Memory system, memory module, and method of operating a memory module
By introducing a retransmission mechanism of nonvolatile memory modules and controllers in the memory system, combining registers and serial presence detection devices, the read and read caused by differences in operation characteristics of dynamic random access memory and nonvolatile memory are solved. The write failure problem realizes reliable transmission and storage of data.
Patent Information
- Application Number
- CN201910231779.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2018-03-27
- Filing Date
- 2019-03-26
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2039-03-26
AI Technical Summary
When developing storage-like memory, read and write operations may fail due to differences in operation characteristics of dynamic random access memory and nonvolatile memory, and the prior art is difficult to effectively solve this problem.
Design a memory system, including a nonvolatile memory module and a controller, ensures reliable transmission and storage of data by resending read and write requests, combining registers and serial presence detection devices, and modifying restrictions through the system management bus. .
Effectively prevent read failures or write failures caused by slower reading or writing speeds of nonvolatile memory than dynamic random access memory, ensuring normal transmission and storage of data.
Smart Images

Figure CN110308869B_ABST
Abstract
Description
[0001] This application claims the priority benefit of Korean Patent Application No. 10-2018-0035270 filed on March 27, 2018, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety. Technical Field
[0002] Embodiments of the inventive concept relate to a semiconductor memory, and more particularly, to a memory system including a memory module, a memory module, and a method of operating the memory module. Background Art
[0003] Semiconductor memory uses semiconductor devices to store data. Semiconductor memory includes volatile memory (such as dynamic random access memory or static random access memory) and non-volatile memory (such as flash memory, phase change memory, ferroelectric memory, magnetic memory, resistive memory, etc.).
[0004] Generally, volatile memory supports high-speed random access and is used as a main memory of a computing system such as a personal computer, a server, or a workstation. Nonvolatile memory supports a large storage capacity and is used as an auxiliary storage device of a computing system.
[0005] In recent years, storage class memory (SCM) has been studied and developed. Storage class memory is developed to support the large storage capacity of non-volatile memory and the high-speed random access of volatile memory. Storage class memory is implemented using non-volatile memory.
[0006] In order to be compatible with the existing main memory, storage class memory is being researched and developed based on the same memory module as the dynamic random access memory. However, due to the difference between the operating characteristics of the dynamic random access memory as the main memory and the operating characteristics of the non-volatile memory, there may be problems in implementing the storage class memory. Summary of the invention
[0007] Embodiments of the inventive concept provide a memory system including a memory module capable of overcoming a difference between operating characteristics and normally performing reading and writing, a memory module, and a method of operating the memory module.
[0008] According to some embodiments, a memory system may include: a nonvolatile memory module; a first controller configured to control the nonvolatile memory module. The nonvolatile memory module may include: a volatile memory device; a nonvolatile memory device; a second controller configured to control the volatile memory device and the nonvolatile memory device. The first controller may be configured to send a read request to the second controller. When normal data is not received from the nonvolatile memory device during a read operation according to the read request, the first controller performs one or more retransmissions of the read request to the second controller without limiting the number of times the first controller performs the one or more retransmissions of the read request.
[0009] The normal data may include error-free data or correctable data with errors within a correctable range. After sending the read request, when a first time period has passed without receiving normal data, the first controller may perform a first resending of the read request among the one or more resendings. After the first resending of the read request, when a second time period has passed without receiving normal data, the first controller may perform a second resending of the read request among the one or more resendings.
[0010] The second time period may be shorter than the first time period.
[0011] The normal data may include error-free data or correctable data having errors within a correctable range, and in response to receiving the read request, the second controller may read data including the normal data or uncorrectable data from one of the nonvolatile memory device or the volatile memory device.
[0012] While the second controller is reading the data from the non-volatile memory device, the second controller may ignore one or more resending of the read request.
[0013] After reading the data from the nonvolatile memory device, the read data may be transmitted to the first controller in response to at least one of the one or more retransmissions of the read request.
[0014] After performing a first retransmission of the one or more retransmissions of the read request, when a third period of time elapses without receiving normal data, the first controller may determine that the read has failed.
[0015] The normal data may include error-free data or correctable data having an error within a correctable range, and the third time period may be longer than a time period for the second controller to read data including the normal data or the uncorrectable data from the nonvolatile memory device.
[0016] The first controller may include a register storing a limit on the number of times the first controller performs the one or more retransmissions of the read request, and the second controller may be configured to modify the limit.
[0017] The second controller may include a serial presence detect (SPD) device, and the second controller may be configured to modify the restriction when the first controller accesses the SPD device.
[0018] The second controller may be configured to modify the limit via a system management bus (SMBus).
[0019] The first controller may send a write request to the second controller, and during a write operation according to the write request, when the second controller writes write data to the nonvolatile memory device, the second controller may activate a write error signal provided to the first controller.
[0020] In response to the write request, the second controller may perform writing to one of the volatile memory device or the nonvolatile memory device, and when writing to the volatile memory device according to the write request is completed, the second controller may deactivate a write error signal.
[0021] When the write error signal is activated, the first controller may resend the write request to the second controller.
[0022] After writing the write data to the nonvolatile memory device is completed, the second controller may deactivate the write error signal upon receiving the write request that has been resent.
[0023] The second controller may ignore the resent write request while the write data is being written to the nonvolatile memory device.
[0024] According to some embodiments, a memory module may include: a volatile memory device; a nonvolatile memory device; and a controller configured to control the volatile memory device and the nonvolatile memory device. During a write operation, in response to a write request, the controller performs a write to one of the volatile memory device or the nonvolatile memory device. When performing a write to the nonvolatile memory device, the controller activates a write error signal output to an external device.
[0025] While performing a write to the non-volatile memory device, the controller may ignore the write request being resent.
[0026] During a read operation, in response to a read request, the controller may perform a read of one of the volatile memory device or the nonvolatile memory device, and while performing the read of the nonvolatile memory device, the controller may ignore the read request being resent.
[0027] According to some embodiments, a method of operating a memory module configured to communicate with a controller may include detecting power on and updating a value of a register of the controller via a system management bus (SMBus) to perform a read retry without limiting the number of times the read retry is performed.
[0028] According to an embodiment of the present invention, when performing a read or write to a non-volatile memory device, a read retry or a write retry is allowed without limiting the number of times the read retry or the write retry is performed. Therefore, an embodiment of the present invention provides a memory module, a memory system including the memory module, and an operating method of the memory module, wherein the memory module can prevent a read failure or a write failure that occurs due to a read speed or a write speed of a non-volatile memory being slower than a read speed or a write speed of a dynamic random access memory. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The above and other objects and features of the present inventive concept will become apparent through detailed description of exemplary embodiments of the present inventive concept with reference to the attached drawings.
[0030] Figure 1 is a block diagram illustrating a computing device according to some embodiments of the inventive concept.
[0031] Figure 2 is a block diagram illustrating a main memory according to some embodiments of the inventive concept.
[0032] Figure 3 is a flowchart for describing a read operation of the first controller 130 a on the main memory 140 a according to some embodiments of the inventive concept.
[0033] Figure 4 According to some embodiments of the present invention Figure 3 A timing diagram of an example read operation of the illustrated method of operation.
[0034] Figure 5 According to some embodiments of the present invention Figure 3 A timing diagram of an example read operation is shown.
[0035] Figure 6 It is used to describe some embodiments of the present invention. Figure 3 An example of a read operation of the operation method is shown.
[0036] Figure 7 is a flowchart for describing an operating method of the first controller 130 a according to some embodiments of the inventive concept.
[0037] Figure 8It is used to describe some embodiments of the present invention. Figure 7 An example of a read operation of the operation method is shown.
[0038] Fig. 9 It is used to describe some embodiments of the present invention. Figure 7 An example of a read operation of the operation method is shown.
[0039] Fig.10 According to some embodiments of the present invention Figure 7 An example of a read operation is shown.
[0040] Fig.11 It is used to describe some embodiments of the present invention. Figure 7 A flow chart of an example of application of the operating method shown.
