System and method for determining channel characteristics

By determining the communication channel characteristics between the memory controller and the memory and adjusting the transceiver settings using a neural network, the problem of inability to effectively correct channel characteristics in the prior art is solved, and the reliability and efficiency of data transmission are improved.

CN119003400APending Publication Date: 2024-11-22MICRON TECHNOLOGY INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410614493.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-19
Filing Date
2024-05-17
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing error correction encoding technology cannot effectively detect and correct errors caused by the characteristics of the communication channel between the memory controller and the memory, resulting in problems such as inversion of logic level in data transmission not being completely solved.

Method used

By determining the characteristics of the communication channel between the memory controller and the memory, the neural network training data set is used to adjust the transceiver settings to correct for the channel characteristics.

Benefits of technology

It improves the reliability and efficiency of data transmission, can detect and correct errors caused by channel characteristics, and enhances the accuracy of memory operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119003400A_ABST
    Figure CN119003400A_ABST
Patent Text Reader

Abstract

The invention relates to a system and method for determining channel characteristics. Apparatuses and methods for determining channel characteristics are disclosed. The channel characteristic may be a characteristic of a channel between the memory controller and the memory. The channel characteristic related to a logic level of data written to or read from the memory through the channel is determined at the memory controller, and a transceiver setting of a transceiver of the memory controller is modified in accordance with the determined characteristic. The channel characteristic may be determined based on storing a pilot signal at the memory controller, causing the pilot signal to be written to the memory, and comparing a read pilot signal corresponding to the written pilot signal with the stored pilot signal.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate generally to memory and, more particularly, in one or more illustrated embodiments, to systems and methods for determining channel characteristics associated with a memory. Background Art

[0002] High data reliability, high-speed memory access, and reduced chip size are some of the features required of semiconductor memories. Semiconductor memories, such as dynamic random access memories (DRAMs), may be controlled using one or more memory controllers that are coupled to the semiconductor memories via one or more communication channels. Memory access operations, such as read operations, write operations, refresh operations, etc., may be performed via one or more communication channels. Summary of the invention

[0003] According to one aspect of the present disclosure, a method is provided. The method includes: determining, at a memory controller, a characteristic of a communication channel between the memory controller and a memory, wherein the characteristic is related to a logic level of data written to or read from the memory through the communication channel; and modifying a transceiver setting of a transceiver of the memory controller for the communication channel based on the determined characteristic.

[0004] According to another aspect of the present disclosure, a method is provided. The method includes: receiving channel data of a channel between a memory controller and a memory, wherein the channel data includes characteristics of the channel and read-write data of the channel; generating a training data set using the channel data, wherein the training data set includes correlations between the read-write data of the channel and the characteristics of the channel; and training a neural network using the training data set to determine the channel characteristics of the channel based on the read-write data of the channel.

[0005] According to another aspect of the present disclosure, a device is provided. The device includes: a memory controller including a transceiver, the memory controller being configured to: determine a characteristic of a communication channel between the memory controller and a memory, wherein the characteristic is related to a logic level of data written to or read from the memory through the communication channel; and modify a transceiver setting of the transceiver for the communication channel based on the determined characteristic.

[0006] According to another aspect of the present disclosure, a non-transitory computer-readable medium is provided. The non-transitory computer-readable medium carries instructions that, when executed by at least one processor, cause the processor to perform operations including: receiving channel data of a channel between a memory controller and a memory, wherein the channel data includes characteristics of the channel and read-write data of the channel; generating a training data set using the channel data, wherein the training data set includes correlations between the read-write data of the channel and the characteristics of the channel; and training a neural network using the training data set to determine channel characteristics of the channel based on the read-write data of the channel. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a schematic block diagram illustrating a system for determining channel characteristics according to various embodiments.

[0008] Figure 2 is a block diagram illustrating a processing unit arranged in a computing system according to various embodiments.

[0009] Figure 3 is a schematic diagram illustrating a neural network according to various embodiments.

[0010] Figure 4 is a flow chart illustrating a process for training a neural network to determine channel characteristics according to various embodiments.

[0011] Figure 5 is a flow chart illustrating a process for modifying transceiver settings of a transceiver of a memory controller according to various embodiments.

[0012] Figure 6 is a flow chart illustrating a process for modifying transceiver settings of a transceiver of a memory controller using a pilot signal in accordance with various embodiments. DETAILED DESCRIPTION

[0013] The memory device may be controlled using one or more memory controllers that perform various operations. For example, the memory controller may include an error correction unit or logic to perform error correction coding (ECC), which may detect and / or correct errors associated with the memory. Typically, ECC techniques may encode raw data with additional encoded bits to protect the raw bits intended to be stored, retrieved, and / or transmitted. However, using ECC increases the amount of resources (e.g., processing and memory resources) used by the memory, and ECC may increase latency. In addition, ECC techniques may not be able to detect and correct certain types of errors, such as errors based on certain channel characteristics associated with a communication channel between a memory controller and the memory. Therefore, the present application describes an example of a method for determining channel characteristics and adjusting transceiver settings of a transceiver of a memory controller based on the channel characteristics.

