KR20160144557A - Nonvolatile memory module, storage device, and electronic device transmitting read data in transmission unit - Google Patents

Abstract

The present invention provides a nonvolatile memory module comprising one or more nonvolatile memories and a device controller. When a read request relating to read data stored in at least a prepared one of the nonvolatile memories, the device controller transmits one of a plurality of transmission unit data in response to the preparation of each of the transmission unit data forming the read data. The transmission unit data are transmitted to the host one by one regardless of the order of forming the read data. According to the present invention, a RAM having a small capacity is employed, so that an area occupied by the RAM and the implementation cost of a device are reduced.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a nonvolatile memory module, a storage device, and an electronic device,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an electronic device, and more particularly, to an operation performed between a host device and a non-volatile memory module or storage device configured to store data.

A computing system such as a personal computer includes various types of components. For example, the computing system includes various components such as a main processor, a main memory device, a storage device, a graphic processor, an input / output device, and the like. Further, the computing system includes a number of buses configured to connect its components.

Each of the components included in the computing system is connected to the bus and communicates with each other. The bus connecting several components may be different from the bus connecting several other components. In this case, the bandwidth supported by one bus may be different from the bandwidth supported by the other bus. A bus with a higher bandwidth can operate faster than a bus with a lower bandwidth.

By way of example, the main memory device and the graphics processor may be connected to the main processor via a bus operating at a high speed. On the other hand, the storage device and the input / output device can be connected to the main processor through a bus operating at a relatively slow speed. That is, several buses can operate at different performance.

Description of the Related Art [0002] In recent years, a technology related to a storage device is rapidly developing. Semiconductor storage mediums such as solid state drives (SSD) replace mechanical storage media such as hard disk drives (HDDs), thereby improving the performance and reliability of storage devices. However, when the storage device is connected to the main processor through a bus operating at a relatively slow speed, the operation performance of the storage device may be degraded. Particularly, when a storage device having high operation performance such as an SSD is connected to a bus operating at a slow speed, it is difficult to maximize the performance of the storage device.

To solve the above problems and to maximize the performance of the storage device, a storage device is provided that is configured to communicate with the host via a bus operating at high speed. Further, a scheme of a read operation is provided for realizing a storage device at a low cost and efficiently operating the storage device.

A non-volatile memory module according to an embodiment of the present invention may include one or more non-volatile memories and a device controller. When a read request relating to read data stored in at least one of the nonvolatile memories is received from the host, the device controller, in response to the preparation of each of the plurality of transfer unit data forming the read data, Lt; / RTI > Each of the plurality of transmission unit data can be transmitted to the host regardless of the order of forming the read data.

In the nonvolatile memory module according to an embodiment of the present invention, the device controller can generate notification data indicating preparation of each of a plurality of transmission unit data. Each of the plurality of transmission unit data can be transmitted to the host based on the notification data.

In the nonvolatile memory module according to an embodiment of the present invention, whether or not all of a plurality of transmission unit data is transmitted to the host can be managed by the host.

In a non-volatile memory module according to an embodiment of the present invention, the device controller may operate according to an interface specification defined by a DIMM specification. Further, the command signal corresponding to the read request is received through the data input / output pin defined in the DIMM specification, and the data signal corresponding to each of the plurality of transfer unit data can be transmitted to the host through the data input / output pin.

A storage device according to another embodiment of the present invention may include one or more non-volatile memories and a device controller. The device controller may send read data stored in at least one of the non-volatile memories to the host in response to a request from the host. The device controller may include a physical layer and a controller. The physical layer may include a RAM, and a RAM controller configured to control the RAM according to a RAM command and a RAM address provided from the host. The controller reads out the read data from the position of the nonvolatile memories corresponding to the storage address and divides the read data based on the storage command and the storage address which are provided from the host and stored in the RAM, The physical layer and non-volatile memories can be controlled to be temporarily stored. The device controller can transmit read data by transmitting each of a plurality of transmission unit data to the host.

In the storage apparatus according to another embodiment of the present invention, the device controller can store the notification data in the RAM. The notification data indicates storage of each of the plurality of transmission unit data in the RAM and may include information on the position in the read data of each of the plurality of transmission unit data.

In the storage apparatus according to another embodiment of the present invention, at least one of the plurality of transmission unit data may include an invalid portion not included in the read data. In this embodiment, the notification data may further include information on the invalid portion. Furthermore, the invalid portion may be discarded by the host based on the notification data, and data excluding the invalid portion in the plurality of transmission unit data may be combined into the read data in the host.

An electronic device according to another embodiment of the present invention may include at least one storage device and at least one processor. The processor may provide a read request to the storage device for read data stored on the storage device. In response to the read request, the storage device may prepare to transmit each of the plurality of transmission unit data forming the read data to the processor and generate notification data regarding the preparation of each of the plurality of transmission unit data. The processor can receive prepared data among a plurality of transmission unit data by referring to the notification data.

According to the embodiment of the present invention, instead of waiting until the read data is completely prepared, the transmission unit (Transmission Unit) data forming the read data is prepared, ) May be employed. Thus, the area occupied by the RAM and the implementation cost of the storage device can be reduced. Furthermore, by managing the completion of the read operation by the host, the work load of the storage apparatus can be reduced.

1 is a block diagram illustrating a computing system including a storage device according to an embodiment of the present invention.
2 is a conceptual diagram showing a software layer of the computing system of FIG.
FIGS. 3 to 7 are block diagrams showing embodiments of the configuration of the storage apparatus of FIG. 1. FIG.
8 is a block diagram illustrating a storage system including the storage device of FIG.
FIG. 9 is a conceptual diagram showing the configuration of the RAM of FIG. 8 and the communication between the processor, the RAM, and the controller.
10 is a flowchart for explaining a write operation of the storage apparatus of FIG.
11 is a conceptual diagram showing a read operation of the storage apparatus of FIG.
Fig. 12 is a flowchart for explaining a read operation of the storage apparatus of Fig. 8;
FIG. 13 is a conceptual diagram showing transmission of transmission unit data and notification data during the reading operation of FIGS. 11 and 12. FIG.
FIG. 14 is a conceptual diagram illustrating a process of transmitting transmission unit data from a storage apparatus to a host apparatus by referring to the notification data of FIG. 13 according to the reading operation of FIGS. 11 and 12. FIG.
FIG. 15 is a conceptual diagram showing a process of acquiring read data by discarding an invalid portion and combining a valid portion in transmission unit data transmitted according to the reading operation of FIGS. 11 and 12. FIG.
16 is a block diagram showing one of the nonvolatile memories of FIG.
17 is a conceptual diagram showing one memory block of the memory cell array of FIG.
18 is a conceptual diagram showing a server system including a storage apparatus according to an embodiment of the present invention.

The foregoing features and the following detailed description are exemplary of the invention in order to facilitate a description and understanding of the invention. That is, the present invention is not limited to these embodiments, but may be embodied in other forms. The following embodiments are merely examples for the purpose of fully disclosing the present invention and are intended to convey the present invention to those skilled in the art. Thus, where there are several ways to implement the components of the present invention, it is necessary to make it clear that the implementation of the present invention is possible by any of these methods or any of the equivalents thereof.

It is to be understood that, in the context of this specification, when reference is made to a configuration including certain elements, or when it is mentioned that a process includes certain steps, other elements or other steps may be included. In other words, the terms used herein are for the purpose of describing specific embodiments only, and are not intended to limit the concept of the present invention. Further, the illustrative examples set forth to facilitate understanding of the invention include its complementary embodiments.

The terms used in this specification are meant to be understood by those of ordinary skill in the art to which this invention belongs. Commonly used terms should be construed in a manner consistent with the context of this specification. Also, terms used in the specification should not be construed as being excessively ideal or formal in nature unless the meaning is clearly defined. BRIEF DESCRIPTION OF THE DRAWINGS Fig.

1 is a block diagram illustrating a computing system including a storage device according to an embodiment of the present invention. 1, a computing system 1000 includes a processor 1100, one or more RAM Module devices 1210 and 1212, one or more storage devices 1220 and 1222 of a first type, Chipset 1300, a graphics processing unit (GPU) 1400, an input / output device 1500, and a second type of storage device 1600.

The computing system 1000 may be implemented as an electronic device. By way of example, computing system 1000 may include at least one of a variety of electronic devices such as a personal computer, a notebook, a tablet, a workstation, a blade server, a network storage, However, the present invention is not limited by this example.

The processor 1100 may control the overall operations of the computing system 1000. The processor 1100 may be a host that includes a plurality of storage devices 1210 and 1212, a first type of storage devices 1220 and 1222, a GPU 1400, an input / output device 1500, Services may be provided from the storage device 1600. [

The processor 1100 may perform various arithmetic and / or logic operations to operate the computing system 1000. Processor 1100 may include one or more processor cores configured to perform operations. For example, depending on the type of computing system 1000, the processor 1100 may include at least one of a Central Processing Unit (CPU), an Application Processor (AP), a dedicated processor, and an Application Specific Integrated Circuit (ASICs) .

The RAM module devices 1210 and 1212 may temporarily store data to be processed or processed by the processor 1100. The RAM module devices 1210 and 1212 may be used as an operation memory, a working memory, or a buffer memory of the computing system 1000. For example, each of the RAM module devices 1210 and 1212 may include volatile memory such as DRAM (Dynamic Random Access Memory), SRAM (Static RAM), and SDRAM (Synchronous DRAM) Magneto-resistive RAM), ReRAM (Resistive RAM), and non-volatile memory such as Ferro-electric RAM (FRAM).

The first type of storage devices 1220 and 1222 may store data regardless of the power supply. The first type of storage devices 1220, 1222 can store data permanently or semi-permanently without powering. By way of example, each of the first type of storage devices 1220 and 1222 may include at least one of a flash memory, a PRAM, an MRAM, a ReRAM, and a non-volatile memory such as a FRAM.

The first type of storage devices 1220 and 1222 may be implemented based on embodiments of the present invention. Embodiments of the first type of storage devices 1220 and 1222 will be described in detail with reference to FIGS. 2 to 18. FIG.

The RAM module devices 1210 and 1212 and the first type of storage devices 1220 and 1222 may be coupled to the processor 1100 through a bus 1230 operating at a high speed. For example, the bus 1230 may support a device implemented as a DIMM (Dual Inline Memory Module), and may employ an interface protocol that operates in a DDR (Double Data Rate) manner. In this example, each of the first type of storage devices 1220 and 1222 may be implemented as a "non-volatile memory module ". The RAM module devices 1210 and 1212 and the first type of storage devices 1220 and 1222 are connected to the processor 1210 through the bus 1230. In this case, 1100).