[0041] Fig.12 is an example of performing a read operation in the case of measuring the third time T3 according to some embodiments of the inventive concept.
[0042] Fig.13 is a block diagram illustrating a computing device according to some embodiments of the inventive concept.
[0043] Fig.14 is a block diagram of a main memory including an SPD device and a register updater according to some embodiments of the inventive concept.
[0044] Fig.15 is a flowchart for describing an operation method of the main memory 140 b updating the register 132 according to some embodiments of the inventive concept.
[0045] Fig.16 is a block diagram illustrating a computing device according to some embodiments of the inventive concept.
[0046] Fig.17 is a flowchart for describing a write operation of the first controller 130 c according to some embodiments of the inventive concept.
[0047] Fig.18 is a flowchart for describing a write operation of the main memory 140 c according to some embodiments of the inventive concept.
[0048] Fig.19 According to some embodiments of the present invention Fig.18 An example timing diagram of a write operation of the illustrated operating method.
[0049] Fig. 20 According to some embodiments of the present invention Fig.18 An example timing diagram of a write operation of the illustrated operating method.
[0050] Fig.21 According to some embodiments of the present invention Fig.18 An example timing diagram of a write operation of the illustrated operating method.
[0051] Fig. 22 According to some embodiments of the present invention Fig.18 An example timing diagram for a write operation is shown.
[0052] Fig.23 According to some embodiments of the present invention Fig.18 An example timing diagram for a write operation is shown. DETAILED DESCRIPTION
[0053] It should be noted that, although there is no specific description related to the various aspects of the inventive concept described for one embodiment that may be included in different embodiments, the various aspects of the inventive concept described for one embodiment may be included in different embodiments. That is to say, the features of all embodiments and / or any embodiment may be combined in any manner and / or combination. These and other objects and / or aspects of the inventive concept are explained in detail in the specification set forth below. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. When a statement such as "at least one of ... " is after a column of elements, the entire column of elements is modified without modifying the individual elements in the column.
[0054] Hereinafter, embodiments of the inventive concept will be described clearly and in detail with reference to the accompanying drawings to an extent that a person having ordinary skill in the art can implement the embodiments of the present invention.
[0055] Figure 1 1 is a block diagram illustrating a computing device 100a according to some embodiments of the inventive concept. For example, the computing device 100a may include a server (such as an application server, a client server, and a data server). In some embodiments, the computing device 100a may include a personal computer or a workstation.
[0056] Reference Figure 1 , the computing device 100a may include a processor 110, a second cache memory 120, a first controller 130a, a main memory 140a, a storage interface 150, and a storage device 160. It will be understood that although the terms first, second, third, etc. may be used herein to describe various elements, these elements should not be limited by these terms; rather, these terms are only used to distinguish one element from another. Therefore, without departing from the scope of the present inventive concept, the first element discussed below may be referred to as the second element.
[0057] The processor 110 may control the components of the computing device 100a and the operations of the components. The processor 110 may execute an operating system and applications and process data using the operating system and applications. The processor 110 may include a first cache memory 111. The first cache memory 111 may include a high-speed memory such as a static random access memory (SRAM).
[0058] The second cache memory 120 may communicate with the processor 110. The second cache memory 120 may include a high-speed random access memory such as a static random access memory (SRAM) and a dynamic random access memory (DRAM).
[0059] The first controller 130a may access the main memory 140a in response to a request from the processor 110. For example, the first controller 130a may be based on one of the standards of a memory module such as a dual in-line memory module (DIMM), a registered DIMM (RDIMM), a load-reduced DIMM (LRDIMM), etc. In some embodiments, the first controller 130a may be as follows: Figure 1 The arrangement shown is external to the processor 110 , or may be included in the processor 110 .
[0060] The first controller 130a may include a timeout controller 131 and a register 132. The timeout controller 131 may measure the time for the first controller 130a to access the main memory 140a. The register 132 may store various parameters associated with the first controller 130a.
[0061] For example, the register 132 may store various timeout values associated with when the first controller 130a accesses the main memory 140a. The timeout controller 131 may control the timeout when the first controller 130a accesses the main memory 140a based on the timeout value stored in the register 132.
[0062] The main memory 140a may include a storage class memory (SCM) having a non-volatile storage capability or a large capacity and having an access speed and random access capability similar to a dynamic random access memory (DRAM).
[0063] In order to support compatibility with existing computing devices, the main memory 140a may be implemented based on one of the standards of a memory module such as DIMM, RDIMM, LRDIMM, etc. The first controller 130a and the main memory 140a may form a memory system.
[0064] The storage interface 150 may receive a request of the processor 110 or transmit data to the storage device 160. The storage interface 150 may transmit data received from the storage device 160 to the processor 110. The storage interface 150 may be based on one of various standards such as Peripheral Component Interconnect Express (PCIe), Non-Volatile Memory Express (NVMe), Serial Advanced Technology Attachment (SATA), etc.
[0065] The storage device 160 may store data received from the storage interface 150 in response to a request received from the storage interface 150. The storage device 160 may transmit the stored data through the storage interface 150 in response to a request received from the storage interface 150.
[0066] The storage device 160 may include a nonvolatile storage medium and a controller for controlling the nonvolatile storage medium. The storage device 160 may include a hard disk drive (HDD), a solid state drive (SDD), and the like.
[0067] The processor 110 may process data hierarchically. For example, user data, source data of an operating system, and source data of applications used in the computing device 100a may be stored in the storage device 160. The user data may include data generated by the operating system, applications, or a user of the computing device 100a.
[0068] When specific data (e.g., source data and / or user data) required by the processor 110 is stored in the storage device 160, the processor 110 may read the specific data from the storage device 160 and may store the specific data in the main memory 140a. When the specific data is updated or modified, the processor 110 may back up the specific data stored in the main memory 140a to the storage device 160.
[0069] Some of the storage areas of the main memory 140a may be mapped to the second cache memory 120. Some of the storage areas of the second cache memory 120 may be mapped to the first cache memory 111. In some embodiments, at least one of the first cache memory 111 and the second cache memory 120 in the computing device 100a may be omitted.
[0070] Figure 2 1 is a block diagram illustrating a main memory 140a according to some embodiments of the inventive concept. In some embodiments, the main memory 140a may be a memory module based on the LRDIMM standard. Figure 2 , the main memory 140 a may include a volatile memory device 210 , a nonvolatile memory device 220 , a second controller 230 , and first to eighth data buffers 241 to 248 .
[0071] The volatile memory device 210 may include first to fourth volatile memories 211 to 214. The first to fourth volatile memories 211 to 214 may be formed as packages separated from each other. The first to fourth volatile memories 211 to 214 may include dynamic random access memories.
[0072] The nonvolatile memory device 220 may include first to fourth nonvolatile memories 221 to 224. The first to fourth nonvolatile memories 221 to 224 may be formed as separate packages physically and / or logically separated from each other. The first to fourth nonvolatile memories 221 to 224 may be storage areas in the nonvolatile memory device 220 identified by different addresses.
[0073] The nonvolatile memory device 220 may include at least one of various nonvolatile memory devices such as a flash memory device, a phase change memory device, a ferroelectric memory device, a resistive memory device, a magnetic memory device, etc.
[0074] The second controller 230 may receive a first command and address CA1, a first clock signal CK1, and a first control signal CTRL1 from the first controller 130a. The second controller 230 may communicate with the first to eighth data buffers 241 to 248 to receive and transmit the second data signal DQ2. The second controller 230 may access the volatile memory device 210 or the nonvolatile memory device 220 according to the first command and address CA1, the first clock signal CK1, and the first control signal CTRL1.
[0075] The second controller 230 may send a second command and address CA2, a second clock signal CK2, and a second control signal CTRL2 to the volatile memory device 210, and may communicate with the volatile memory device 210 to receive and send a third data signal DQ3. The second controller 230 may send a third command and address CA3, a third clock signal CK3, and a third control signal CTRL3 to the nonvolatile memory device 220, and may communicate with the nonvolatile memory device 220 to receive and send a fourth data signal DQ4.
