The present invention relates generally to memory devices and in a particular embodiment the present invention relates to non-volatile memory devices.
Memory devices can include internal, semiconductor, integrated circuits in computers or other electronic devices. There are many different types of memory including random-access memory (RAM), read only memory (ROM), dynamic random access memory (DRAM), static RAM (SRAM), synchronous dynamic RAM (SDRAM), and non-volatile memory.
Non-volatile memory devices (e.g., flash memory) have developed into a popular source of non-volatile memory for a wide range of electronic applications. Flash memory devices typically use a one-transistor memory cell that allows for high memory densities, high reliability, and low power consumption. Common uses for flash memory include personal computers, personal digital assistants (PDAs), digital cameras, and cellular telephones. Program code and system data such as a basic input/output system (BIOS) are typically stored in flash memory devices for use in personal computer systems.
Non-volatile memory devices are also incorporated into solid state storage devices such as solid state drives. Solid state drives can be used in computers to replace the hard disk drives that typically have used magnetic or optical disks for storing large amounts of data. A solid state drive does not use moving parts whereas a hard disk drive requires a complex and sensitive drive and read/write head assembly to interact with the magnetic/optical disk. Thus, the solid state drives are more resistant to damage and loss of data through vibration and impacts.
One drawback to current solid state drive technology is achieving the memory density necessary to adequately and cost effectively replace a computer's hard disk drive. Most modern computers require the capability for storing very large amounts of data (e.g., 250 GB or more) due to digital images, movies, and audio files. Thus, an effective solid state drive should have a memory density approaching a typical hard drive, remain cost competitive, and still fit within the constantly decreasing thickness of a laptop computer or within the constraints of an enterprise storage system, for example.
For the reasons stated above, and for other reasons stated below that will become apparent to those skilled in the art upon reading and understanding the present specification, there is a need in the art for a way to increase the memory density of a solid state drive while maintaining or reducing the size.
In the following detailed description of the invention, reference is made to the accompanying drawings that form a part hereof and in which is shown, by way of illustration, specific embodiments in which the invention may be practiced. In the drawings, like numerals describe substantially similar components throughout the several views. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims and equivalents thereof.
The memory array comprises an array of non-volatile memory cells 201 (e.g., floating gate) arranged in columns such as series strings 204, 205. Each of the cells 201 are coupled drain to source in each series string 204, 205. An access line (e.g. word line) WL0-WL31 that spans across multiple series strings 204, 205 is connected to the control gates of each memory cell in a row in order to bias the control gates of the memory cells in the row. Data lines, such as bit lines BL1, BL2 are eventually connected to sense amplifiers (not shown) that detect the state of each cell by sensing current on a particular bit line.
Each series string 204, 205 of memory cells is coupled to a source line 206 by a source select gate 216, 217 and to an individual bit line BL1, BL2 by a drain select gate 212, 213. The source select gates 216, 217 are controlled by a source select gate control line SG(S) 218 coupled to their control gates. The drain select gates 212, 213 are controlled by a drain select gate control line SG(D) 214.
Each memory cell can be programmed as a single level cell (SLC) or multilevel cell (MLC). Each cell's threshold voltage (Vt) is indicative of the data that is stored in the cell. For example, in an SLC, a Vt of 0.5V might indicate a programmed cell while a Vt of −0.5V might indicate an erased cell. The MLC may have multiple Vt windows that each indicate a different state. Multilevel cells can take advantage of the analog nature of a traditional flash cell by assigning a bit pattern to a specific voltage range stored on the cell. This technology permits the storage of two or more bits per cell, depending on the quantity of voltage ranges assigned to the cell.
The non-volatile memory device 300 includes an array 330 of non-volatile memory cells such as the floating gate memory cells that are illustrated in
The memory array 330 can be organized into memory blocks. The quantity of memory blocks is typically determined by the size of the memory device (i.e., 512 MB, 1 GB). In one embodiment, each memory block is organized into 64 pages.
Address buffer circuitry 340 is provided to latch address signals provided through the I/O circuitry 360. Address signals are received and decoded by a row decoder 344 and a column decoder 346 to access the memory array 330. It will be appreciated by those skilled in the art, with the benefit of the present description, that the number of address input connections depends on the density and architecture of the memory array 330. That is, the number of addresses increases with both increased memory cell counts and increased bank and block counts. Data is also input and output through the I/O circuitry 360 based on the timing of the control signals 372.
The non-volatile memory device 300 reads data in the memory array 330 by sensing voltage or current changes in the memory array columns using sense amplifier circuitry 350. The sense amplifier circuitry 350, in one embodiment, is coupled to read and latch a row of data from the memory array 330. Data input and output buffer circuitry 360 is included for bidirectional data communication as well as address communication over a plurality of data connections 362 with an external controller. Write circuitry 355 is provided to write data to the memory array.
The memory control circuitry 370 decodes signals provided on control bus 372 from an external controller. These signals can include read/write (R/
The non-volatile memory device 300 communicates with an external controller over a channel 390. In one embodiment, the channel 390 comprises the memory address, data, and control signals between the external controller and the memory device 300. The embodiment of
The embodiment of
Each controller 501, 502 is configured with a host interface 520, 521 over which the controller communicates with external devices/systems such as computers and cameras. The host interface 520, 521 can be parallel ATA, SATA, SAS, PCIe, Fiber Channel, SCSI, Gigabit Ethernet, or some other communication standard channel.
Use of the host interface 521 for the slave controller is not necessary for proper operation of the solid state storage device of
Each controller 501, 502 includes a mode select input 530, 531 that determines whether the controller operates as a master or a slave. The mode select input 530, 531 enables the controllers to be virtually identical so that the manufacturer is not required to manufacture and track different types of controllers.
