Certain nonvolatile memories, such as a synchronous flash memory, that support “burst” data have a sense circuit that senses all data within a maximum non-continuous burst length at one time and places the data in an output buffer. On such devices, once an address is supplied to the device, it will wait for some initial latency count while all burst data starting from the initial address is sensed and transferred to the output buffer. The data is then output one unit per clock cycle until all sensed data is transferred to the requester.
In cases where the burst length requested by a memory controller is half of the sense width of the memory, half of the sensed data is not used by the controller. Even with address pipelining, if the initial latency count is more than the burst length, there are wasted bus cycles. Thus, there is a need for alternate ways to retrieve information from memory.
Turning to
Address latches 110 and 115 and output multiplexer 140 may temporarily store information. As used herein, the terms “information” and “data” may be used interchangeably, and may refer to both data and instructions. Address latches 110 and 115 and output multiplexer 140 may be, for example, registers, queues, or latches, although the scope of the present invention is not limited in this respect. Output multiplexer 140 may be adapted to store 256 bits of information, although the scope of the present invention is not limited in this respect. As shown in the embodiment of
In alternate embodiments, output multiplexer 140 may be adapted to store more or less than 256 bits of information. While shown as a single structure in
Address latches 110 and 115 may receive read requests from a memory controller (not shown in
After receiving read requests, sense arrays 130 and 135 may be used to sense the information at the requested addresses in memory array 120. Sense arrays 130 and 135 may include, for example, sense amplifiers (not shown) to sense the information stored in memory array 120. As shown in
After sensing the requested information from memory array 120, this information may be transferred to output multiplexer 140. The retrieved information may be transmitted from output multiplexer 140 via output stage 145 to a processor for use therein.
Control logic 150 may include circuitry to control the accessing and retrieval of information from memory array 120. For example, control logic 150 may be adapted to receive control, data, and/or address signals from a memory controller of a host system. In some embodiments, control logic 150 may decode a received address, store the decoded address in address latches 110 and 115, enable sense arrays 130 and 135 to sense information stored at the decoded address in memory array 120, and transfer the sensed information to output multiplexer 140. In certain embodiments, control logic 150 may also determine which address latch is enabled for a given sense operation, for example, by determining which latch has a valid address for read sensing. In certain embodiments, two read-state machine (RSM) latency counters may be used to keep track of two overlapping sense operations. In the embodiment of
Thus in certain embodiments, a bus data rate may be improved by separating a sense array (logically and/or physically) to sense data from more than one non-contiguous initial address. The bus rate may be optimized when a burst length requested by the controller is half of the sense width, in certain embodiments. For example in one embodiment, a 256 bit sense array may sense two word groups, each four double words long, and each from a different initial address. In such an embodiment, the two requests may be separated by four clock cycles, and half of the sense amplifiers in the array may be selected to sense each request. However, the scope of the present invention is not so limited, and in other embodiments a word group may be two or more units of data.
A memory device in accordance with one embodiment of the present invention may perform synchronous burst read operations. A synchronous read operation may refer to synchronously reading information from the memory device using a clock signal of a host system. That is, information may be synchronously transmitted between a processor, a memory controller, and the memory device using a common reference clock. A burst read may refer to retrieving more than one unit of data in response to a single read request. A unit of data may be a byte of data, a word of data, or a double word of data. It should be noted that the terms “byte,” “word,” “double word,” are terms denoting different units of data. As an example, in certain embodiments a byte of data may refer to eight bits of data, a word may refer to 16 bits of data, and a double word may refer to 32 bits of data, although the scope of the present invention is not limited in this regard.
Referring now to
In this embodiment, twenty-two clock cycles of a clock signal (labeled CLK) are illustrated. Address signals (labeled ADDRESS) may be transmitted to a memory device from a memory controller using a bus. As shown in
In this embodiment, fixed-length synchronous burst read operations are illustrated, in that a fixed number of words are requested during each read request. For example, initial read request X0 at clock cycle 0 requests the retrieval of four double words of information from addresses X0 through X3, respectively. In this example, one double word of information is located at each address. Similarly, the second read request (YO) at clock cycle 4 requests four double words of information respectively from addresses Y0 through Y3, and so forth for additional read requests.