[0076] In some embodiments, the first command and address CA1, the second command and address CA2, and the third command and address CA3 may have different formats from each other. In some embodiments, at least two of the first command and address CA1, the second command and address CA2, and the third command and address CA3 may have the same format. For example, the format in which the second controller 230 communicates with the volatile memory device 210 may be different from the format in which the second controller 230 communicates with the non-volatile memory device 220.
[0077] The second controller 230 may send a first buffer command CMD_B1 to control the first to fourth data buffers 241 to 244. The second controller 230 may send a second buffer command CMD_B2 to control the fifth to eighth data buffers 245 to 248.
[0078] The first to eighth data buffers 241 to 248 may communicate with the first controller 130a in synchronization with the data strobe signal DQS to transmit and receive the first data signal DQ1. The first to eighth data buffers 241 to 248 may transmit the first data signal DQ1 received from the first controller 130a to the second controller 230 as the second data signal DQ2.
[0079] The first to eighth data buffers 241 to 248 may transmit the second data signal DQ2 received from the second controller 230 to the first controller 130a as the first data signal DQ1. The first to eighth data buffers 241 to 248 may be formed as packages separated from each other.
[0080] In some embodiments, the volatile memory device 210 may be used as a cache memory for the nonvolatile memory device 220. Some storage space of the nonvolatile memory device 220 may be mapped to the volatile memory device 210.
[0081] When the first storage space indicated by the first command and address CA1 received from the first controller 130a is mapped to the volatile memory device 210, that is, when a cache hit occurs, the second controller 230 may send a second command and address CA2 to the volatile memory device 210. The volatile memory device 210 may perform a write operation and a read operation according to the second command and address CA2.
[0082] When the first storage space indicated by the first command and address CA1 received from the first controller 130a is not mapped to the volatile memory device 210, that is, when a cache miss occurs, the second controller 230 may map the first storage space indicated by the first command and address CA1 to the volatile memory device 210.
[0083] For example, a second storage space associated with a first storage space of the nonvolatile memory device 220 may be secured in the volatile memory device 210. When the storage space of the volatile memory device 210 is insufficient, the second controller 230 may discard data mapped to other storage spaces of the volatile memory device 210, or return data of another storage space to the nonvolatile memory device 220 to secure the storage space of the volatile memory device 210.
[0084] When data is stored in the first storage space of the nonvolatile memory device 220, the second controller 230 may copy the data stored in the first storage space to the second storage space of the volatile memory device 210. Then, the second controller 230 may send a second command and an address CA2 to the volatile memory device 210. The volatile memory device 210 may perform a write operation and a read operation on the second storage space in response to the second command and the address CA2.
[0085] To release the second storage space in the volatile memory device 210, the second controller 230 may check whether the second storage space is dirty (ie, previously used). For example, when writing to the second storage space is performed, the second storage space may be determined to be dirty.
[0086] When the second storage space is not dirty, the second controller 230 may discard the data of the second storage space to release the second storage space. When the second storage space is dirty, the second controller 230 may write the data of the second storage space to the nonvolatile memory device 220 to send back the data of the second storage space. After sending back the second storage space, the second controller 230 may discard the data of the second storage space to release the second storage space.
[0087] In some embodiments, the volatile memory device 210 and the non-volatile memory device 220 may be directly accessed by the first controller 130a. For example, when the first command and address CA1 or the first control signal CTRL1 indicates the volatile memory device 210, the second controller 230 may send the second command and address CA2, the second clock signal CK2 and / or the second control signal CTRL2 to the volatile memory device 210.
[0088] When the first command and address CA1 or the first control signal CTRL1 indicates the nonvolatile memory device 220 , the second controller 230 may transmit a third command and address CA3 , a third clock signal CK3 , and / or a third control signal CTRL3 to the nonvolatile memory device 220 .
[0089] In some embodiments, the number of volatile memories, nonvolatile memories, and data buffers is not limited thereto. The number of volatile memories or the number of nonvolatile memories may be equal to the number of data buffers. The number of data buffers may be changed to nine or increased / decreased as needed.
[0090] Figure 3 1 is a flowchart for describing a read operation of the first controller 130a on the main memory 140a. Figures 1 to 3 In operation S110 , the first controller 130 a may receive a first read request. For example, the first controller 130 a may receive the first read request from the processor 110 .
[0091] In operation S120, the first controller 130a may send a second read request to the second controller 230. For example, the first controller 130a may generate a second read request using the first read request. The format of the first read request may be the same as or different from the format of the second read request. One or more second read requests may be generated from one first read request.
[0092] In operation S130, the first controller 130a may determine whether normal data is received within a first time period T1 (hereinafter, also referred to as the first time T1). For example, the normal data may include error-free data or correctable data having an error within a correctable range. The correctable range may be determined according to the type of error correction code used for communication between the first controller 130a and the second controller 230.
[0093] Unlike normal data, data having errors or data having errors outside a correctable range may be error data. When normal data is received within the first time T1, in operation S140, it may be determined that the reading is successful. The first controller 130a may transmit the received normal data to the processor 110.
[0094] When normal data is not received within the first time T1 or error data is received within the first time T1, in operation S150, the first controller 130a may resend the second read request to the second controller 230. For example, the second read request sent in operation S150 may be the same as the second read request sent in operation S120. Operation S150 may be referred to as a read retry.
[0095] In operation S160, the first controller 130a may determine whether normal data is received within a second time period T2 (hereinafter, also referred to as second time T2). The second time T2 may be equal to or different from the first time T1. When normal data is received within the second time T2, in operation S140, it may be determined that the reading is successful.
[0096] When normal data is not received within the second time T2, operation S170 may be performed. In operation S170, the first controller 130a may determine whether the second read request is resent at least the first value N1 number of times (N1 times). For example, the first controller 130a may determine whether the read retry is performed the first value N1 number of times.
[0097] When the read retry is not performed the number of times of the first value N1, in operation S150, the read retry may be performed. When the read retry is performed the number of times of the first value N1, operation S180 may be performed. In operation S180, when an uncorrectable error occurs, the first controller 130a may determine that the read fails. This prevents the read request of the first controller 130a from falling into an infinite loop.
[0098] Figure 4 Is used to describe Figure 3 For example, the first command and the address CA1 may be associated with the volatile memory device 210, and the read operation performed in the volatile memory device 210 may be performed in the following manner: Figure 4 is shown in .
[0099] Reference Figures 1 to 4 , the processor 110 may generate a first read request R1. In operation S211, the processor 110 may send the first read request R1 to the first controller 130a. The first controller 130a may generate a second read request R2 according to the first read request R1.
[0100] In operation S212, the first controller 130a may send a second read request R2 to the second controller 230. The second read request R2 may be sent to the second controller 230 as a first command and an address CA1. According to the sending of the second read request R2, the timeout controller 131 may start measuring (or counting) the first time T1 ( Figure 3 In other words, after the second read request R2 is sent by the first controller 130a and / or when the second read request R2 is received by the second controller 230, the timer associated with the first time T1 may be started.
[0101] The second controller 230 may generate a third read request R3 according to the second read request R2. In operation S213, the second controller 230 may send the third read request R3 to the volatile memory device 210. The third read request R3 may be sent to the volatile memory device 210 as a second command and an address CA2.
[0102] For example, the second controller 230 may not process the second read request R2, and may send the unprocessed second read request R2 as the third read request R3 to the volatile memory device 210. In some embodiments, the second controller 230 may process the second read request R2 into a form suitable for the volatile memory device 210, and may send the processed second read request R2 to the volatile memory device 210 as the third read request R3.
[0103] The volatile memory device 210 may perform a read operation RD in response to the third read request R3. Data read from the volatile memory device 210 may be transmitted to the second controller 230. In operation S214, the read operation RD may be completed.
[0104] The second controller 230 may perform the first data transmission DT1 to transmit the data read from the volatile memory device 210 to the first controller 130a. In operation S215, the first data transmission DT1 may be completed, and the data may be transmitted to the first controller 130a.