In the illustrated embodiment, a logical high signal on the mode select input 530 causes the top controller 501 to operate in the master mode. The logical high signal is generated by pulling up the mode select input 530 to VCC through a resistor. A logical low signal on the mode select input 531 causes the bottom controller 502 to operate in the slave mode. The logical low signal is generated by connected the mode select input 531 to ground potential.
Each controller 501, 502 further comprises communication channels 510, 511 as discussed previously. In the illustrated embodiment, each channel is used to communicate with four stacked memory devices 540, 541. However, the number of memory devices used in each channel is not limited to four. Alternate embodiments can use more or less memory devices. There are, however, limitations to the number of devices which may be placed on a memory channel. These limitations arise from the loading of the channel and the addressing of devices on the channel. Loading limitations occur because each device on a channel presents an electrical load, primarily capacitive, on the channel. Adding capacitance to the channel requires a corresponding increase in channel drive current, or the speed of the channel must be lowered.
Channels 0-7 in each controller 501, 502 are used to communicate with the memory devices 540, 541. Channels 8 and 9512, 513 of each controller 501, 502 are used to communicate with the other controller 501, 502. Alternate embodiments can use different channels for communicating with the memory devices and different channels for communicating between controllers.
The communication between the controllers 501, 502 enables the controllers to operate in a parallel mode. While the master controller 501 is communicating with its memory devices 540, the slave controller 502 can be communicating with its memory devices 541. The two common communication channels 512, 513 between the controllers 501, 502 enable the master controller 501 to send operating instructions to the slave controller 502. The common channels 512, 513 also enable the master controller 501 to send data, addresses, and control signals that are addressed to the memory devices that are controlled by the slave controller 502.
If the host interface 521 of the slave controller 502 is not used or not able to be used, the slave controller 502 can transmit data read from the memory devices 541 to the master controller 501 for output through the host interface 520. Similarly, the master controller 501 can transmit data to the slave controller 502, through the shared communication channels 512, 513, to be stored in the memory devices 541 of the slave controller 502.
In order to increase the capacity of the solid state storage device, two or more additional communication channels from the master controller 501 and/or the slave controller 502 can be used for one or more additional slave controllers to operate in parallel with the other controllers 501, 502. Since each slave controller has the potential to communicate with eight communication channels, the memory capacity of the solid state storage device can be greatly increased by adding additional slave controllers operating in the parallel mode.
The controller comprises a communication controller block 601 that generates the control signals for the memory devices. As previously discussed, these control signals can include the chip enable and read/write signals as well as other memory control signals.
A memory sequencer block 603 generates the timing and commands necessary for operation of the memory devices. The sequencer block 603 controls an access process to write and/or read the memory devices on each channel. For example, the sequencer block 603 can generate the control signals that control the select gate drain and select gate source transistors as described with reference to
A multiplexer circuit 609 selects between the output of the communication controller 601 and the output of the memory sequencer 603 and outputs the selected input over the memory communication channel 611. The select control input of the multiplexer 609 is generated by a register 605, logic 607, and the input master/
The register 605, in one embodiment, is a one bit storage device such as a flip-flop. The register 605 is set and reset (i.e., logical “1” and logical “0” respectively) by other circuitry of the memory controller 501. One state is used to select the communication controller 601 and the other state is used to select the memory sequencer 603.
The logic circuit 607 is responsible for combining the register 605 output and the master/
In one embodiment of operation, the parallel mode output signal from the logic 607 is derived from the contents of the register 605 if the master/
The embodiment illustrated in
Once the functions of the memory controllers are set, communication is performed with the memory devices through both the master and slave controllers 705. The master and slave controllers are now operating in the parallel operation mode.
In summary, one or more embodiments enable a solid state storage device controller to operate in a parallel operation mode. By using communication channels from a master controller to communicate with slave controllers, the memory density of a solid state storage device can be increased.
Although specific embodiments have been illustrated and described herein, it will be appreciated by those of ordinary skill in the art that any arrangement that is calculated to achieve the same purpose may be substituted for the specific embodiments shown. Many adaptations of the invention will be apparent to those of ordinary skill in the art. Accordingly, this application is intended to cover any adaptations or variations of the invention. It is manifestly intended that this invention be limited only by the following claims and equivalents thereof.
This is a continuation of U.S. Ser. No. 12/241,636 titled “SOLID STATE STORAGE DEVICE CONTROLLER WITH PARALLEL OPERATION MODE”, filed on Sep. 30, 2008 now U.S. Pat. No. 8,244,937 (allowed), that is commonly assigned and incorporated herein by reference.
Number | Name | Date | Kind |
---|---|---|---|
5430859 | Norman et al. | Jul 1995 | A |
5463643 | Gaskins et al. | Oct 1995 | A |
5887150 | Schneider et al. | Mar 1999 | A |
6145041 | Chambers | Nov 2000 | A |
6401154 | Chiu et al. | Jun 2002 | B1 |
6813678 | Sinclair et al. | Nov 2004 | B1 |
20050154288 | Wang et al. | Jul 2005 | A1 |
20050169061 | Sohn et al. | Aug 2005 | A1 |
20070198856 | Lee et al. | Aug 2007 | A1 |
20090307389 | Sprouse et al. | Dec 2009 | A1 |
20100095053 | Bruce et al. | Apr 2010 | A1 |
Entry |
---|
Agrawal et al., “Design Tradeoff for SSD Performance”, USENIX '08: 2008 USENIX Annual Technical Conference, pp. 57-70. |
Number | Date | Country | |
---|---|---|---|
20120284454 A1 | Nov 2012 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 12241636 | Sep 2008 | US |
Child | 13552764 | US |