In Figure 1, a computing system 1000 is shown comprising two RAM module devices 1210, 1212 and two first type storage devices 1220, 1222. However, the number of RAM module devices and the number of storage devices of the first type may be variously modified or modified depending on the configuration of the computing system 1000 and the configuration of the bus 1230.

The chipset 1300 may connect other components of the computing system 1000 to the processor 1100. By way of example, the chipset 1300 may connect a graphics processing unit (GPU) 1400, an input / output device 1500, and a second type of storage device 1600 to the processor 1100. By way of example, chipset 1300 may include a Southbridge chipset.

By way of example, GPU 1400 may perform operations to process image data. To this end, GPU 1400 may include one or more cores and one or more memories. The GPU 1400 may provide the results of operations to the processor 1100 via the chipset 1300 or may be provided with the results of operations of the processor 1100. The GPU 1400 can cause the display device to display an image based on the calculation result.

The input / output device 1500 may provide information provided by a user of the computing system 1000 to the processor 1100 through the chipset 1300. [ Alternatively, the input / output device 1500 may provide services to a user of the computing system 1000 based on data provided from the processor 1100 via the chipset 1300. [ For example, the input / output device 1500 may include an input interface such as a keyboard, a keypad, a button, a touch panel, a touch screen, a touch pad, a touch ball, a camera, a microphone, a gyroscope sensor, Further, the input / output device 1500 may include an output interface such as a speaker, a motor, and the like.

The second type of storage device 1600 may store data regardless of the power supply. By way of example, the second type of storage device 1600 may include a storage medium such as a solid state drive (SSD), a hard disk drive (HDD), or the like.

Unlike the first type of storage devices 1220 and 1222, the second type of storage device 1600 can be coupled to the processor 1100 via a bus operating at a relatively slow rate. By way of example, if the second type of storage device 1600 includes an SSD, a bus operating at a slower rate may degrade the performance of the second type of storage device 1600. [ Because SSDs include their own processors and fast-running semiconductor non-volatile memory, SSDs can have high operating performance. However, when the SSD is connected to a bus operating at a slow speed, it is difficult to maximize the performance of the SSD.

In an embodiment of the present invention, the first type of storage devices 1220, 1222 coupled to the processor 1100 via the bus 1230 operating at high speed may exhibit high operating performance. That is, a storage device including a semiconductor non-volatile memory, such as an SSD, can operate at higher performance when implemented in the form of first type storage devices 1220, 1222.

In the following, the configuration and operation of the first type of storage devices 1220 and 1222 connected to the processor 1100 through the bus 1230 operating at high speed will be described. Quot; storage device "is a first type of storage device coupled to the processor 1100 via a bus 1230 operating at high speed. It is assumed that the bus 1230 operating at a high speed employs an interface protocol defined on the basis of a DIMM specification. However, this assumption is intended to assist the understanding of the present invention, and the present invention is not limited by this assumption. Here, the DIMM specification refers to a specification regarding the configuration and operation of a device implemented in the form of a DIMM.

2 is a conceptual diagram showing a software layer of the computing system of FIG. In the processor 1100 of FIG. 1, software related to a host layer (HL) may be driven. Further, in the storage device of FIG. 1 (i.e., the "first type" storage device 1220 or 1222), software or firmware related to the storage layer (SL)

The host layer HL may include a first host layer HL1 and a second host layer HL2. The storage layer SL may include a first storage layer SL1 and a second storage layer SL2. The first host layer HL1 and the first storage layer SL1 may be provided as physical layers of the host layer HL and the storage layer SL, respectively.

For example, the first host layer HL1 may include a DIMM layer DL1, and the first storage layer SL1 may include a DIMM layer DL2. In this example, the host layer HL and the storage layer SL can physically access each other through the DIMM layers DL1 and DL2 based on the physical address. By way of example, the host layer HL and the storage layer SL can communicate via the DIMM layers DL1 and DL2 according to an interface protocol defined based on the DIMM specification.

As will be described in more detail with reference to FIG. 8, the first storage layer SL1 may include a RAM RM. The second storage layer SL2 may include a nonvolatile memory NM. The nonvolatile memory NM may permanently or semi-permanently store data provided from the host layer HL under the control of the control layer CL of the second storage layer SL2. Further, according to the control of the control layer CL, management operations such as garbage collection, wear leveling, and the like regarding the nonvolatile memory NM can be performed.

In some embodiments of the present invention, the DIMM layer DL2 may be provided with a RAM command and a RAM address that are used to control the RAM RM from the host layer HL. The RAM (RM) can temporarily store the storage command and the storage address used for controlling the nonvolatile memory (NM) according to the RAM command and the RAM address. In addition, the RAM RM may temporarily store write data to be stored in the nonvolatile memory NM and / or read data read from the nonvolatile memory NM. This embodiment will be described in more detail with reference to Figs. 8 to 15. Fig.

The first host layer HL1 may include a RAM driver RD for interfacing with the RAM RM. The second host layer HL2 may include an operating system (OS) for operating the host layer HL. The operating system (OS) may control and manage the overall operations of the computing system 1000 of FIG. By way of example, an operating system (OS) can handle various operations such as program execution, access to files, activation of applications (AP), control of the storage layer (SL) The second host layer HL2 may execute one or more applications AP to provide various services to the user of the host layer HL.

Depending on the operation of the operating system (OS) and / or the application (AP), the host layer HL may provide write data to be stored in the nonvolatile memory NM to the storage layer SL. Alternatively, the storage layer SL may provide the host layer (HL) with read data used for operation of the operating system (OS) and / or the application (AP) among data stored in the nonvolatile memory (NM). Each of the second host layer HL2 and the second storage layer SL2 can logically recognize the other party based on a logical address.

3 is a block diagram showing an embodiment of the configuration of the storage apparatus of FIG. At least one of the first type of storage devices 1220, 1222 of FIG. 1 may include the storage device 2000 of FIG. As an example, the storage device 2000 may be a non-volatile memory module implemented as an LRDIMM (Load Reduced DIMM). In this example, the storage device 2000 is connected to a DIMM socket of the computing system 1000 of FIG. 1 and is capable of communicating with the processor 1100 of FIG. 1 in accordance with an interface protocol defined based on the DIMM specification.

3, the storage device 2000 may include a device controller 2100, one or more non-volatile memories 2200, a buffer memory 2300, and a Serial Presence Detect (SPD) have. The device controller 2100 can control and manage the overall operations of the storage device 2000.

The non-volatile memories 2200 can store data regardless of the power supply, under the control of the device controller 2100. By way of example, non-volatile memories 2200 may be implemented as a single chip or package. Alternatively, each of the non-volatile memories 2200 may be implemented as a separate chip, package, device, or module. The buffer memory 2300 can buffer the read data to be stored in the non-volatile memories 2200 or the read data to be read from the non-volatile memories 2200 under the control of the device controller 2100.

The device controller 2100 can receive the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK from the processor 1100 through the control signal line. The RAM command CMD_R and the RAM address ADDR_R can be used to control the read / write operation with respect to the RAM 2100b. The device controller 2100 can exchange data signals DQ and data strobe signals DQS with the processor 1100 through a data signal line different from the control signal line.

In an embodiment of the present invention, the data signal DQ may include a storage command and a storage address that are used to control read / write operations with respect to the non-volatile memories 2200. Further, the data signal DQ may include write data to be stored in the non-volatile memories 2200 or read data to be read from the non-volatile memories 2200. In some cases, the data signal DQ may include status information regarding write data and read data.

The RAM 2100b may temporarily store the storage command and the storage address according to the RAM command and the RAM address. In addition, the RAM 2100b may temporarily store the write data and the read data according to the RAM command and the RAM address. The device controller 2100 is configured to store write data in the nonvolatile memories 2200 or read data in the nonvolatile memories 2200 according to the storage command and the storage address stored in the RAM 2100b, (2200).

The device controller 2100, the RAM 2100b, the nonvolatile memories 2200, and the buffer memory 2300 can be configured and operated as described with reference to Figs. 8-15. As an example, when a read request is received from a host (e.g., processor 1100 of FIG. 1) for read data stored in at least one of non-volatile memories 2200, Each of a plurality of transmission unit data (transmission unit data) generated by dividing data may be temporarily stored in the RAM 2100b and then output as a data signal DQ.

In the above embodiment, instead of waiting for the read data to be fully prepared, the RAM 2100b having a small capacity can be employed by transferring each of the transfer unit data forming the read data as it is prepared. Thus, the area occupied by the RAM 2100b and the implementation cost of the storage device 2000 can be reduced.

As an example, the completion of a read operation (i.e., transmission of all transmission unit data) may be managed by a host (e.g., processor 1100 of FIG. 1) rather than by storage apparatus 2000. Thus, the work load of the storage apparatus 2000 can be reduced. Embodiments of the present invention will be described in more detail with reference to Figs. 8 to 15. Fig.

The SPD chip 2500 may store information on the characteristics of the storage device 2000. [ As an example, the SPD chip 2500 may store initialization information or device information such as the module type, module configuration, storage capacity, line layout, operating environment, etc. of the storage device 2000. By way of example, the SPD chip 2500 may include a programmable read-only memory (e.g., an Electrically Erasable Programmable Read Only Memory (EEPROM)).

 The processor 1100 of the computing system 1000 may read information stored in the SPD chip 2500 when the computing system 1000 including the storage device 2000 is booted. The processor 1100 can recognize and operate the storage device 2000 based on the read information. In an embodiment of the present invention, the processor 1100 can recognize and operate the storage device 2000 as a storage medium based on the information read.

As an example, the SPD chip 2500 may communicate with the processor 1100 based on a side-band interface convention. In this embodiment, the SPD chip 2500 and the processor 1100 can send and receive a side-band signal SBS over a communication channel supporting the side-band interface protocol. Further, the SPD chip 2500 may communicate with the device controller 2100 based on a side-band interface convention. By way of example, the side-band interface protocol may support a physical layer defined based on an I2C (Inter-Integrated Circuit) or UART (Universal Asynchronous Receiver / Transmitter) specification.

4 is a block diagram showing an embodiment of the configuration of the storage apparatus of FIG. At least one of the first type of storage devices 1220, 1222 of FIG. 1 may include the storage device 3000 of FIG. By way of example, the storage device 3000 may be a non-volatile memory module implemented in the form of an RDIMM (Registered DIMM). In this example, the storage device 3000 is connected to a DIMM socket of the computing system 1000 of FIG. 1 and is capable of communicating with the processor 1100 of FIG. 1 in accordance with an interface convention defined based on the DIMM specification.