[0105] Before the first time T1 elapses after the second read request R2 is sent, the first controller 130a may receive data from the main memory 140a. For example, the received data may be normal data. Therefore, the first controller 130a may determine that the read is successful.
[0106] The first controller 130a may perform a second data transfer DT2 to transmit data received from the second controller 230 to the processor 110. In operation S216, the second data transfer DT2 may be completed, and the data may be transmitted to the processor 110. The processor 110 may determine a read completion RC.
[0107] Figure 5 yes Figure 3 An example of a read operation is shown. Figures 1 to 3 and Figure 5 , since operations S221 to S223 are Figure 4 The illustrated operations S211 to S213 are the same, so their detailed descriptions will be omitted.
[0108] When the volatile memory device 210 performs the read operation RD, in operation S224, the read data may be directly transmitted to the first controller 130a through the second controller 230 and the first to eighth data buffers 241 to 248 without being controlled and buffered by the second controller 230. Since the LRDIMM is based on a dynamic random access memory (DRAM), the volatile memory device 210 may directly communicate with the first controller 130a.
[0109] Operation S226 can be performed with Figure 4Operation S216 is shown to be the same. When the data read from the volatile memory device 210 is directly transmitted to the first controller 130a, the time until the first controller 130a receives the data after the second read request R2 is transmitted can be reduced.
[0110] Figure 6 Is used to describe Figure 3 1. For example, the first command and the address CA1 may be associated with the nonvolatile memory device 220. The read operation performed in the nonvolatile memory device 220 is performed in Figure 6 is shown in .
[0111] Reference Figures 1 to 3 and Figure 6 , the processor 110 may generate a first read request R1. In operation S231, the processor 110 may send the first read request R1 to the first controller 130a. The first controller 130a may generate a second read request R2 according to the first read request R1.
[0112] In operation S232, the first controller 130a may send a second read request R2 to the second controller 230. The second read request R2 may be sent to the second controller 230 as a first command and an address CA1. According to the sending of the second read request R2, the timeout controller 131 may start measuring (or counting) the first time T1 ( Figure 3 In other words, after the second read request R2 is sent by the first controller 130a and / or when the second read request R2 is received by the second controller 230, the timer associated with the first time T1 may be started.
[0113] The second controller 230 may generate a third read request R3 according to the second read request R2. In operation S233, the second controller 230 may send the third read request R3 to the nonvolatile memory device 220. The third read request R3 may be sent to the nonvolatile memory device 220 as a third command and an address CA3.
[0114] For example, the second controller 230 may not process the second read request R2, and may send the unprocessed second read request R2 as the third read request R3 to the nonvolatile memory device 220. In some embodiments, the second controller 230 may process the second read request R2 into a form suitable for the nonvolatile memory device 220, and may send the processed second read request R2 to the nonvolatile memory device 220 as the third read request R3.
[0115] The nonvolatile memory device 220 may perform a read operation RD in response to the third read request R3 . Data read from the nonvolatile memory device 220 may be transmitted to the second controller 230 .
[0116] In one exemplary embodiment, the read speed of the nonvolatile memory device 220 may be lower than the read speed of the volatile memory device 210. The time required to read data from the nonvolatile memory device 220 may be longer than the time required to read data from the volatile memory device 210.
[0117] As described above, LRDIMM is based on dynamic random access memory (DRAM). Therefore, the first time T1 and the second time T2 are determined by the read time of the dynamic random access memory (DRAM). The first time T1 and the second time T2 are shorter than the read time of the nonvolatile memory device 220.
[0118] The read operation RD of the nonvolatile memory device 220 may not be completed until the first time T1 elapses after the first controller 130a sends the second read request R2 in operation S232. In operation S234, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry ( Figure 3 Operation S150 shown).
[0119] The read operation RD of the nonvolatile memory device 220 may not be completed until the second time T2 elapses after the first controller 130a sends the second read request R2 in operation S234. In operation S235, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry ( Figure 3 Operation S150 shown).
[0120] The read operation RD of the nonvolatile memory device 220 may not be completed until the second time T2 elapses after the first controller 130a sends the second read request R2 in operation S235. In operations S236 and S237, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry ( Figure 3 Operation S150 shown).
[0121] Until the read retry is performed the number of times of the first value N1, the read operation RD of the nonvolatile memory device 220 may not be completed. After reaching N1 retries, the first controller 130a may determine that a read failure occurs. The first controller 130a may generate an error report ER. In operation S238, the error report ER may be sent to the processor 110. The processor 110 may perform an error handling EH according to the error report ER. The error handling EH may include an exception handling including a known handling (such as a machine check handling).
[0122] In operation S239, the read operation RD of the nonvolatile memory device 220 may be completed, and the data may be sent to the second controller 230. However, the first controller 130a may have determined that a read failure has occurred. Therefore, when a read operation of the nonvolatile memory device 220 of the main memory 140a is performed, the read operation of the main memory 140a may fail due to the difference between the read speed of the nonvolatile memory device 220 and the read speed of the volatile memory device 210.
[0123] To solve this problem, according to an embodiment of the inventive concept, the first controller 130a may perform a read retry without limiting the number of times. For example, the first value N1 may be stored in the register 132. The first controller 130a according to an embodiment of the inventive concept may invalidate the first value N1 stored in the register 132, or may set the first value N1 to infinity or a very large number that is logically close to infinity.
[0124] Figure 7 is a flowchart for describing an operating method of the first controller 130a according to some embodiments of the inventive concept. Figure 1 , Figure 2 and Figure 7 In operation S310 , the first controller 130 a may receive a first read request. For example, the first controller 130 a may receive the first read request from the processor 110 .
[0125] In operation S320, the first controller 130a may send a second read request R2 to the second controller 230. For example, the first controller 130a may generate a second read request using the first read request. The format of the first read request may be the same as or different from the format of the second read request. One or more second read requests may be generated from one first read request.
[0126] In operation S330 , the first controller 130 a may determine whether normal data is received within the first time T1 . When normal data is received within the first time T1 , in operation S340 , it may be determined that the reading is successful . The first controller 130 a may transmit the received normal data to the processor 110 .
[0127] When normal data is not received within the first time T1 or error data is received within the first time T1, the first controller 130a may resend the second read request to the second controller 230 to perform a read retry in operation S350.
[0128] In operation S360, the first controller 130a may determine whether normal data is received within the second time T2. The second time T2 may be shorter than the first time T1. When normal data is received within the second time T2, in operation S340, it may be determined that the reading is successful.
[0129] When normal data is not received within the second time T2, the first controller 130a may perform a read retry in operation S350. That is, the first controller 130a may resend a read request without limiting the number of times.
[0130] Figure 8 Is used to describe Figure 7 For example, the first command and the address CA1 may be associated with the nonvolatile memory device 220, and the read operation performed in the nonvolatile memory device 220 may be performed in the nonvolatile memory device 220. Figure 8 is shown in .
[0131] Reference Figure 1 , Figure 2 , Figure 7 and Figure 8 , the processor 110 may generate a first read request R1. In operation S411, the processor 110 may send the first read request R1 to the first controller 130a. The first controller 130a may generate a second read request R2 according to the first read request R1.
[0132] In operation S412, the first controller 130a may send a second read request R2 to the second controller 230. The second read request R2 may be sent to the second controller 230 as a first command and an address CA1. According to the sending of the second read request R2, the timeout controller 131 may start measuring (or counting) the first time T1 ( Figure 7 Operation S330 shown).
[0133] The second controller 230 may generate a third read request R3 according to the second read request R2. In operation S413, the second controller 230 may send the third read request R3 to the nonvolatile memory device 220. The third read request R3 may be sent to the nonvolatile memory device 220 as a third command and an address CA3.
[0134] The nonvolatile memory device 220 may perform a read operation RD in response to the third read request R3 . Data read from the nonvolatile memory device 220 may be transmitted to the second controller 230 .
[0135] The read operation RD of the nonvolatile memory device 220 may not be completed until the first time T1 elapses after the first controller 130a sends the second read request R2 in operation S412. In operation S414, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry ( Figure 7 Operation S350 shown).