The read requests may be referred to as burst read requests since more than one unit of data is transmitted from the memory device in response to a single read request. However, the amount of information retrieved in response to a single read request is not limited in this respect. Although four double word synchronous burst reads are illustrated in the timing diagram of
The Valid Address signal (labeled ADV#) may be transmitted to the memory device and may indicate that a valid address is available on the ADDRESS signal line.
During operation of a host system, read requests may be transferred from a memory controller to the memory device via a bus. In various embodiments, read requests may be received via input stage 105 at address latches 110 and 115 and/or control logic 150. In some embodiments, after receiving read requests, control logic 150 may enable retrieval of the information from memory array 120. For example, control logic 150 may enable sensing of word groups, such as four double word groups of information located at two different initial addresses of memory array 120. Sense arrays 130 and 135 may each sense the four double words of information from these locations, and control logic 150 may enable transfer of this information to output multiplexer 140. In alternate embodiments, control logic 150 may enable sense arrays 130 and 135 to sense eight double words from a single initial address.
The amount of time to retrieve information from memory device 140 in response to a read request may be referred to as a latency time or latency count and may be measured in terms of clock cycles of signal CLK. The latency count may be based on factors such as, for example, the processing speed of the memory device and other characteristics of the components of the memory device. In some embodiments, the time to retrieve information from a memory device in response to a read request may be programmable.
In the embodiment illustrated in
In the embodiment of
In the embodiment of
In the embodiment of
The reading of information as shown in
The memory device of
Further, embodiments may be implemented in a computer program, and stored on a storage medium (such as those described above) having stored thereon instructions which can be used to program a computer system, wireless device or the like to perform the embodiments.
The processor 310 may be coupled over a host bus 315 to a memory hub (i.e., a memory controller) 330 in one embodiment, which may be coupled to a system memory 320 via a memory bus 325. The memory hub 330 may also be coupled over an Advanced Graphics Port (AGP) bus 333 to a video controller 335, which may be coupled to a display 337. The AGP bus 333 may conform to the Accelerated Graphics Port Interface Specification, Revision 2.0, published May 4, 1998, by Intel Corporation, Santa Clara, Calif.
Memory hub 330 may control the transfer of information within system 300, e.g., between processor 310, memory hub 330, and memory 320. That is, memory hub 330 may generate control signals, address signals, and data signals that may be associated with a particular write or read operation to memory 320.
In some embodiments, memory hub 330 may be integrated with processor 310 and/or with memory 320. In alternate embodiments, memory hub 330 may be a discrete component or dedicated chip. In other embodiments, portions of the functionality of memory hub 330 may be implemented in processor 310 or in memory 320 as, for example, a software application, module, or routine.
The memory hub 330 may also be coupled (via a hub link 338) to an input/output (I/O) hub 340 that is coupled to a input/output (I/O) expansion bus 342 and a Peripheral Component Interconnect (PCI) bus 344, as defined by the PCI Local Bus Specification, Production Version, Revision 2.1 dated in June 1995, or alternately a bus such as the PCI Express bus, or another third generation I/O interconnect bus. The I/O expansion bus 342 may be coupled to an I/O controller 346 that controls access to one or more I/O devices. As shown in
The PCI bus 344 may be coupled to various components including, for example, a flash memory 360 which may include the structure shown in the block diagram of
Although the description makes reference to specific components of the system 300, it is contemplated that numerous modifications and variations of the described and illustrated embodiments may be possible. More so, while
While the present invention has been described with respect to a limited number of embodiments, those skilled in the art will appreciate numerous modifications and variations therefrom. It is intended that the appended claims cover all such modifications and variations as fall within the true spirit and scope of this present invention.
Number | Name | Date | Kind |
---|---|---|---|
5784331 | Lysinger | Jul 1998 | A |
6212121 | Ryu et al. | Apr 2001 | B1 |
6216180 | Kendall et al. | Apr 2001 | B1 |
6366497 | Guliani et al. | Apr 2002 | B1 |
6425062 | Kendall et al. | Jul 2002 | B1 |
6456540 | Baltar et al. | Sep 2002 | B1 |
6914830 | Merritt et al. | Jul 2005 | B2 |
6920534 | Dover | Jul 2005 | B2 |
20040019756 | Perego et al. | Jan 2004 | A1 |
20050135148 | Chevaillier et al. | Jun 2005 | A1 |
Number | Date | Country | |
---|---|---|---|
20040268075 A1 | Dec 2004 | US |