4, the storage device 3000 includes a device controller 3100, one or more non-volatile memories 3200, a buffer memory 3300, a data buffer circuit 3400, and an SPD chip 3500 can do. The device controller 3100, the RAM 3100b, the nonvolatile memories 3200, and the buffer memory 3300 can be configured and operated as described with reference to Figs. 8-15.

As an example, when a read request is provided from a host (e.g., processor 1100 of FIG. 1) for read data stored in at least one of non-volatile memories 3200, Each of a plurality of transmission unit data generated by dividing data may be temporarily stored in the RAM 3100b and then output as a data signal DQ. In this embodiment, instead of waiting for the read data to be fully prepared, the RAM 3100b with a small capacity can be employed by transferring each of the transfer unit data forming the read data as it is prepared. Therefore, the area occupied by the RAM 3100b and the implementation cost of the storage apparatus 3000 can be reduced.

As an example, the completion of the read operation (i.e., transmission of all transmission unit data) may be managed by the host (e.g., processor 1100 of FIG. 1) rather than by storage apparatus 3000. Thus, the operation load of the storage apparatus 3000 can be reduced. Embodiments of the present invention will be described in more detail with reference to Figs. 8 to 15. Fig.

The device controller 3100, the RAM 3100b, the nonvolatile memories 3200, the buffer memory 3300 and the SPD chip 3500 correspond to the device controller 2100, the RAM 2100b, the nonvolatile memories The buffer memory 2300, and the SPD chip 2500, respectively. Redundant descriptions of the device controller 3100, the RAM 3100b, the nonvolatile memories 3200, the buffer memory 3300, and the SPD chip 3500 will be omitted.

The data buffer circuit 3400 can exchange the data signal DQ and the data strobe signal DQS with the processor 1100. The data buffer circuit 3400 may provide the received signal to the device controller 3100 or may receive the signal to be transmitted from the device controller 3100. [ That is, the data buffer circuit 3400 can buffer the data between the processor 1100 and the device controller 3100. As an example, the data buffer circuit 3400 may be used to synchronize the timing of data transmission.

By way of example, data buffer circuit 3400 may include one or more data buffers. Each of the data buffers may receive or output a data signal DQ and a data strobe signal DQS via a corresponding data signal line. The data buffers may operate under the control of the device controller 3100.

5 is a block diagram showing an embodiment of the configuration of the storage apparatus of FIG. At least one of the first type of storage devices 1220 and 1222 of FIG. 1 may include the storage device 4000 of FIG. By way of example, the storage device 4000 may be implemented as a non-volatile memory module coupled to a DIMM socket of the computing system 1000 of FIG. In this example, the storage device 4000 may communicate with the processor 1100 of FIG. 1 in accordance with an interface convention defined based on the DIMM specification.

In the embodiment of FIG. 5, the storage device 4000 may include a control circuit 4005, one or more non-volatile memories 4200, and one or more DRAMs 4600. The non-volatile memories 4200 may be utilized as a storage medium of the computing system 1000. The DRAMs 4600 may be used as the main memory of the computing system 1000. That is, the storage apparatus 4000 can perform the function of the main memory together with the function of the storage medium.

By way of example, non-volatile memories 4200 may include at least one of EEPROM, flash memory, PRAM, MRAM, ReRAM, and FRAM. In FIG. 5, the storage device 4000 is shown as including DRAMs 4600. However, in some other embodiments, DRAMs 4600 may be replaced with other memories that are randomly accessed, such as SRAM, SDRM, PRAM, MRAM, ReRAM, and FRAM.

The control circuit 4005 may include a device controller 4100 and an SPD chip 4500. The device controller 4100 and the non-volatile memories 4200 may be configured and operated as described with reference to Figs. 8-15. As an example, when a read request is received from a host (e.g., processor 1100 of FIG. 1) for read data stored in at least one of non-volatile memories 4200, Each of the plurality of transfer unit data generated by dividing the data may be temporarily stored in the RAM 4100b and then output as the data signal DQ.

In the above embodiment, instead of waiting until the read data is fully prepared, the RAM 4100b having a small capacity can be employed by transmitting each transfer unit data forming the read data as it is prepared. Thus, the area occupied by the RAM 4100b and the implementation cost of the storage device 4000 can be reduced.

As an example, the completion of a read operation (i.e., transmission of all transmission unit data) may be managed by a host (e.g., processor 1100 of FIG. 1), and not by storage apparatus 4000. Thus, the operation load of the storage apparatus 4000 can be reduced. Embodiments of the present invention will be described in more detail with reference to Figs. 8 to 15. Fig.

The device controller 4100, the RAM 4100b, the nonvolatile memories 4200 and the SPD chip 4500 correspond to the device controller 2100, the RAM 2100b, the nonvolatile memories 2200, and the SPD Chip 2500 may be configured and operated in the same or similar manner, respectively. For convenience of description, redundant descriptions of the device controller 4100, the RAM 4100b, the nonvolatile memories 4200, and the SPD chip 4500 will be omitted.

The device controller 4100 can selectively write data included in the data signal DQ and the data strobe signal DQS to the nonvolatile memories 4200 or DRAMs 4600 on the basis of the signal received from the processor 1100 As shown in FIG. Alternatively, the device controller 4100 may selectively receive data stored in the non-volatile memories 4200 or DRAMs 4600, based on signals received from the processor 1100, as a data signal DQ and a data strobe signal DQS). By way of example, processor 1100 may be coupled to non-volatile memories 4200 or DRAMs 4600 based on at least one of a RAM command CMD_R, a RAM address ADDR_R, a storage command, a storage address, It is selectively accessible.

6 is a block diagram showing an embodiment of the configuration of the storage apparatus of FIG. At least one of the first type of storage devices 1220, 1222 of FIG. 1 may include the storage device 5000 of FIG. By way of example, storage device 5000 may be implemented as a non-volatile memory module coupled to a DIMM socket of computing system 1000 of FIG. In this example, the storage device 5000 may communicate with the processor 1100 of FIG. 1 in accordance with an interface convention defined based on the DIMM specification.

In the embodiment of FIG. 6, the storage device 5000 may include a control circuit 5005, one or more non-volatile memories 5200, and one or more DRAMs 5600. The non-volatile memories 5200 may be utilized as a storage medium of the computing system 1000. The DRAMs 5600 may be utilized as the main memory of the computing system 1000. The nonvolatile memories 5200 and DRAMs 5600 may be configured and operable, respectively, the same or similar to the nonvolatile memories 4200 and DRAMs 4600 of FIG. For purposes of illustration, redundant descriptions of non-volatile memories 5200 and DRAMs 5600 will be omitted.

The control circuit 5005 may include a device controller 5100, a data buffer circuit 5400, and an SPD chip 5500. The device controller 5100 and nonvolatile memories 5200 may be configured and operative as described with reference to Figures 8-15. As an example, if a read request is provided from a host (e.g., processor 1100 of FIG. 1) for read data stored in at least one of non-volatile memories 5200, Each of a plurality of transmission unit data generated by dividing data may be temporarily stored in the RAM 5100b and then output as the data signal DQ.

In the above embodiment, a small amount of RAM 5100b may be employed by transferring each of the transfer unit data forming the read data in preparation, instead of waiting until the read data is fully prepared. Thus, the area occupied by the RAM 5100b and the implementation cost of the storage device 5000 can be reduced.

As an example, the completion of the read operation (i.e., transmission of all transmission unit data) may be managed by the host (e.g., processor 1100 of FIG. Thus, the operation load of the storage apparatus 5000 can be reduced. Embodiments of the present invention will be described in more detail with reference to Figs. 8 to 15. Fig.

The device controller 5100, the RAM 5100b and the SPD chip 5500 can be configured and operated respectively in the same or similar to the device controller 2100, the RAM 2100b, and the SPD chip 2500 in Fig. 3 . The data buffer circuit 5400 may be configured and operated in the same or similar manner as the data buffer circuit 3400 of FIG. For convenience of description, redundant descriptions of the device controller 5100, the RAM 5100b, the data buffer circuit 5400, and the SPD chip 5500 will be omitted.

Device controller 5100 can control non-volatile memories 5200 and DRAMs 5600 based on signals received from processor 1100. [ Processor 1100 may selectively access non-volatile memories 5200 or DRAMs 5600.

For example, when processor 1100 stores data in non-volatile memories 5200, the data to be stored may be transferred to device controller (not shown) via data buffer circuit 5400 as data signal DQ and data strobe signal DQS 5100). The device controller 5100 may provide the provided data to the nonvolatile memories 5200. [ For example, when processor 1100 reads data from non-volatile memories 5200, device controller 5100 writes data read from non-volatile memories 5200 to data signal DQ and data strobe signal DQS, To the processor 1100 through the data buffer circuit 5400.

When the processor 1100 stores data in the DRAMs 5600 as an example, the device controller 5100 transfers the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK to the DRAMs 5600, . The data to be stored may be provided to the DRAMs 5600 through the data buffer circuit 5400 as the data signal DQ and the data strobe signal DQS. For example, when the processor 1100 reads data from the DRAMs 5600, the device controller 5100 transfers the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK to the DRAMs 5600 . The DRAMs 5600 output data based on the provided signals and the data buffer circuit 5400 outputs the data output from the DRAMs 5600 as a data signal DQ and a data strobe signal DQS to the processor 1100 ).

FIG. 7 is a block diagram showing an embodiment of the configuration of the storage apparatus of FIG. 1. FIG. At least one of the first type of storage devices 1220, 1222 of FIG. 1 may include the storage device 6000 of FIG. By way of example, storage device 6000 may be implemented as a non-volatile memory module coupled to a DIMM socket of computing system 1000 of FIG. In this example, the storage device 6000 can communicate with the processor 1100 of FIG. 1 in accordance with an interface convention defined based on the DIMM specification.

In the embodiment of FIG. 7, the storage device 6000 may include a control circuit 6005, one or more non-volatile memories 6200, and one or more DRAMs 6600. The non-volatile memories 6200 may be used as a storage medium of the computing system 1000. The DRAMs 6600 may be used as the main memory of the computing system 1000. The non-volatile memories 6200 and the DRAMs 6600 can be configured and operated respectively in the same or similar manner to the non-volatile memories 4200 and the DRAMs 4600 in Fig. For purposes of illustration, redundant descriptions of non-volatile memories 6200 and DRAMs 6600 will be omitted.