[0136] The read operation RD of the nonvolatile memory device 220 may not be completed until the second time T2 elapses after the first controller 130a sends the second read request R2 in operation S414. In operation S415, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry ( Figure 7 Operation S350 shown).
[0137] Similarly, as the second time T2 elapses, in operations S416 to S418, the first controller 130a may resend the second read request R2 to the second controller 230 to perform a read retry. While the read operation RD is being performed in the nonvolatile memory device 220, the second controller 230 may ignore the received second read request associated with the read operation RD (e.g., the second read request received in operations S414 to S418).
[0138] In operation S419, the read operation RD may be completed in the nonvolatile memory device 220, and the read data may be transmitted to the second controller 230. The second controller 230 may perform a first data transmission DT1 to transmit the data read from the nonvolatile memory device 220 to the first controller 130a. In operation S420, the first data transmission DT1 may be completed, and the data may be transmitted to the first controller 130a.
[0139] In operation S418, after sending the second read request R2 and before the second time T2 elapses, the first controller 130a may receive data from the main memory 140a. For example, the received data may be normal data. Therefore, the first controller 130a may determine that the read is successful.
[0140] The first controller 130a may perform a second data transfer DT2 to transmit data received from the second controller 230 to the processor 110. In operation S421, the second data transfer DT2 may be completed, and the data may be transmitted to the processor 110. The processor 110 may determine a read completion RC.
[0141] As described above, since the first controller 130 a can perform a read request without limiting the number of times, normal data can be read from the nonvolatile memory device 220 .
[0142] Fig. 9 Is used to describe Figure 7 For example, the first command and address CA1 may be associated with the nonvolatile memory device 220, and the volatile memory device 210 may be used as a cache memory of the nonvolatile memory device 220. Fig. 9 is shown in .
[0143] Reference Figure 1 , Figure 2 , Figure 7 and Fig. 9 In operation S431, the processor 110 may send a first read request R1 to the first controller 130a. The first controller 130a may generate a second read request R2 according to the first read request R1.
[0144] In operation S432, the first controller 130a may send a second read request R2 to the second controller 230. The second read request R2 may be sent to the second controller 230 as a first command and an address CA1. According to the sending of the second read request R2, the timeout controller 131 may start measuring (or counting) the first time T1 ( Figure 7 Operation S330 shown).
[0145] The second controller 230 may determine whether the storage space associated with the second read request R2 is mapped to the volatile memory device 210 (i.e., whether it is a cache hit). When the storage space associated with the second read request R2 is mapped to the volatile memory device 210, that is, when a cache hit occurs, the second controller 230 may send a third read request R3 as a second command and address CA2 or a second control signal CTRL2 to the volatile memory device 210.
[0146] The read operation of the volatile memory device 210 and the reference Figure 4 or Figure 5 The read operations of the volatile memory device 210 described above are the same. Therefore, their detailed description will be omitted.
[0147] When the storage space associated with the second read request R2 is not mapped to the volatile memory device 210 , that is, when a cache miss occurs, the second controller 230 may map the storage space associated with the second read request R2 to the volatile memory device 210 .
[0148] The second controller 230 may generate a third read request R3 for the storage space associated with the second read request R2. In operation S433, the second controller 230 may send the third read request R3 to the nonvolatile memory device 220. The third read request R3 may be sent to the nonvolatile memory device 220 as a third command and an address CA3.
[0149] The nonvolatile memory device 220 may perform a read operation RD in response to the third read request R3 . Data read from the nonvolatile memory device 220 may be transmitted to the second controller 230 .
[0150] As the first time T1 or the second time T2 passes or expires, the first controller 130a may send a second read request R2 to perform a read retry in operations S434 to S438. The second read request R2 may be repeatedly sent as needed to generate a successful read operation.
[0151] In operation S439 , the read operation RD of the nonvolatile memory device 220 may be successfully completed, and data read from the nonvolatile memory device 220 may be transmitted to the second controller 230 .
[0152] When data is transmitted from the nonvolatile memory device 220, in operation S440, the second controller 230 may transmit a write request W to the volatile memory 210. The write request W may include data read from the nonvolatile memory device 220. In some embodiments, the write request W may be transmitted together with the data read from the nonvolatile memory device 220.
[0153] For example, a write request W may be sent as a second command and address CA2 to the volatile memory device 210. In some embodiments, the write request W may be sent as a second control signal CTRL2 to the volatile memory device 210. For example, the second controller 230 may activate a specific control signal such as SAVEn.
[0154] When a specific control signal is activated, the second controller 230 may transmit data read from the nonvolatile memory device 220 to the volatile memory device 210. The volatile memory device 210 may write the data received from the second controller 230 in response to the activated specific control signal.
[0155] The volatile memory device 210 may perform a write operation WR according to the write request W. Since the volatile memory device 210 performs the write operation WR, the first memory space of the nonvolatile memory device 220 associated with the second read request R2 may be mapped (or backed up) to the second memory space of the volatile memory device 210 .
[0156] After the write operation WR is completed, in operation S441, the first controller 130a may send a second read request R2 to the second controller 230. In operation S442, the second controller 230 may send a third read request R3 to the volatile memory device 210 in response to the second read request R2 received in operation S441 after the read operation RD is completed. The third read request R3 may request to read data mapped from the nonvolatile memory device 220 to the volatile memory device 210.
[0157] The volatile memory device 210 may perform a read operation RD in response to the third read request R3. When the read operation RD is completed, in operation S443, data associated with the second read request R2 may be transmitted to the second controller 230. The second controller 230 may perform a first data transmission DT1.
[0158] When the first data transmission DT1 is performed, in operation S444, data may be sent to the first controller 130a. Before the second time T2 elapses after sending the second read request R2 in operation S441, the first controller 130a may receive data associated with the second read request R2. Therefore, the first controller 130a may determine that the read is successful ( Figure 7 Operation S340 shown).
[0159] The first controller 130a may perform the second data transmission DT2 to send the data to the processor 110. When the data is sent, the processor 110 may determine that the reading is completed in operation S445.
[0160] Fig.10 yes Figure 7 An example of a read operation is shown. Figure 1 , Figure 2 , Figure 7 and Fig.10 , since operations S451 to S460 are Fig. 9 Operations S431 to S440 are shown to be the same, so their detailed descriptions will be omitted.
[0161] exist Fig.10In operation S461 of the present invention, the first controller 130a may send a second read request R2 to the second controller 230. In operation S462, the second controller 230 may send a third read request R3 to the volatile memory device 210 in response to the second read request R2. For example, the second controller 230 may send the second read request R2 received from the first controller 130a to the volatile memory device 210 as the third read request R3.
[0162] When the volatile memory device 210 performs the read operation RD, in operation S463, the read data may be directly transmitted to the first controller 130a through the second controller 230 and the first to eighth data buffers 241 to 248 without being controlled and buffered by the second controller 230. Since the LRDIMM is based on a dynamic random access memory (DRAM), the volatile memory device 210 may directly communicate with the first controller 130a.
[0163] Operation S464 can be performed with Fig. 9 Operation S445 is shown to be the same. When the data read from the volatile memory device 210 is directly transmitted to the first controller 130a, the time until the first controller 130a receives the data after the second read request R2 is transmitted can be reduced.
[0164] Fig.11 Is used to describe Figure 7 A flowchart showing an example of an application of the method of operation shown. Figure 1 , Figure 2 and Fig.11 Operations S510 to S550 may be performed with reference to Figure 7 The described operations S310 to S350 are the same. That is, the first controller 130a may perform a read retry without limiting the number of times.
[0165] In operation S560, when normal data is not received within the second time T2, operation S570 may be performed. In operation S570, after the second read request R2 is sent for the first time, it is determined whether a third time period T3 (hereinafter, also referred to as the third time T3) has passed. When the third time T3 has not passed, in operation S550, a read retry may be performed without limiting the number of times.
[0166] When the third time T3 elapses, the first controller 130a may determine a read failure when an uncorrectable error occurs in operation S580. In some embodiments, information about the third time T3 may be stored in the register 132.
