the memory device using a first asynchronous memory read protocol. If the first data is read from the memory device, the memory device is identified as being an asynchronous memory. If the first data is not read from the device, the memory control logic writes a second data item to the memory device using a synchronous memory write protocol.

Abstract: An embodiment of the invention is directed at a bridge having an outbound pipe for buffering transaction information and data being transported from various devices to a bus. The bridge has an arbiter for granting requests associated with these devices to access the outbound pipe for transferring the transaction information and data into the pipe. The bridge generates a reject signal in response to an initial request associated with an initial transaction from a first one of the devices if the outbound pipe is unavailable to accept further transaction information or data. The bridge has response control logic for generating a retry response for the initial transaction in response to the reject signal. The bridge is able to assert a stamp signal in response to the reject signal. The arbiter in response to the stamp being asserted waits, without granting any other lower priority requests to access the outbound pipe, until a subsequent transaction from the first device makes progress.

Abstract: A method and apparatus for decoupling internal latencies of a bus bridge from those on an external bus is described. In one embodiment, the method includes detecting a write cycle by an initiator for transmitting data to a device. The method further includes asserting a write request to the device, responsive to detecting the write cycle, asserting a ready request to the initiator without detecting an acknowledge from the device, and receiving the data from the initiator.

Abstract: A method and apparatus for accessing a memory resource, such as an array of DRAM modules, is described. The methodology commences with the receipt of a memory address during a memory access cycle. A row address is then generated by selecting predetermined bits of the memory address as the row address. Concurrently with the generation of the row address, a determination is made as to the configuration of a memory device within the memory resource and targeted by the memory address. Thereafter, a column address is generated by selecting bits of the memory address as the column address based on the configuration of the targeted memory device. The time required for the determination of the configuration of the targeted memory device is thus absorbed within the time expended generating the row address.

Abstract: A synchronizing circuit translates signals in a slow clock domain into a fast clock domain. The frequency of the slow clock is a submultiple of the fast clock frequency. A synchronizing pulse signal is developed at the frequency of the slow clock, but is phase synchronized to the fast clock. The synchronizing pulse signal is employed to gate the signal in the slow clock domain so that it is synchronized in the fast clock domain. In a system where the ratio between the fast clock frequency and slow clock frequency is determined by a frequency divisor signal, a snooping circuit is employed to capture the frequency divisor signal to achieve rapid synchronization between the clock domains.

Abstract: A method of transmitting a signal from a first clock domain to a second clock domain commences with the generation of first and second clock signals. The first and second clock signals are substantially synchronous and have respective frequencies that are non-integer multiples. A first signal, which is generated in the first clock domain responsive to a transition of the first clock signal that is substantially coincident with a transition of the second clock signal, is prevented from being latched in the second clock domain responsive to the transition of the second clock signal. The first clock signal is prevented from being latched for a time period which is greater than a maximum clock skew which may exist between the first and second clock signals.

Abstract: A method of transmitting a signal from a relatively fast clock domain to a relatively slow clock domain is described. The fast and slow clock domains operate according to respective fast and slow clock signals that are substantially synchronized and that have respective frequencies that are non-integer multiples. A first state of an input signal is latched at the commencement of a first period of the fast clock signal, the commencement of the first period of the fast clock signal being substantially coincident with the commencement of a first period of the slow clock signal. In response to the latching of the first state of the input signal, a first output signal is generated and held over the first period, and at least one further period, of the fast clock signal. The first output signal is then latched in the second time domain in response to the commencement of a second period of the slow clock signal, the second period being immediately subsequent to the first period of the slow clock signal.

Abstract: A method and apparatus for detecting DRAM symmetry. A memory address including a row address and a column address bit is forced to a known value regardless of the host bit which would otherwise be mapped thereto. If the forced bit is in the column address it should be a bit which is not used by an asymmetric DRAM of the depth in the system to be tested, but would be used in a symmetric DRAM of the same depth. Conversely, if the forced bit is in the row address the bit should be used in the asymmetric case but not in the symmetric case. It is important that regardless of what bit in the memory address is forced, the forced bit should not be used by both cases at the depth tested. A first and second known value, are written respectively to two memory addresses which differ only in the value which would normally be mapped to this forced bit. The forced bit will cause an overwrite if the DRAM is of the type which uses the forced bit in its addressing.

Abstract: Memory access control logic for controlling sequential and toggle mode burst accesses to a memory in a computer system using toggle mode automatic increment logic. The memory access control logic of the invention controls the sequence in which locations of a memory are accessed during a memory burst access operation wherein the burst access sequence is determined by an order in which a burst access starting address is incremented. Toggle increment logic for incrementing a starting address in a toggle sequence is included in the computer system in which the memory access control logic of the invention is used. An input bus receives a burst access request and a burst access starting address indicating a first memory location to be accessed in response to the burst access request from a device in the computer system. Additional logic determines whether the device requires a linear increment sequence or a toggle increment sequence for the burst access.

Abstract: A register address space is defined with a capacity large enough to accommodate substantial growth in the number of required registers. Unused register locations are reserved for future use. Access requests directed to reserved addresses are redirected to a physical register containing the same stored value that would be returned if a physical register were associated with the reserved address to which the access was originally directed. The physical register is separate from any central processing unit.

Abstract: A latching mechanism captures an address transmitted on a multiplexed address/data bus and preserves it for the full bus cycle. A transparent latch with a multiplexed feedback path allows the address to be quickly captured and decoded. An additional multiplexer and latch cooperate with the first mentioned latch to keep the address stable for a sufficient time to allow latching by slower memory elements. Additional elements are provided to automatically increment the address for multiple data burst operation.