The control circuit 6005 may include a device controller 6100 and an SPD chip 6500. The device controller 6100 and nonvolatile memories 6200 may be configured and operative as described with reference to Figures 8-15. As an example, when a read request is provided from a host (e.g., processor 1100 of FIG. 1) for read data stored in at least one of non-volatile memories 6200, Each of a plurality of transmission unit data generated by dividing data may be temporarily stored in the RAM 6100b and output as a data signal DQ.

In the above embodiment, instead of waiting until the read data is fully prepared, the RAM 6100b having a small capacity can be employed by transferring each of the transfer unit data forming the read data as it is prepared. Thus, the area occupied by the RAM 6100b and the implementation cost of the storage device 6000 can be reduced.

As an example, the completion of the read operation (i.e., transmission of all transmission unit data) may be managed by the host (e.g., processor 1100 of FIG. 1) rather than by storage device 6000. Thus, the operation load of the storage apparatus 6000 can be reduced. Embodiments of the present invention will be described in more detail with reference to Figs. 8 to 15. Fig.

The device controller 6100, the RAM 6100b and the SPD chip 6500 may be constructed and operated respectively in the same or similar manner to the device controller 2100, the RAM 2100b, and the SPD chip 2500 in Fig. 3 . For ease of explanation, redundant descriptions of the device controller 6100, RAM 6100b, and SPD chip 6500 will be omitted.

The device controller 6100 can control the nonvolatile memories 6200 and the DRAMs 6600 based on signals received from the processor 1100. [ Processor 1100 may selectively access non-volatile memories 6200 or DRAMs 6600.

For example, when the processor 1100 stores data in the non-volatile memories 6200, the non-volatile memories 6200 store the data to be stored as a data signal DQ and a data strobe signal DQS in the device controller 6100). For example, when the processor 1100 reads data from the non-volatile memories 6200, the device controller 6100 transfers the data read from the non-volatile memories 6200 to the data signal DQ and the data strobe signal DQS, To the processor 1100 as shown in FIG.

For example, when the processor 1100 stores data in the DRAMs 6600, the device controller 6100 transfers the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK to the DRAMs 6600, . The data to be stored may be provided to the DRAMs 6600 as a data signal DQ and a data strobe signal DQS. For example, when the processor 1100 reads data from the DRAMs 6600, the device controller 6100 transfers the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK to the DRAMs 6600 . The DRAMs 6600 output data based on the provided signals and the output data can be provided to the processor 1100 as a data signal DQ and a data strobe signal DQS.

8 is a block diagram illustrating a storage system including the storage device of FIG. The storage system 10 may include a storage device 100 and a processor 101. The storage device 100 and the processor 101 may correspond to the storage device 1220 or 1222 of the first type and the processor 1100 of FIG. Thus, redundant descriptions of the storage device 100 and the processor 101 will be omitted. With reference to Fig. 8, the configuration and operation of the storage device 100, and the communication between the storage device 100 and the processor 101 will be described.

In one embodiment, the storage device 100 may include a device controller 110, one or more non-volatile memories 120, and a buffer memory 130. The device controller 110 may correspond to one of the device controllers 2100, 3100, 4100, 5100, 6100 of FIGS. 3-7. Non-volatile memories 120 may correspond to one of the non-volatile memories 2200, 3200, 4200, 5200, 6200 of FIGS. 3-7. The buffer memory 130 may correspond to one of the buffer memories 2400 and 3400 of FIGS.

In some alternative embodiments, the storage device 100 may include the data buffer circuits 3400, 5400 of Figures 4 and 6, the SPD chips 2500, 3500, 4500, 5500, 6500 of Figures 3-7, And may further include at least one of the DRAMs 4600, 5600, and 6600 shown in FIGS. FIG. 8 shows an exemplary configuration for facilitating understanding of the present invention, and the configuration of the storage device 100 may be variously modified or modified based on the embodiments described with reference to FIG. 3 to FIG.

In accordance with the control of the device controller 110, the storage device 100 can perform a unique function. For example, when the processor 101 provides write request and write data (DATA_W) to the storage device 100 to store write data (DATA_W) in the storage device 100, Accordingly, the write data (DATA_W) may be stored in the nonvolatile memories 120 or the buffer memory 130. [ For example, when the processor 101 provides a read request to the storage device 100 to read the read data (DATA_R) stored in the storage device 100, under the control of the device controller 110, The read data (DATA_R) stored in the buffer memory (120) or the buffer memory (130) may be transmitted to the processor (101).

The device controller 110 may include a physical layer 111 and a controller 112. The physical layer 111 may include a RAM controller 111a and a RAM 111b. The RAM controller 111a can receive the RAM command CMD_R, the RAM address ADDR_R, and the clock signal CLK provided from the processor 101. [ The RAM controller 111a can control the RAM 111b according to the RAM command CMD_R and the RAM address ADDR_R.

The RAM 111b may store or output data based on the RAM command CMD_R and the RAM address ADDR_R. The RAM 111b may receive the data signal DQ and the data strobe signal DQS provided from the processor 101 and may store data corresponding to the data signal DQ. Alternatively, the RAM 111b may output the data stored therein as the data signal DQ and provide the output data to the processor 101. [

The data signal DQ may include a storage command CMD_S and a storage address ADDR_S provided from the processor 101 to control the nonvolatile memories 120. In this embodiment, Further, the data signal DQ may include write data (DATA_W) to be stored in the nonvolatile memories 120 or read data (DATA_R) read from the nonvolatile memories 2200. In some cases, the data signal DQ may include write data (DATA_W) and status information (STI) regarding read data (DATA_R).

In the write operation with respect to the nonvolatile memories 120, the RAM 111b can store the storage command CMD_S and the storage address ADDR_S in accordance with the RAM command CMD_R and the RAM address ADDR_R. Further, the RAM 111b may temporarily store the write data (DATA_W) provided from the processor 101 according to the RAM command (CMD_R) and the RAM address (ADDR_R). According to the control of the controller 112, the storage command CMD_S, the storage address ADDR_S, and the write data DATA_W may be provided to the nonvolatile memories 120. Write data DATA_W may be stored in the nonvolatile memories 120 based on the storage command CMD_S and the storage address ADDR_S.

In the read operation with respect to the nonvolatile memories 120, the RAM 111b can store the storage command CMD_S and the storage address ADDR_S according to the RAM command CMD_R and the RAM address ADDR_R. The storage command CMD_S and the storage address ADDR_S may be provided to the nonvolatile memories 120 under the control of the controller 112. [ The read data DATA_R may be read from the nonvolatile memories 120 based on the storage command CMD_S and the storage address ADDR_S and temporarily stored in the RAM 111b and then provided to the processor 101.

That is, data (DATA_W, DATA_R) can be exchanged between the processor 101 and the nonvolatile memories 120 under the control of the controller 112. [ For this purpose, for example, the physical layer 111 is defined based on the DIMM specification and can operate in accordance with the DDR type interface protocol. The device controller 110 may operate in accordance with an interface protocol defined by the DIMM specification. The storage device 100 is implemented in the form of a DIMM and is capable of communicating with the processor 101 in accordance with the interface protocol defined by the DIMM specification.

In the above example, the RAM command CMD_R, the RAM address ADD_R, and the clock signal CLK may be provided through a command pin Pin defined in the DIMM specification. The storage command CMD_S corresponding to the write request or the read request can be transmitted through the data input / output pin defined in the DIMM specification together with the storage address ADDR_S. Write data or read data (DATA) may also be transmitted via the data input / output pins.

In accordance with the control of the RAM controller 111a and the controller 112, the RAM 111b can store status information (STI) regarding the progress of the write operation or the read operation. The processor 101 can recognize whether the write operation or the read operation is completed based on the state information (STI). Further, the controller 112 can recognize whether or not a write operation or a read operation needs to proceed based on the state information (STI). Status information (STI) may also be transmitted via the data input / output pins.

For example, the RAM 111b may include a multi-port RAM such as a Dual Port SRAM (DPSRAM), a Shared RAM, or the like. In this example, the RAM 111b may be accessed by the processor 101 and the controller 112, respectively, through different ports. The configuration of the ram 111b will be described in more detail with reference to Fig. Further, the write operation and the read operation will be described in more detail with reference to FIGS. 10 to 15. FIG.

The controller 112 may include various hardware or software components for controlling the physical layer 111 and the non-volatile memories 120. For example, the controller 112 may include an ECC encoding / decoding engine, a scrambler / descrambler, a data buffer, and a Flash Translation Layer .

In the above example, the controller 112 may detect and correct errors in the data by the ECC encoding / decoding engine, and generate and add ECC codes for the data. The controller 112 may scramble or descramble the data by a scrambler / descrambler. The controller 112 may temporarily store the data read from the RAM 111b or the nonvolatile memories 120 in the data buffer. The controller 112 may perform a translation between the logical address and the physical address for the storage address ADDR_S by the flash translation layer. To this end, the buffer memory 130 may store a mapping table between a logical address and a physical address of the non-volatile memories 120. [

FIG. 9 is a conceptual diagram showing the configuration of the RAM of FIG. 8 and the communication between the processor, the RAM, and the controller. As an embodiment, the RAM 111b may include a command area CA, a writing area WA, a reading area RA, and a state area STA. The command area CA, the write area WA, the read area RA, and the status area STA can be logically or physically distinguished.

One of the command area CA, the writing area WA, the reading area RA and the state area STA can be selected based on the RAM address ADDR_R (see Fig. 8) provided from the processor 101 have. Further, based on the RAM command (CMD_R, see FIG. 8) provided from the processor 101, a write operation or a read operation can be performed with respect to the selected area. As an example, if a RAM write command is provided as the RAM command CMD_R, a write operation can be performed in the selected area. On the other hand, when a RAM read command is provided as the RAM command CMD_R, a read operation can be performed in the selected area.

The command area CA may store the storage command CMD_S and the storage address ADDR_S provided from the processor 101. [ The controller 112 can read the storage command CMD_S and the storage address ADDR_S stored in the command area CA. The storage command CMD_S may indicate whether a write operation is to be performed in one or more non-volatile memories 120 (see FIG. 8) or whether a read operation is to be performed (i.e., a write request or a read request). The storage address ADDR_S may indicate the location of the non-volatile memories 120 in which a write operation or a read operation is to be performed.