[0167] The third time T3 may be determined according to the time (eg, read time) required to perform a read operation in the nonvolatile memory device 220. For example, the third time T3 may be longer than the read time (eg, the third time T3 may be two or more times the read time).
[0168] Fig.12 is an example of performing a read operation while measuring the third time T3. Fig. 9 In contrast, in operation S432 , when the first controller 130 a sends the second read request R2 to the second controller 230 , the timeout controller 131 may start measuring (or counting) the third time T3 .
[0169] In some embodiments, the third time T3 may be longer than the time to perform a read operation on the nonvolatile memory device 220. When the timeout is measured, the first controller 130a may be prevented from repeatedly performing a read retry when normal data is not read due to an error in the main memory 140a. That is, a hang may be prevented from occurring in the memory system including the first controller 130a and the main memory 140a.
[0170] Fig.13 is a block diagram illustrating a computing device 100b according to some embodiments of the inventive concept. Fig.13 , the computing device 100b may include a processor 110 , a second cache memory 120 , a first controller 130b , a main memory 140b , a storage interface 150 , and a storage device 160 .
[0171] The operations of the processor 110, the second cache memory 120, the storage interface 150, and the storage device 160 may be similar to those described in the reference Figure 1 The operations of the processor 110, the second cache memory 120, the storage interface 150, and the storage device 160 are described to be the same or similar. Therefore, their detailed descriptions will be omitted.
[0172] and Figure 1 In contrast, the first controller 130b may also communicate with the main memory 140b via the system management bus SMBus. The main memory 140b may include a serial presence detection (SPD) device 141 and a register updater 142. The SPD device 141 may allow the first controller 130b to know that the main memory 140b exists and what timing to use to access the main memory 140b.
[0173] The SPD device 141 may include information about the main memory 140b. When power is supplied to the first controller 130b and the main memory 140b, the first controller 130b may access the SPD device 141 of the main memory 140b to obtain information about the main memory 140b.
[0174] Based on the obtained information, the first controller 130b may set or adjust a method or parameter for accessing the main memory 140b. For example, the first controller 130b may access the SPD device 141 via the system management bus SMBus.
[0175] The register updater 142 may update the register 132 of the first controller 130b via the system management bus SMBus. For example, when the first controller 130b accesses the SPD device 141 of the main memory 140b, the first controller 130b may allow the main memory 140b to access the register 132 via the system management bus SMBus.
[0176] While the first controller 130b is accessing the SPD device 141, the register updater 142 may update some of the information stored in the register 132. For example, the register updater 142 may update the information stored in the register 132 so that the reference Figures 7 to 12 The described operation is allowed.
[0177] Fig.14 1 is a block diagram showing a main memory 140b including an SPD device 141 and a register updater 142. Figure 2 In contrast, the second controller 230 may include an SPD device 141 and a register updater 142 .
[0178] The SPD device 141 may be included in the second controller 230, or may be provided as a package separate from the second controller 230 to be disposed outside the second controller 230. The SPD device 141 and the register updater 142 may communicate with the first controller 130b through the system management bus SMBus.
[0179] Fig.15 1 is a flowchart for describing the operation method of the main memory 140b updating the register 132. Figures 13 to 15 In operation S610, the second controller 230 may detect power-on. In operation S620, the register updater 142 of the second controller 230 may update information stored in the register 132 through the system management bus SMBus.
[0180] For example, the register updater 142 may invalidate or remove the number of times limit stored in the register 132. The register updater 142 may update the third time T3 stored in the register 132 according to the read time of the nonvolatile memory device 220. For example, the register updater 142 may update the register 132 so that the third time T3 is longer than the read time.
[0181] Fig.16 is a block diagram illustrating a computing device 100c according to some embodiments of the inventive concept. Fig.16 , the computing device 100c may include a processor 110, a second cache memory 120, a first controller 130c, a main memory 140c, a storage interface 150, and a storage device 160.
[0182] The operations of the processor 110, the second cache memory 120, the storage interface 150, and the storage device 160 may be similar to those described in the reference Figure 1 The operations of the processor 110, the second cache memory 120, the storage interface 150, and the storage device 160 are described to be the same or similar. Therefore, their detailed descriptions will be omitted.
[0183] and Figure 1 In contrast, the main memory 140c may output a write error signal WRCRC to the first controller 130c. For example, the first controller 130c may send a write request to the main memory 140c. The write data of the write request may be sent together with the parity generated by the error correction code.
[0184] The main memory 140c can check whether there is an error in the write data by using parity check. When there is an error in the write data, the main memory 140c can enable (or, optionally, activate) (e.g., low level) the write error signal WRCRC. When the write error signal WRCRC is enabled, the first controller 130c can resend the write request.
[0185] The main memory 140c may include a write error controller 143. Fig.14 As described above, the write error controller 143 may be included in the second controller 230. The write error controller 143 may control the write error signal WRCRC when performing writing to the nonvolatile memory device 220. For example, the write error signal WRCRC may include an ALERTn signal.
[0186] Fig.17 1 is a flowchart for describing the write operation of the first controller 130c. Figure 2 , Fig.16 and Fig.17 In operation S710 , the first controller 130 c may receive a first write request. For example, the first controller 130 c may receive the first write request from the processor 110 .
[0187] In operation S720, the first controller 130c may send a second write request to the second controller 230. For example, the first controller 130c may generate a second write request using the first write request. The format of the first write request may be the same as or different from the format of the second write request. One or more second write requests may be generated from one first write request.
[0188] In operation S730, the first controller 130c may check whether the write error signal WRCRC is enabled. When the write error signal WRCRC is disabled (or, alternatively, deactivated), in operation S740, the first controller 130c may determine that the write is successful.
[0189] When the write error signal WRCRC is enabled, the first controller 130c may perform recovery in operation S750. For example, the first controller 130c may perform recovery of a communication link between the first controller 130c and the main memory 140c. Recovery may include ZQ calibration, write training, and / or read training.
[0190] In operation S720, the first controller 130c may resend the second write request. That is, the first controller 130c may perform a write retry without limiting the number of times.
[0191] Fig.18 140c is a flowchart for describing the write operation of the main memory 140c. Figure 2 , Fig.16 and Fig.18 In operation S810, the second controller 230 may receive a second write request. For example, the second controller 230 may receive the second write request from the first controller 130c as a first command and an address CA1.
[0192] In operation S820, the second controller 230 may determine whether the second write request results in writing to the nonvolatile memory device 220. When the second write request does not result in writing to the nonvolatile memory device 220, in operation S830, the second controller 230 may perform a write operation on the volatile memory device 210 according to the second write request.
[0193] When the second write request results in writing to the nonvolatile memory device 220 , the second controller 230 may activate the write error signal WRCRC in operation S840 . The second controller 230 may perform a write operation to the nonvolatile memory device 220 in operation S850 .
[0194] After the write operation to the nonvolatile memory device 220 is completed, when a second write request is received in operation S860 , the second controller 230 may deactivate (eg, high level) the write error signal WRCRC in operation S870 .
[0195] As reference Figure 6 As described above, a write operation to the nonvolatile memory device 220 may require a longer time than a write operation to the volatile memory device 210. The first controller 130c may be configured to control the main memory 140c based on a write speed of the volatile memory device 210.
[0196] For example, the first controller 130c may send the second write request to the main memory 140c, and may determine that the write operation is completed when there is no reply from the main memory 140c (eg, the write error signal WRCRC is disabled).
[0197] When the write operation to the nonvolatile memory device 220 is not completed and the first controller 130c determines that the write is completed, a write failure may occur. To solve this problem, the main memory 140c according to an embodiment of the inventive concept may maintain the write error signal WRCRC in an enabled state (e.g., a low level) until the write operation to the nonvolatile memory device 220 is completed.
[0198] Fig.19 Is used to describe Fig.18 For example, the first command and address CA1 may be associated with the volatile memory device 210, and the write operation performed in the volatile memory device 210 may be performed in the following manner: Fig.19 is shown in .