The write area WA and the read area RA can store write data (DATA_W) and read data (DATA_R), respectively. Write data DATA_W provided from the processor 101 may be temporarily stored in the write area WA and then provided to the nonvolatile memories 120 under the control of the controller 112. [ The read data (DATA_R) read from the nonvolatile memories 120 may be provisionally stored in the read area RA under the control of the controller 112 and then provided to the processor 101. [

11 to 15, in the embodiment of the present invention, instead of the read data (DATA_R), a plurality of transmission unit data generated by dividing the read data (DATA_R) may be transmitted to the processor 101 . The read area RA of the RAM 111b may store transfer unit data forming the read data (DATA_R). Each of the transmission unit data may be temporarily stored in the RAM 111b and then transmitted to the processor 101. [ Each of the transmission unit data can be transmitted as a data signal DQ (see FIG. 8) through a data input / output pin defined in the DIMM specification. In an embodiment of the present invention, by transmitting all transmission unit data, the read data (DATA_R) can be transmitted.

The status area STA can store the status information STI regarding the write data DATA_W and the read data DATA_R under the control of the RAM controller 111 (see FIG. 8) and the controller 112. FIG. The status information (STI) may include information on the progress of a write operation or a read operation. The processor 101 can recognize whether the write operation or the read operation is completed based on the state information (STI). Further, the controller 112 can recognize whether or not a write operation or a read operation needs to proceed based on the state information (STI).

For example, when the processor 101 desires to store the write data (DATA_W), the processor 101 can provide the write data (DATA_W) in the write area WA. Further, the processor 101 can provide information on the write data (DATA_W) and status information (STI) concerning the request of the write operation to the state area (STA). The controller 112 can control the write operation such that write data (DATA_W) is stored in at least one of the nonvolatile memories 120 based on the status information (STI). The processor 101 can recognize completion of the write operation based on the status information STI when the controller 112 stores the status information STI informing completion of the write operation in the status area STA. To do this, the processor 101 may polle the status area STA at specific times (e.g., periodically).

For example, if the processor 101 wants to read the read data (DATA_R), the processor 101 sends information about the read data (DATA_R) and status information (STI) As shown in FIG. The controller 112 may control the read operation such that the read data (DATA_R) is read from at least one of the non-volatile memories 120 based on the status information (STI). The processor 101 can recognize the completion of the read operation based on the status information STI when the controller 112 stores the status information STI informing completion of the read operation in the status area STA. Further, the processor 101 may be provided with read data (DATA_R) stored in the read area (RA).

As described above, in the embodiment of the present invention, instead of the read data (DATA_R), the transfer unit data generated by dividing the read data (DATA_R) may be transmitted to the processor 101. [ In this embodiment, the status area STA of the RAM 111b can store "Notification Data" as the status information STI. The notification data may include information on transmission unit data forming the read data (DATA_R). The notification data will be described in more detail with reference to FIG. 13 to FIG.

10 is a flowchart for explaining a write operation of the storage apparatus of FIG. The processor 101 can store the write data (DATA_W) in the storage device 100 according to the write operation of Fig. To facilitate understanding of the present invention, Figures 8 and 9 will be referred to together.

In operation S110, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a write to the RAM 111b. Furthermore, the processor 101 may provide the RAM address ADDR_R for selecting the command area CA of the RAM 111b to the storage device 100. [

In operation S120, the processor 101 may provide the data signal DQ and the data strobe signal DQS to the storage device 100. [ In operation S120, the data signal DQ may include a write command for the storage device 100, and more specifically a storage command CMD_S for requesting a write operation for the non-volatile memories 120 . Further, the data signal DQ may include a storage address ADDR_S indicating the location of the non-volatile memories 120 in which a write operation is to be performed.

S110 and S120 operations may form a command transaction operation for transferring a write command for the non-volatile memories 120 to the storage device 100. [ When the S110 and S120 operations are performed, the command area CA of the RAM 111b may store the storage command CMD_S and the storage address ADDR_S. Here, the storage command CMD_S may indicate that a write operation is performed in the non-volatile memories 120. [

In operation S130, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a write to the RAM 111b. Further, the processor 101 may provide the RAM address ADDR_R for selecting the write area WA of the RAM 111b to the storage device 100. [

In operation S140, the processor 101 may provide the data signal DQ and the data strobe signal DQS to the storage device 100. [ In operation S140, the data signal DQ may include write data (DATA_W) to be stored in the storage device 100. [

S130 and S140 operations may form a data transaction operation for transferring write data (DATA_W) to be stored in the non-volatile memories 120 to the storage device 100. [ When the operations of S130 and S140 are performed, the write area WA of the RAM 111b can store the write data (DATA_W). As the storage command CMD_S, the storage address ADDR_S and the write data DATA_W are stored in the RAM 111b, the controller 112 performs a write operation based on the storage command CMD_S and the storage address ADDR_S Can be controlled.

In operation S150, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a read about the RAM 111b. Further, the processor 101 may provide the RAM address ADDR_R for selecting the status area STA of the RAM 111b to the storage device 100. [

In operation S160, the processor 101 may receive the data signal DQ and the data strobe signal DQS from the storage device 100. [ In operation S160, the data signal DQ may include status information (STI) regarding the write operation.

In operation S170, the storage apparatus 100 may store the write data (DATA_W) and the status information (STI) related to the write operation in the status area STA. For example, when the write operation is completed in the storage device 100, the write operation is scheduled, or the instruction of the write operation is entered in the queue, operation S170 is performed. .

In operation S180, the processor 101 can determine whether or not the write operation has been completed. The processor 101 can determine whether or not the write operation is completed based on the state information (STI) stored in the state area STA.

Operations S150 through S180 may form a confirm transaction operation to confirm whether the write operation has been completed in the non-volatile memories 120. [ If it is determined that the write operation has not been completed, the processor 101 may continue to poll whether the write operation has been completed by repeating S150 and S160 operations. On the other hand, if it is determined that the write operation is completed, the processor 101 may request the next operation of the storage device 100. [

11 is a conceptual diagram showing a read operation of the storage apparatus of FIG. To facilitate understanding of the present invention, Figures 8 and 9 will be referred to together.

Referring to FIG. 11, at time 't0', the processor 101 may provide a read request to the storage device 100 (see action 1). The processor 101 may provide a read request to the storage device 100 to read the read data (DATA_R) stored in the storage device 100. [ The processor 101 may provide the storage command 100 with the storage command CMD_S corresponding to the read request. The processor 101 may provide the storage device 100 with a storage address ADDR_S indicating the location where the read data DATA_R is stored.

When the storage device 100 receives a read request, the storage device 100 may send the read data (DATA_R) to the processor 101. [ In the embodiment of the present invention, instead of transferring the complete read data (DATA_R) to the processor 101, the storage apparatus 100 transmits a plurality of transfer unit data generated by dividing the read data (DATA_R) to the processor 101 (See action 2).

The storage device 100 can read the read data DATA_R from the position of the nonvolatile memories 120 corresponding to the storage address ADDR_S under the control of the device controller 110. [ However, when the read data (DATA_R) is distributed and stored in a highly dispersed manner, the entire read data (DATA_R) may not be read all at once. Alternatively, when the size of the read data (DATA_R) exceeds the unit size of the read operation, the entire read data (DATA_R) may not be read all at once.

When the read data (DATA_R) is transferred to the processor (101) after the entire read data (DATA_R) has been completely read, the RAM (111b) must have a large capacity to buffer the entire read data (DATA_R). Accordingly, it may be inefficient to transmit the read data (DATA_R) to the processor 101 after the entire read data (DATA_R) has been read, although the entire read data (DATA_R) is not read at once. Rather, it may be efficient to transmit the read portion whenever a part of the read data (DATA_R) is read.

In the embodiment of the present invention, the storage device 100 transfers each of the transfer unit data D [1] to D [10] forming the read data (DATA_R) to the processor 101). As an example, it is assumed that ten transfer unit data (i.e., D [1] to D [10]) form read data (DATA_R). It is to be noted, however, that this example is provided only for the sake of understanding of the present invention, and is not intended to limit the present invention.

Here, the "transmission unit" of the transmission unit data can be variously changed or modified according to the embodiment. The transmission unit may have any size suitable for transmitting data. The transmission unit may have a fixed size or a variable size. In some embodiments, the transmission unit may constitute a packet unit used for data transmission.

By way of example, at time t1, the third transmission unit data D [3] may be first read from at least one of the non-volatile memories 120 and be ready to be transmitted. The device controller 110 may transmit the third transmission unit data D [3] to the processor 101 in response to the preparation of the third transmission unit data D [3]. Therefore, the processor 101 can first receive the third transmission unit data D [3].

Next, at time t2, the first transmission unit data D [1] may be read from at least one of the non-volatile memories 120 and be ready to be transmitted. Further, at time t3 and time t4, tenth transmission unit data D [10] and seventh transmission unit data D [7] are read from at least one of the nonvolatile memories 120 It may be ready to be transmitted. The device controller 110 transmits the transmission unit data D [1], D [10], or D [10] prepared in response to the preparation of each of the transmission unit data D [1], D [ 7]) to the processor 101. The processor 101 can receive the transfer unit data prepared in the storage apparatus 100 one by one.

Finally, at time t10, the fifth transmission unit data D [5] may be read and transmitted to the processor 101. [ The processor 101 can manage whether or not the transmission of the read data (DATA_R) is completed (see operation 3). The processor 101 can determine that the transmission of the read data (DATA_R) is completed at time t11 after finally receiving the fifth transmission unit data D [5].

In the embodiment of the present invention, the transmission unit data D [1] to D [10] are transmitted to the device controller 110 in response to preparation of each transmission unit data D [1] to D [10] And may be transmitted to the processor 101 one by one according to the control. In some embodiments, each of the transmission unit data D [1] to D [10] may be transmitted to the processor 101 regardless of the order in which the read data (DATA_R) is formed. That is, each of the transmission unit data D [1] to D [10] may be transmitted to the processor 101 as it is prepared. The read data DATA_R can be transmitted to the processor 101 by transmitting each of the transfer unit data D [1] to D [10] to the processor 101. [

In the embodiment of the present invention, instead of storing the entire read data (DATA_R), the RAM 111b may store only the prepared transfer unit data D [1] to D [10]. Therefore, the ram 111b having a small capacity can be employed. As a result, the area occupied by the RAM 111b and the implementation cost of the storage device 100 can be reduced.

In the embodiment of the present invention, whether or not all of the transmission unit data D [1] to D [10] are transmitted to the processor 101 (i.e., whether or not the reading operation has been completed) . That is, the storage apparatus 100 only transmits each of the transmission unit data D [1] to D [10], and whether or not all of the transmission unit data D [1] to D [10] I can not. Therefore, the operation load of the storage apparatus 100 can be reduced. To manage the completion of the read operation by the processor 101, "notification data" can be used. The notification data will be described with reference to Figs. 13 to 15. Fig.

Fig. 12 is a flowchart for explaining a read operation of the storage apparatus of Fig. 8; The processor 101 may be provided with the read data (DATA_R) stored in the storage device 100 according to the read operation of Figs. To facilitate understanding of the present invention, Figures 8 and 9 will be referred to together.

In operation S210, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a write to the RAM 111b. Furthermore, the processor 101 may provide the RAM address ADDR_R for selecting the command area CA of the RAM 111b to the storage device 100. [

In operation S220, the processor 101 may provide the data signal DQ and the data strobe signal DQS to the storage device 100. [ In operation S220, the data signal DQ may include a storage command CMD_S for requesting a read operation on the storage device 100, and more specifically, a read operation on the non-volatile memories 120 . Further, the data signal DQ may include a storage address ADDR_S indicating the location of the nonvolatile memories 120 in which a read operation is to be performed.

S210 and S220 operations may form a command transaction operation for transferring a read command to non-volatile memories 120 to storage device 100. [ When operations S210 and S220 have been performed, the command area CA of the RAM 111b may store the storage command CMD_S and the storage address ADDR_S. As the storage command CMD_S and the storage address ADDR_S are stored in the RAM 111b, the controller 112 can control the reading operation based on the storage command CMD_S and the storage address ADDR_S.

In operation S230, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a read about the RAM 111b. Further, the processor 101 may provide the RAM address ADDR_R for selecting the status area STA of the RAM 111b to the storage device 100. [

In operation S240, the processor 101 may receive a data signal DQ and a data strobe signal DQS from the storage device 100. [ In operation S240, the data signal DQ may include status information (STI) regarding the read operation.

In operation S250, the storage device 100 may store the read data (DATA_R) and the status information (STI) regarding the read operation in the status area (STA). If a read operation is performed in the storage device 100 for a specific transfer unit data among a plurality of transfer unit data forming the read data (DATA_R), operation S250 may be performed. Here, the status information STI may include "notification data ". The notification data may indicate that the specific transmission unit data is stored in the RAM 111b and is ready to be transmitted. Further, the notification data may include information on the position in the read data (DATA_R) of the prepared transmission unit data.

In operation S260, the processor 101 may determine whether or not a read operation has been performed with respect to specific transmission unit data. The processor 101 can determine whether or not a read operation relating to the specific transmission unit data has been performed based on the state information STI (more specifically, "notification data") stored in the state area STA.

Operations S230 through S260 may form a unit read acknowledgment transaction operation that verifies whether specific unit of transfer data has been read from non-volatile memories 120. [ If it is determined that the read operation has not yet been performed, the processor 101 may continue to poll whether the read operation has been performed by repeating S230 and S240 operations. On the other hand, if it is determined that the read operation has been performed, operation S270 may be performed.

In operation S270, the processor 101 may provide a RAM command (CMD_R) to the storage device 100 for requesting a read about the RAM 111b. Furthermore, the processor 101 may provide the RAM address ADDR_R for selecting the read area RA of the RAM 111b to the storage device 100. [

In operation S280, the processor 101 may receive the data signal DQ and the data strobe signal DQS from the storage device 100. [ In operation S280, the data signal DQ may include transmission unit data D [n] prepared from transmission unit data.

S270 and S280 operations may form a data transaction operation that transmits the transfer unit data D [n] to transfer the read data (DATA_R) from the storage device 100 to the processor 101. [ The transfer unit data D [n] may be stored in the read area RA of the RAM 111b and then provided to the processor 101. In this case,

In operation S290, the processor 101 may determine whether or not the entire read operation has been completed (i.e., whether or not all transmission unit data has been transmitted). The processor 101 may determine whether the entire read operation has been completed by referring to the notification data of the stored status information (STI) in operation S250. If it is determined that the entire read operation has not yet been completed, the processor 101 may receive transmission unit data that has not yet been transmitted by repeating the operations S230 to S280 one by one.

If all of the transmission unit data has been transmitted, in S292 operation, the processor 101 can determine that the entire reading operation is completed. Further, the processor 101 may request the next operation of the storage device 100. [ S290 and S292 operations may form a full read confirmation transaction operation to determine whether the entire read data (DATA_R) has been completely transferred.

FIG. 13 is a conceptual diagram showing transmission of transmission unit data and notification data during the reading operation of FIGS. 11 and 12. FIG.

The processor 101 can provide a read request to the storage device 100 (see FIG. 8) by storing the storage command CMD_S and the storage address ADDR_S in the command area CA. In response to the read request, the device controller 110 (see FIG. 8) controls the controller 112 so that each of the plurality of transfer unit data generated by dividing the read data (DATA_R) (See FIG. 8), and the nonvolatile memories 120 (see FIG. 8).

More specifically, according to the control of the controller 112, the transmission unit data D [n] prepared from the transmission unit data can be temporarily stored in the reading area RA of the RAM 111b. Further, under the control of the controller 112, the device controller 110 generates notification data NTI [n] corresponding to the transmission unit data D [n] and outputs notification data NTI [n] And can be stored in the state area STA of the RAM 111b as state information STI. The processor 101 can receive the transmission unit data D [n] stored in the reading area RA based on the notification data NTI [n].

As an embodiment, the notification data (NTI [n]) may include a preparation notification (PN). The preparation notification PN may indicate that the transmission unit data D [n] is stored in the RAM 111b and is ready to be transmitted. The processor 101 can recognize the preparation of the transmission unit data D [n] based on the preparation notification PN and receive the transmission unit data D [n].

As an embodiment, the notification data (NTI [n]) may include position information (PI). The position information PI may include information on the position in the read data (DATA_R) of the transmission unit data D [n]. For example, the position information PI may include information necessary for grasping the relationship between the transfer unit data D [n] and the read data DATA_R, such as an address corresponding to the transfer unit data D [n] . The processor 101 can determine whether or not all transmission unit data has been received based on the position information PI. Further, the processor 101 may combine the transmission unit data into the read data (DATA_R) after all of the transmission unit data is received, based on the position information PI.

As an embodiment, the notification data (NTI [n]) may include invalid partial information (IPI). The invalid portion information IPI may include information on an invalid portion included in the transmission unit data D [n]. In some cases, the transmission unit data D [n] may include an invalid portion not included in the read data (DATA_R). The invalid portion will be described with reference to FIG.

FIG. 14 is a conceptual diagram illustrating a process of transmitting transmission unit data from a storage apparatus to a host apparatus by referring to the notification data of FIG. 13 according to the reading operation of FIGS. 11 and 12. FIG.

At time 't0', the processor 101 may provide a read request for the read data (DATA_R) to the storage device 100 (see operations S210 and S220 of FIG. 12). When a read request is received, as described above, the storage apparatus 100 may transmit each of a plurality of transmission unit data forming the read data (DATA_R) to the processor 101. [ However, the transfer unit data may be transferred to the processor 101 one by one as prepared, regardless of the order of forming the read data (DATA_R).

The processor 101 can confirm whether or not the notification data has been generated in the storage device 100 at a specific point in time (e.g., periodically, or whenever a specific condition is satisfied) after providing the read request S230 to S260 operations). When the notification data is generated, the processor 101 recognizes that the specific transmission unit data is prepared, and can receive the prepared transmission unit data.

As an example, at time t1, the third transmission unit data D [3] may be stored in the RAM 111b (see Fig. 8) and ready to be transmitted. The storage apparatus 100 may generate notification data NTI [3] for informing the preparation of the third transmission unit data D [3].

At time t2, the processor 101 can receive the third transmission unit data D [3] based on the notification data (NTI [3]) (see operations S270 and S280 in Fig. 12). Further, the processor 101 can obtain information on the third transmission unit data D [3] by referring to the notification data (NTI [3]). However, since not all of the transmission unit data has yet been received, transmission of transmission unit data can be continuously performed (see arrows from S290 operation to S230 operation in Fig. 12).

The first transmission unit data D [1] and the tenth transmission unit data D [10] may be stored in the RAM 111b and ready for transmission at time t2 and time t3, respectively . The storage device 100 generates notification data NTI [1], NTI [10] corresponding to the first transmission unit data D [1] and the tenth transmission unit data D [10] . In some cases, several transmission unit data may be prepared before the processor 101 confirms the notification data.

At time t4, the processor 101 generates the first transmission unit data D [1] and the tenth transmission unit data D [10] based on the notification data NTI [1], NTI [ Can be received. Further, the processor 101 refers to the notification data (NTI [1], NTI [10]) and stores information about the first transmission unit data D [1] and the tenth transmission unit data D [ Can be obtained. Therefore, the processor 101 can appropriately arrange the first transmission unit data D [1], the third transmission unit data D [3], and the tenth transmission unit data D [10].

At time " t6 ", the processor 101 can confirm whether or not notification data has been generated in the storage device 100. [ However, in some cases, transmission unit data may not have been prepared yet (see arrows from S260 operation to S230 operation of FIG. 12). In this case, the processor 101 can wait until the next notification data is confirmed or perform another operation.

At time t7, the fifth transmission unit data D [5] may finally be stored in the RAM 111b and ready to be transmitted. The storage apparatus 100 may generate notification data (NTI [5]) corresponding to the fifth transmission unit data D [5]. At time t8, the processor 101 can receive the fifth transmission unit data D [5] based on the notification data (NTI [5]). Further, the processor 101 can obtain information on the fifth transmission unit data D [5] by referring to the notification data (NTI [5]).

At time t9, the processor 101 refers to the notification data (NTI [1] to NTI [10]) to determine that all of the transmission unit data D [1] to D [10] have. Thus, the processor 101 can determine that the entire read operation has been completed (see S292 operation in FIG. 12). The processor 101 appropriately arranges the transmission unit data D [1] to D [10] by referring to the notification data NTI [1] to NTI [10] and acquires the read data DATA_R .

In summary, when a read request is received from the processor 101, the storage device 100 may store each of the transfer unit data generated by dividing the read data in the RAM 111b. The storage device 100 may generate notification data in response to the preparation of each of the transmission unit data. In response to the generation of the notification data, the processor 101 can receive the prepared transmission unit data one by one. By transmitting all of the transmission unit data, read data (DATA_R) can be transmitted from the storage device 100 to the processor 101. [ Whether or not all of the transmission unit data has been transmitted can be managed by the processor 101. [

FIG. 15 is a conceptual diagram showing a process of acquiring read data by discarding an invalid portion and combining a valid portion in transmission unit data transmitted according to the reading operation of FIGS. 11 and 12. FIG.