[0199] Reference Figure 2 , Fig.16 , Fig.18 and Fig.19 , the processor 110 may generate a first write request W1. In operation S911, the processor 110 may send the first write request W1 to the first controller 130c. The first controller 130c may generate a second write request W2 according to the first write request W1.
[0200] In operation S912, the first controller 130c may transmit a second write request W2 to the second controller 230. The second write request W2 may be transmitted to the second controller 230 as a first command and an address CA1.
[0201] The second controller 230 may generate a third write request W3 according to the second write request W2. In operation S913, the second controller 230 may send the third write request W3 to the volatile memory device 210. The third write request W3 may be sent to the volatile memory device 210 as a second command and an address CA2.
[0202] For example, the second controller 230 may not process the second write request W2, and may send the unprocessed second write request W2 as the third write request W3 to the volatile memory device 210. In some embodiments, the second controller 230 may process the second write request W2 into a form suitable for the volatile memory device 210, and may send the processed second write request W2 to the volatile memory device 210 as the third write request W3.
[0203] The volatile memory device 210 may perform a write operation WR in response to the third write request W3. Figure 5 As described above, the first controller 130 c may directly write data to the volatile memory device 210 through the second controller 230 and the first to eighth data buffers 241 to 248 without the control or buffering of the second controller 230 .
[0204] When there is no error in the write data, the second controller 230 may maintain the write error signal WRCRC in a disabled state of a high level. When there is an error in the write data, the second controller 230 may control the write error signal WRCRC to an enabled state that may correspond to a low level. The first controller 130c may resend the second write request W2 according to the enabled write error signal WRCRC.
[0205] In some embodiments, the second controller 230 or the volatile memory device 210 may check whether there is an error in the write data. When there is an error in the write data, the second controller 230 or the volatile memory device 210 may enable the write error signal WRCRC to a low level.
[0206] For example, the write error signal WRCRC output from the volatile memory device 210 may be included in the second control signal CTRL2 and may be transmitted to the second controller 230. The second controller 230 may transmit the write error signal WRCRC received from the volatile memory device 210 to the first controller 130c.
[0207] Fig. 20 Is used to describe Fig.18 For example, the write operation of the nonvolatile memory device 220 is performed according to the first command and the address CA1. Fig. 20is shown in .
[0208] Reference Figure 2 , Fig.16 , Fig.18 and Fig. 20 , the processor 110 may generate a first write request W1. In operation S921, the processor 110 may send the first write request W1 to the first controller 130c. The first controller 130c may generate a second write request W2 according to the first write request W1.
[0209] In operation S922, the first controller 130c may send a second write request W2 to the second controller 230. The second write request W2 may be sent to the second controller 230 as a first command and an address CA1. The second write request W2 may result in a write operation to the nonvolatile memory device 220. Therefore, when receiving the second write request W2, the second controller 230 may enable the write error signal WRCRC to a low level.
[0210] The second controller 230 may generate a third write request W3 according to the second write request W2. In operation S923, the second controller 230 may send the third write request W3 to the nonvolatile memory device 220. The third write request W3 may be sent to the nonvolatile memory device 220 as a third command and an address CA3.
[0211] For example, the second controller 230 may not process the second write request W2, and may send the unprocessed second write request W2 as the third write request W3 to the nonvolatile memory device 220. In some embodiments, the second controller 230 may process the second write request W2 into a form suitable for the nonvolatile memory device 220, and may send the processed second write request W2 to the nonvolatile memory device 220 as the third write request W3.
[0212] The nonvolatile memory device 220 may perform a write operation WR in response to the third write request W3. When the write error signal WRCRC is enabled, the first controller 130c may perform recovery RE in operation S924. After recovery RE is performed, the first controller 130c may resend the second write request W2 to perform a write retry in operation S925.
[0213] When the write operation WR is performed in the nonvolatile memory device 220 , the first controller 130 c may repeatedly perform recovery RE and write retry according to the enabled write error signal WRCRC in operations S926 to S928 .
[0214] In operation S929, the nonvolatile memory device 220 may notify the second controller 230 that the write operation WR is completed. For example, the nonvolatile memory device 220 may control the ready / busy signal (R / nB) so that the ready / busy signal (R / nB) indicates a ready state. When the ready / busy signal (R / nB) indicates a ready state, the nonvolatile memory device 220 may notify the second controller 230 that the write operation WR is completed.
[0215] In operation S930, the first controller 130c may send a second write request W2 to the second controller 230 to perform a write retry. In operation S930, when the second write request W2 is received, the second controller 230 may disable the write error signal WRCRC to a high level. When the write error signal WRCRC is disabled, the first controller 130c may determine that the write operation WR is completed.
[0216] As described above, when performing the write operation WR to the nonvolatile memory device 220, the second controller 230 may enable the write error signal WRCRC even if no error occurs. When the write error signal WRCRC is enabled, the first controller 130c may resend the write request without limiting the number of times. Therefore, the first controller 130c is held (i.e., the first controller 130c continues to wait for the write operation WR to the nonvolatile memory device 220) and the write error is prevented until the write operation WR to the nonvolatile memory device 220 is completed.
[0217] Fig.21 Is used to describe Fig.18 For example, the first command and address CA1 may be associated with the nonvolatile memory device 220, and the volatile memory device 210 may be used as a cache memory of the nonvolatile memory device 220. Fig.21 is shown in .
[0218] Reference Figure 2 , Fig.16 , Fig.18 and Fig.21 , the processor 110 may generate a first write request W1. In operation S941, the processor 110 may send the first write request W1 to the first controller 130c. The first controller 130c may generate a second write request W2 according to the first write request W1.
[0219] In operation S942, the first controller 130c may send a second write request W2 to the second controller 230. The second write request W2 may be sent as a first command and an address CA1 to the second controller 230. The second controller 230 may determine whether a storage space associated with the first command and the address CA1 is mapped to the volatile memory device 210.
[0220] For example, the storage space associated with the first command and address CA1 may not be mapped to the volatile memory device 210. In addition, when the free storage space of the volatile memory device 210 is insufficient to provide the storage space associated with the first command and address CA1, a write operation to the nonvolatile memory device 220 may result.
[0221] The second controller 230 may select a specific storage space in the storage space that is mapped to the volatile memory device 210, and may delete the data of the selected specific storage space. For example, the selected specific storage space may be a dirty storage space that has been previously used. The second controller 230 may cause a write operation to the non-volatile memory device 220 by sending the data of the selected specific storage space back to the non-volatile memory device 220.
[0222] In operation S943, the second controller 230 may transmit a read request R for the selected specific storage space to the volatile memory device 210. The read request R may be transmitted to the volatile memory device 210 as a second command and address CA2 or a second control signal CTRL2.
[0223] For example, a read request R2 may be sent as a second command and address CA2 to the volatile memory device 210. In some embodiments, the read request R may be sent as a second control signal CTRL2 to the volatile memory device 210. For example, the second controller 230 may activate a specific control signal such as SAVEn.
[0224] When a specific control signal is activated, the volatile memory device 210 may output stored data such as data at a location (eg, bank) specified by an internal schedule and / or all data. The second controller 230 may store data received from the volatile memory device 210 .
[0225] The volatile memory device 210 may perform a read operation RD in response to the read request R. In operation S944, data read from the volatile memory device 210 may be transmitted to the second controller 230. When data of the selected storage space is read from the volatile memory device 210, in operation S945, the second controller 230 may transmit a third write request W3 to the nonvolatile memory device 220. The third write request W3 may be transmitted to the nonvolatile memory device 220 as a third command and address CA3 or a third control signal CTRL3.
[0226] The nonvolatile memory device 220 may perform a write operation WR in response to the third write request W3. When the nonvolatile memory device 220 performs the write operation WR, the write error signal WRCRC is enabled. Therefore, when the nonvolatile memory device 220 performs the write operation WR, in operations S946 to S950, the first controller 130c may repeatedly perform a write retry to send a recovery RE and a second write request W2. In one example, in response to determining that the free space should be ensured by the second controller 230 reading the data of the volatile memory and writing the data into the nonvolatile memory, the second controller 230 may activate WRCRC. Therefore, when performing a volatile memory read, WRCRC may be activated.