In some embodiments, at least one of the plurality of transmission unit data forming the read data may include an invalid portion. The invalid part means a part not included in the read data. In contrast, a portion included in the read data may be referred to as a valid portion.

In some cases, the size of the data read from the non-volatile memories 120 (see FIG. 8) may be smaller than the size of the transfer unit data. In this case, the transfer unit data may include data read from the nonvolatile memories as a valid portion. Further, in accordance with the control of the device controller 110 (see Fig. 8), an invalid portion can be added to the transmission unit data. The invalid portion may be added to the transmission unit data to form the transmission unit.

As an example, the invalid portion may include meaningless data irrelevant to the read data or data of a specific pattern. As described with reference to Fig. 13, the notification data may include invalid portion information (IPI). The invalid portion information (IPI) may include information necessary for identifying the invalid portion such as the position of the invalid portion, the content of the invalid portion, the length of the invalid portion, and the like.

The processor 101 (see FIG. 8) can identify the invalid portion included in the received transmission unit data based on the notification data including the invalid portion information IPI. Since the invalid portion is independent of the read data, the processor 101 (see FIG. 8) can discard the invalid portion. Further, the processor 101 may combine data other than the invalid portion. Thereby, the processor 101 can acquire read data.

For example, referring to FIG. 15, read data may be formed of first transmission unit data D [1] through tenth transmission unit data D [10]. For example, each of the fifth transmission unit data D [5] and the tenth transmission unit data D [10] may include an invalid portion. The processor 101 discards the invalid portion contained in the fifth transmission unit data D [5] based on the notification data corresponding to the fifth transmission unit data D [5], and transmits the modified fifth transmission unit data D [ (D [5] ') can be obtained. The processor 101 discards the invalid portion included in the tenth transmission unit data D [10] based on the notification data corresponding to the tenth transmission unit data D [10] (D [10] ') can be obtained.

The processor 101 may combine the modified fifth transmission unit data D [5] 'and the modified tenth transmission unit data D [10]' with other transmission unit data. Thereby, the processor 101 can acquire read data. The finally obtained read data may contain only the data intended by the processor 101 without an invalid portion.

According to the embodiments described with reference to Figures 8-15, the processor 101 may communicate with the device controller 112 of Figure 8 via a bus operating at a high speed, such as the bus 1230 of Figure 1 . For example, when the storage device 100 of FIG. 8 is implemented in the form of a DIMM and the processor 101 communicates with the device controller 112 in accordance with an interface protocol operating in DDR mode, ) Is recognized as a DIMM device, and a write operation and a read operation can be performed on the RAM 111b according to an interface protocol operating in the DDR mode. Therefore, according to the embodiment of the present invention, the storage apparatus 100 can exhibit high operation performance.

16 is a block diagram showing one of the nonvolatile memories of FIG. At least one of the non-volatile memories 120 of FIG. 8 may include a non-volatile memory 121. FIG. The nonvolatile memory 121 may include a memory cell array 121a, an address decoder 121b, a control logic and voltage generator 121c, a page buffer 121d, and an input / output circuit 121e.

The memory cell array 121a may include a plurality of memory blocks BLK1 to BLKz. Each of the memory blocks may comprise a plurality of cell strings. Each of the cell strings may comprise a plurality of memory cells. Each of the memory cells may be connected to a plurality of word lines (WL). Each of the memory cells may include a single level cell storing one bit or a multi level cell storing at least two bits.

As an example, the memory cell array 121a may include a three-dimensional memory array. The three-dimensional memory array may be monolithically formed on one or more physical levels of memory cell arrays having an active region disposed over a silicon substrate and circuits associated with operation of the memory cells. The circuitry associated with the operation of the memory cells may be disposed within or on the substrate. The term " Monolithical "means that layers of each level of the three-dimensional memory array are deposited directly on the lower level layers of the three-dimensional memory array.

As an example, the three-dimensional memory array may include vertical NAND strings with vertical orientation and at least one memory cell located over the other memory cell. The at least one memory cell may include a charge trap layer. Each of the vertical NAND strings may include at least one select transistor located above the memory cells. At least one select transistor may be constructed in the same structure as the memory cells and monolithically formed with the memory cells.

Suitable configurations for a three-dimensional memory array, such as a three-dimensional memory array comprising a plurality of levels and having word lines or bit lines shared between levels, are described in U.S. Patent No. 7,679,133, U.S. Patent No. 8,554,466, U.S. Patent No. 8,654,587, U.S. Patent No. 8,559,235, and U.S. Patent Application Publication No. 2011/0233648, the disclosures of which are incorporated herein by reference.

The address decoder 121b may be connected to the memory cell array 121a via word lines WL, string selection lines SSL, and ground selection lines GSL. The address decoder 121b can receive the storage address ADDR_S 'from the device controller 110 (see FIG. 8) and decode the received storage address ADDR_S'. The address decoder 121b may select at least one of the word lines WL based on the decoded storage address ADDR_S 'and may drive the selected at least one word line.

The control logic and voltage generator 121c may receive the storage command CMD_S 'and the control signal CTRL from the device controller 110. [ The control logic and voltage generator 121c can control the address decoder 121b, the page buffer 121d, and the input / output circuit 121e in response to the received signals. As an example, the control logic and voltage generator 121c may be configured such that the write data (DATA) provided from the device controller 110 is stored in the memory cell array 121a in response to the storage command CMD_S 'and the control signal CTRL The decoder 121b, the page buffer 121d, and the input / output circuit 121e so that the read data (DATA) stored in the memory cell array 121a can be read.

The control logic and voltage generator 121c may generate various voltages used to operate the non-volatile memory 121. [ By way of example, control logic and voltage generator 121c may generate a plurality of program voltages, a plurality of pass voltages, a plurality of selected read voltages, a plurality of unselected read voltages, a plurality of erase voltages, and a plurality of verify voltages . The control logic and voltage generator 121c may provide the generated voltages to the address decoder 121b or to the substrate of the memory cell array 121a.

The page buffer 121d may be connected to the memory cell array 121a through a plurality of bit lines BL. The page buffer 121d controls the bit lines BL so that the write data DATA provided from the input / output circuit 121e is stored in the memory cell array 121a under the control of the control logic and the voltage generator 121c . The page buffer 121d may read the read data stored in the memory cell array 121a and provide the read data to the input / output circuit 121e under the control of the control logic and the voltage generator 121c. For example, the page buffer 121d may receive data on a page basis from the input / output circuit 121e, or may read data on a page basis from the memory cell array 121a. As an embodiment, the page buffer 121d may include data latches for temporarily storing data read from the memory cell array 121a or data provided from the input / output circuit 121e.

The input / output circuit 121e may receive write data (DATA) from an external device such as the device controller 110 and provide the supplied write data (DATA) to the page buffer 121d. Alternatively, the input / output circuit 121e may receive the read data (DATA) from the page buffer 121d and provide the received read data (DATA) to an external device such as the device controller 110. For example, the input / output circuit 121e can exchange data (DATA) with an external device in synchronization with the control signal CTRL.

17 is a conceptual diagram showing one memory block of the memory cell array of FIG. Referring to Fig. 17, a first memory block BLK1 of a three-dimensional structure will be described. By way of example, FIG. 17 shows a case where the memory cell array 121a of FIG. 16 includes a NAND flash memory. However, the present invention is not limited by Fig. Furthermore, other memory blocks may also be configured similar to the first memory block BLK1.

Referring to FIG. 17, the first memory block BLK1 may include a plurality of cell strings CS11, CS12, CS21, and CS22. The cell strings CS11, CS12, CS21, CS22 may be arranged along the row direction and the column direction to form rows and columns. For example, the cell strings CS11 and CS12 may be connected to the string selection lines SSL1a and SSL1b to form a first row. The cell strings CS21 and CS22 may be connected to the string selection lines SSL2a and SSL2b to form a second row. Furthermore, the cell strings CS11 and CS21 may be connected to the first bit line BL1 to form the first column. The cell strings CS12 and CS22 may be connected to the second bit line BL2 to form a second column.

Each of the cell strings CS11, CS12, CS21, and CS22 may include a plurality of cell transistors. For example, each of the cell strings CS11, CS12, CS21, and CS22 includes a plurality of memory cells MC1 to MC8, a plurality of memory cells MC1 to MC8, a plurality of memory cells MC1 to MC8, (Dummy) memory cells DMC1, DMC2. As an example, each of the plurality of cell transistors included in the cell strings CS11, CS12, CS21, and CS22 may be a charge trap flash memory cell.

The memory cells MC1 to MC8 are connected in series and can be stacked in a height direction perpendicular to the plane formed by the row direction and the column direction. The string selected transistors SSTa and SSTb may be connected in series and the string selected transistors SSTa and SSTb connected in series may be provided between the memory cells MC1 to MC8 and the bit line BL. The grounded selected transistors GSTa and GSTb are connected in series and the grounded selected transistors GSTa and GSTb connected in series may be provided between the memory cells MC1 to MC8 and the common source line CSL.

As an example, a first dummy memory cell DMC1 may be provided between the memory cells MC1 to MC8 and the ground selected transistors GSTa and GSTb. As an example, a second dummy memory cell DMC2 may be provided between the memory cells MC1 to MC8 and the string selected transistors SSTa and SSTb.

The ground selected transistors GSTa and GSTb of the cell strings CS11, CS12, CS21 and CS22 can be connected in common to the ground selection line GSL. By way of example, the ground selected transistors of the same row may be connected to the same ground select line, and the ground selected transistors of different rows may be connected to different ground select lines. By way of example, the first ground selected transistors GSTa of the cell strings CS11, CS12 of the first row may be connected to the first ground selection line and the first ground selection transistors GSTa of the cell strings CS21, 1 ground selected transistors (GSTa) may be connected to the second ground selection line.

By way of example, not shown, ground selected transistors lying at the same height from a substrate (not shown) may be connected to the same ground select line, and ground selected transistors placed at different heights may be connected to different ground select lines . As an example, the first ground selected transistors GSTa of the cell strings CS11, CS12, CS21, CS22 are connected to a first ground selection line, and the second ground selection transistors GSTb are connected to a second ground selection line Lt; / RTI >

The memory cells placed at the same height from the substrate or ground selected transistors (GSTa, GSTb) are connected in common to the same word line, and the memory cells placed at different heights can be connected to different word lines. For example, the first to eighth memory cells MC1 to MC8 of the cell strings CS11, CS12, CS21, and CS22 may be commonly connected to the first to eighth word lines WL1 to WL8, respectively.

The string selected transistors of the same row among the first string selected transistors SSTa lying at the same height may be connected to the same string select line and the other strings of string selected transistors may be connected to another string select line. For example, the first string selected transistors SSTa of the cell strings CS11 and CS12 of the first row are connected in common with the string selection line SSL1a and the cell strings CS21 and CS22 of the second row are connected in common, The first string selected transistors (SSTa) of the memory cell array may be connected in common with the string selection line (SSL1a).

Similarly, string selected transistors in the same row of the second string selected transistors (SSTb) that lie at the same height may be connected to the same string select line, and strings of the other rows may be connected to different string select lines. By way of example, the second string selected transistors SSTb of the cell strings CS11, CS12 of the first row are connected in common with the string selection line SSL1b and the cell strings CS21, CS22 of the second row are connected in common, The second string selected transistors (SSTb) of the second transistor can be connected in common with the string selection line (SSL2b).

Although not shown in the figure, string selected transistors of cell strings in the same row may be connected in common to the same string select line. For example, the first and second string selected transistors (SSTa, SSTb) of the cell strings CS11, CS12 of the first row may be connected in common to the same string selection line. The first and second string selected transistors (SSTa, SSTb) of the cell strings CS21, CS22 of the second row may be connected in common to the same string selection line.

By way of example, dummy memory cells that lie at the same height are connected to the same dummy word line, and dummy memory cells that lie at different heights can be connected to different dummy word lines. For example, the first dummy memory cells DMC1 may be connected to the first dummy word line DWL1, and the second dummy memory cells DMC2 may be connected to the second dummy word line DWL2.

In the first memory block BLK1, reading and writing can be performed line by line. As an example, one row of the first memory block BLKa may be selected by the string selection lines SSL1a, SSL1b, SSL2a, and SSL2b.

For example, when a turn-on voltage is supplied to the string selection lines SSL1a and SSL1b and a turn-off voltage is supplied to the string selection lines SSL2a and SSL2b, Cell strings CS11 and CS12 of one row may be connected to bit lines BL1 and BL2. On the other hand, when a turn-on voltage is supplied to the string selection lines SSL2a and SSL2b and a turn-off voltage is supplied to the string selection lines SSL1a and SSL1B, the cell strings CS21 and CS22 of the second row, May be connected to the bit lines BL1 and BL2. Among the memory cells of the cell string of the row driven by driving the word line, the memory cells located at the same height can be selected. Read and write operations can be performed on selected memory cells. Selected memory cells may form a physical page unit.

In the first memory block BLK1, erasing may be performed in units of memory blocks or units of subblocks. When erasing is performed in units of memory blocks, all the memory cells MC1 to MC8 of the first memory block BLK1 can be erased simultaneously according to one erase request. When performed in units of subblocks, some of the memory cells MC1 to MC8 of the first memory block BLK1 may be simultaneously erased in response to one erase request, and some of the memory cells MC1 to MC8 may be erased. A low voltage (e. G., Ground voltage) is applied to the word line connected to the erased memory cells, and the word line connected to the erased memory cells may be floated.

The configuration of the first memory block BLK1 shown in Fig. 17 is an example. The number of cell strings may increase or decrease and the number of rows and columns constituted by cell strings may increase or decrease depending on the number of cell strings. Further, the number of the cell transistors (GST, MC, DMC, SST, etc.) of the first memory block BLK1 may increase or decrease, and the height of the first memory block BLK1 Can be increased or decreased. In addition, the number of lines (GSL, WL, DWL, SSL, etc.) connected to the cell transistors may increase or decrease according to the number of cell transistors.

18 is a conceptual diagram showing a server system including a storage apparatus according to an embodiment of the present invention. Referring to FIG. 18, the server system 7000 may include a plurality of server racks. FIG. 18 exemplarily shows one server rack 7100 among a plurality of server racks.

Each of the server racks may include at least one storage device. By way of example, the server rack 7100 may include at least one storage device. The storage device can be implemented based on the embodiments of the present invention described with reference to Figs. Fig. 18 shows one storage device 7200 among a plurality of storage devices included in the server rack 7100. Fig.

The server rack 7100 may include at least one processor 1100, one or more RAM module devices 1210 and 1212, and at least one chipset 1300, as shown in FIG. 1, as well as the storage device 7200 have. Further, the server system 7000 can include the GPU 1400, the input / output device 1500, and the at least one second type storage device 1600 shown in FIG.

The storage device 7200 may be connected without the chipset 1300 to at least one processor 1100 included in the server rack 7100. By way of example, storage device 7200 may be a non-volatile memory module implemented in the form of a DIMM. In this example, the storage device 7200 can communicate with the processor 1100 by being coupled to a DIMM socket that is electrically coupled to the processor 1100. By way of example, storage device 7200 may communicate with processor 1100 in accordance with an interface protocol defined based on the DIMM specification and operating in DDR fashion.

The storage device 7200 may be configured and operative based on the embodiments of the invention described with reference to Figures 1-17. According to embodiments of the present invention, the storage device 7200 can communicate with the processor 1100 over a bus operating at a high speed. According to embodiments of the present invention, the storage apparatus 7200 can exhibit high operation performance, and the storage performance of the server system 7000 can be improved.

Circuits, chips, devices, and modules according to embodiments of the present invention may be implemented using various types of semiconductor packages. By way of example, the circuits, chips, devices, and modules according to embodiments of the present invention may be implemented on a variety of devices such as Package on Package (PoP), Ball Grid Arrays (BGAs), Chip Scale Packages (CSPs), Plastic Leaded Chip Carriers Die in Waffer Pack, COB (Chip On Board), CERDIP (Ceramic Dual In-line Package), MQFP (Metric Quad Flat Pack), TQFP (Thin Quad Flat) Packs, Small Outline Integrated Circuits (SOIC), Shrink Small Outline Package (SSOP), Thin Small Outline Package (TSOP), System In Package (SIP), Multi Chip Package (MCP) And can be mounted using a package such as a wafer-level process stack package (WSP).

The configurations shown in the respective conceptual diagrams should be understood from a conceptual viewpoint only. In order to facilitate understanding of the present invention, the shape, structure, size, etc. of each of the components shown in the conceptual diagram have been exaggerated or reduced. The configuration actually implemented may have a physical shape different from that shown in the respective conceptual diagrams. Each conceptual diagram is not intended to limit the physical form of the component.

The device configurations shown in the respective block diagrams are intended to facilitate understanding of the invention. Each block may be formed of blocks of smaller units depending on the function. Alternatively, the plurality of blocks may form a block of a larger unit depending on the function. That is, the technical idea of the present invention is not limited to the configuration shown in the block diagram.

The present invention has been described above with reference to the embodiments of the present invention. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. Accordingly, the above embodiments should be understood in an illustrative rather than a restrictive sense. That is, the technical idea that can achieve the same object as the present invention, including the gist of the present invention, should be interpreted as being included in the technical idea of the present invention.

Therefore, it is intended that the present invention cover modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. The scope of protection of the present invention is not limited to the above embodiments.

10: Storage Systems
100: Storage device 101: Processor
110: device controller 111: physical layer
111a: RAM controller 111b: RAM
112: controller
120: Nonvolatile memories 121: Nonvolatile memories
121a: memory cell array 121b: address decoder
121c: Control logic and voltage generator
121d: page buffer 121e: input / output circuit
130: buffer memory
1000: computing system 1100: processor
1210, 1212: RAM module devices 1220, 1222: storage device of the first type
1230: Bus running at high speed
1300: Chipset 1400: GPU
1500 I / O device 1600: second type storage device
2000, 3000, 4000, 5000, 6000: Storage device
4005, 5005, 6005: control circuit
2100, 3100, 4100, 5100, 6100: Device controller
2100b, 3100b, 4100b, 5100b, 6100b: RAM
2200, 3200, 4200, 5200, 6200: non-volatile memories
2300, 3300: buffer memory
3400, 5400: Data buffer circuit
2500, 3500, 4500, 5500, 6500: SPD chip
4600, 5600, 6600: DRAMs
7000: Server system 7100: Server rack
7200: Storage Devices

Claims (10)

One or more non-volatile memories; And
Volatile memories, a read request for read data stored in at least one of the nonvolatile memories is received from the host, and a read request for the read data stored in at least one of the nonvolatile memories is received from the host in response to preparation of each of the plurality of transfer unit data forming the read data. And a device controller configured to transmit to the host,
Wherein each of the plurality of transfer unit data is transferred to the host regardless of the order of forming the read data. The method according to claim 1,
Wherein the plurality of transmission unit data is transmitted to the host one by one under the control of the device controller in response to preparation of each of the plurality of transmission unit data. The method according to claim 1,
Wherein the device controller is further configured to generate notification data indicating the preparation of each of the plurality of transmission unit data,
And each of the plurality of transmission unit data is transmitted to the host based on the notification data. The method according to claim 1,
Wherein the device controller is configured to operate in accordance with an interface protocol defined by a DIMM specification. One or more non-volatile memories; And
And a device controller configured to transmit read data stored in at least one of the non-volatile memories to the host in response to a request from the host,
The device controller comprising:
A physical layer including a RAM and a RAM controller configured to control the RAM according to a RAM command and a RAM address provided from the host; And
Volatile memories corresponding to the storage addresses and storing a plurality of transfer unit data generated by dividing the read data based on a storage command and a storage address provided from the host and stored in the RAM, And a controller configured to control the physical layer and the non-volatile memories such that each of them is temporarily stored in the RAM,
And the device controller is configured to transmit the read data by transmitting each of the plurality of transmission unit data to the host. 6. The method of claim 5,
Wherein the device controller is further configured to store notification data in the RAM,
Wherein the notification data indicates storage of each of the plurality of transmission unit data in the RAM and includes information on a position of each of the plurality of transmission unit data in the read data. The method according to claim 6,
Wherein whether or not all of the plurality of transmission unit data has been transmitted to the host is managed by the host based on the notification data. The method according to claim 6,
Wherein at least one of the plurality of transmission unit data includes an invalid portion not included in the read data,
Wherein the notification data further includes information regarding the invalid portion. 9. The method of claim 8,
The invalid portion is discarded by the host based on the notification data,
Wherein data excluding the invalid portion from the plurality of transmission unit data is combined into the read data at the host. At least one storage device; And
And at least one processor configured to provide a read request for read data stored in the storage device to the storage device,
In response to the read request, the storage device is arranged to prepare to transmit each of a plurality of transmission unit data forming the read data to the processor and generate notification data relating to the preparation of each of the plurality of transmission unit data,
And the processor is further configured to receive the prepared one of the plurality of transmission unit data with reference to the notification data.

Images