[0227] In operation S951, the nonvolatile memory device 220 may inform the second controller 230 that the write operation WR is completed. After the write operation WR is completed, in operation S952, the first controller 130c may send a second write request W2 to perform a write retry.
[0228] After the write operation WR to the nonvolatile memory device 220 is completed, when the second write request W2 is received (operation S952), the second controller 230 may disable the write error signal WRCRC. In operation S952, the second controller 230 may map the storage space associated with the first command and the address CA1 to the volatile memory device 210 according to the second write request W2.
[0229] In operation S953, the second controller 230 may transmit a third write request W3 to the volatile memory device 210. The third write request W3 may be transmitted as a second command and address CA2 or a second control signal CTRL2 to the volatile memory device 210. The volatile memory device 210 may perform a write operation WR in response to the third write request W3.
[0230] Fig. 22 yes Fig.18 An example timing diagram for a write operation is shown in Figure 1. Figure 2 , Fig.16 , Fig.18 and Fig. 22 , since operations S961 to S971 correspond to Fig.21 Operations S941 to S951 are not shown, so their detailed descriptions will be omitted.
[0231] After the write operation WR is completed in the nonvolatile memory device 220, in operation S972, the first controller 130c may send a second write request W2 to the second controller 230. The second controller 230 may send the second write request W2 to the volatile memory device 210 as a third write request W3.
[0232] Data transmitted from the first controller 130c may be directly transmitted to the volatile memory device 210 through the second controller 230 and the first to eighth data buffers 241 to 248 without being controlled and buffered by the second controller 230. Since the LRDIMM is based on a dynamic random access memory (DRAM), the volatile memory device 210 may directly communicate with the first controller 130c.
[0233] Fig.23 yes Fig.18 An example timing diagram for a write operation is shown in Figure 1. Figure 2 , Fig.16 , Fig.18 and Fig.23 , when the read operation RD is completed, the second controller 230 may wait without sending the third write request W3 to the nonvolatile memory device 220. After the read operation RD is completed, in operation S947, a second write request W2 may be sent from the first controller 130c. In operation S954, the second controller 230 may send the third write request W3 to the nonvolatile memory device 220 in response to the second write request W2.
[0234] In some embodiments, Fig.13 and Fig.14 In FIG. 1 , the second controller 230 is described as including an SPD device 141 and a register updater 142. In addition, in Fig.16 , the second controller 230 is described as including the write error controller 143. However, not limited thereto, the second controller 230 according to an exemplary embodiment of the inventive concept may include the SPD device 141, the register updater 142, and the write error controller 143.
[0235] The register updater 142 may update the registers 132 of the first controllers 130a, 130b, and 130c to perform read retry without limiting the number of times. In addition, the register updater 142 may update the registers 132 of the first controllers 130a, 130b, and 130c to perform write retry without limiting the number of times.
[0236] While the inventive concepts have been described with reference to exemplary embodiments thereof, it will be apparent to those skilled in the art that various changes and modifications may be made thereto without departing from the spirit and scope of the inventive concepts as set forth in the following claims.
Claims
1. A memory system, include: Non-volatile memory module; The first controller is configured to control the non-volatile memory module, wherein the non-volatile memory module comprises: a volatile memory device; a non-volatile memory device; a second controller configured to control the volatile memory device and the non-volatile memory device, wherein the first controller is configured to send a read request to the second controller, wherein the second controller is configured to control the volatile memory device or the nonvolatile memory device to start a read operation in response to a read request, During a read operation according to the read request, when normal data is not received from the nonvolatile memory device, the first controller resends the read request to the second controller one or more times without limiting the number of times the first controller resends the read request one or more times.
2. The memory system according to claim 1, in, Normal data includes error-free data and / or correctable data having errors within a correctable range. wherein after sending the read request, when a first time period elapses without receiving normal data, the first controller performs a first resending of one or more resendings of the read request, Wherein, after the first retransmission of the read request, when a second period of time has passed without receiving normal data, the first controller performs a second retransmission of the one or more retransmissions of the read request.
3. The memory system according to claim 2, in, The second time period is shorter than the first time period.
4. The memory system according to claim 1, in, Normal data includes error-free data and / or correctable data having errors within a correctable range. In response to receiving the read request, the second controller reads data including normal data and / or uncorrectable data from one of the nonvolatile memory device and the volatile memory device.
5. The memory system according to claim 4, in, While the second controller is reading the data from the non-volatile memory device, the second controller ignores one or more resending of the read request.
6. The memory system according to claim 5, in, After reading the data from the nonvolatile memory device, the read data is sent to the first controller in response to at least one of the one or more resending of the read request.
7. The memory system according to claim 1, in, After performing a first retransmission of the one or more retransmissions of the read request, when a third period of time elapses without receiving normal data, the first controller determines that the read has failed.
8. The memory system according to claim 7, in, Normal data includes error-free data and / or correctable data having errors within a correctable range. The third time period is longer than a time period for the second controller to read data from the non-volatile memory device, wherein the data includes normal data and / or uncorrectable data.
9. The memory system according to claim 1, in, The first controller includes: a register storing a limit on the number of times the first controller performs one or more resending of the read request, Therein, the stored limit includes a number that is logically close to infinity.
10. The memory system according to claim 9, in, The second controller includes a serial presence detection device that indicates to the first controller that the non-volatile memory is present.
11. The memory system according to claim 9, in, The second controller is configured to communicate with the first controller via a system management bus.
12. The memory system according to claim 1, in, The first controller sends a write request to the second controller. Wherein, during a write operation according to the write request, when the second controller writes write data to the nonvolatile memory device, the second controller activates a write error signal provided to the first controller.
13. The memory system according to claim 12, in, In response to the write request, the second controller performs writing to one of the volatile memory device and the non-volatile memory device, When the writing to the non-volatile memory device according to the writing request is completed, the second controller deactivates the writing error signal.
14. The memory system according to claim 12, in, When the write error signal is activated, the first controller resends the write request to the second controller.
15. The memory system according to claim 12, in, After writing the write data to the nonvolatile memory device is completed, the second controller deactivates the write error signal upon receiving the write request that has been resent.
16. The memory system according to claim 15, in, The second controller ignores the resent write request while the write data is being written to the nonvolatile memory device.
17. A memory module, include: a volatile memory device; a non-volatile memory device; a controller configured to control the volatile memory device and the nonvolatile memory device, wherein during a write operation, in response to a write request, the controller performs a write to one of the volatile memory device and the non-volatile memory device, Wherein, when writing to the nonvolatile memory device is performed, the controller activates a write error signal output to the external device, the write error signal causing the write request to be resent, wherein during the read operation, in response to a read request, the controller performs a read of one of the volatile memory device and the non-volatile memory device, wherein the controller is configured to: output a value to an external device to update a register of the external device, the value indicating the number of times a read retry from the external device to the memory module is performed, Wherein, during a read operation according to the read request, when normal data is not received from the nonvolatile memory device, the external device resends the read request to the controller one or more times without limiting the number of times the external device resends the read request one or more times.
18. The memory module according to claim 17, in, While executing a write to the non-volatile memory device, the controller ignores the write request being resent.
19. The memory module according to claim 17, in, While performing a read of the non-volatile memory device, the controller ignores the read request being resent.
20. A method of operating a memory module configured to communicate with an external controller, the memory module comprising a volatile memory device, a nonvolatile memory device, and a controller configured to control the volatile memory device and the nonvolatile memory device, the method include: detecting power-on at the memory module; outputting, by the memory module, a value to the external controller via a system management bus to update a register of the external controller, the value indicating a number of times a read retry from the external controller to the memory module has been performed, Wherein, during a read operation according to a read request, when normal data is not received from the nonvolatile memory device, the external controller performs one or more retransmissions of the read request to the controller without limiting the number of times the external controller performs one or more retransmissions of the read request.