[0014] Various embodiments of the present disclosure will be explained in detail below with reference to the accompanying drawings. The following detailed description refers to the accompanying drawings that show specific aspects and embodiments of the present disclosure in an illustrative manner. The detailed description contains sufficient details to enable a person skilled in the art to practice the embodiments of the present disclosure. Other embodiments may be utilized, and structural changes, logical changes, and electrical changes may be made without departing from the scope of the present disclosure. The various embodiments disclosed herein are not necessarily mutually exclusive, as some disclosed embodiments may be combined with one or more other disclosed embodiments to form new embodiments.

[0015] Figure 1 1 is a schematic block diagram illustrating a system 100 for determining channel characteristics according to various embodiments. The system 100 includes a host computing device 104 coupled to a memory controller 102, which can control one or more memory devices 112. In some examples, the memory controller 102 is embodied in or is an element of the host computing device 104. In these and other implementations, the host computing device 104 may include a system on a chip (SOC), a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), or the like, and the memory controller 102 may include logic, circuitry, or components of such a SOC, CPU, GPU, and / or FPGA. In some examples, the host computing device 104 may be one physical device and the memory controller 102 may be a separate physical device (e.g., each may be a chiplet in a chiplet system). In some cases, the memory controller 102 and the memory device 112 may be elements of a module (e.g., a dual in-line memory module (DIMM), a card, or a drive) and the host computing device 104 may be a separate processor.

[0016] The memory controller 102 may include a host interface 114, which may be coupled to a host bus 122 for connecting to a host computing device 104. The host interface 114 is coupled to and / or may be implemented using a processor 106 or processing resource, which may be a SOC, an application specific integrated circuit (ASIC), an FPGA, or the like, and may be separate from or may be an element of the host computing device 104, as described above. The processor 106 may include channel characteristic logic 108 and memory control logic 110. The host interface 114 and processor 106 may also be coupled to a cache 116, for example, via an internal memory controller bus. The processor 106 may be coupled to the memory device 112 via a memory interface 118 and a corresponding memory bus 124. The memory interface 118 may also be coupled to the cache 116, for example, also via an internal memory controller bus. Cache 116 may be coupled to error correction logic 120 , which may perform error correction on data communicated to / from cache 116 .

[0017] Memory device 112 may store data retrieved and / or accessed by host computing device 104. As an example, in operation, host computing device 104 processes a data set (e.g., an image or content data set) for use by one or more neural networks hosted on host computing device 104. The data set may be stored on memory device 112. For example, processor 106 may obtain the data set from one or more memory devices 112 via host bus 122. Memory device 112 may be included in one or more computing devices and / or may store data for one or more computing devices, such as, but not limited to, computing devices in a data center or personal computing devices. Processor 106 may store a data set (e.g., an image) in one or more of memory devices 112 (e.g., the data set may be distributed among memory devices 112). Processor 106 may store discrete units of a data set (e.g., an image or a video frame) in memory device 112.

[0018] The memory device 112 stores and provides information (e.g., data and instructions) in response to a memory access request received from the memory controller 102 (e.g., a memory access request from the host computing device 104 that is routed or processed by the processor 106). In operation, the memory device 112 processes the memory access request to store and / or retrieve information based on the memory access request. For example, the host computing device 104 may include a host processor that can execute a user application that requests stored data and / or stored instructions (and / or requests to store data / instructions) at the memory device 112. When executed, the user application generates a memory access request to access data or instructions in the memory device 112. Typically, the memory access request may include a command and an address, such as a memory command and a memory address. In various embodiments, the memory access request may include a command and an address for a read operation, a write operation, an activation operation, or a refresh operation at the memory device 112. Typically, the received command and address may facilitate the execution of a memory access operation for the memory device 112 at the memory device 112, such as a read operation, a write operation, an activation operation, and / or a refresh operation. Thus, a memory access request may be or include at least one memory address of one or more of the memory devices 112. In the example of a write operation, the memory access request may include data in addition to a command and an address, for example. The memory access request from the host computing device 104 is provided to the processor 106 via the host bus 122.

[0019] After receiving one or more memory access requests for memory devices 112 at processor 106, memory controller 102 may perform error correction on data associated with the memory access requests to produce error-corrected data, for example, using error correction logic 120. Additionally or alternatively, memory controller 102 may perform address translation using memory access requests (e.g., commands and addresses) to translate logical memory addresses into physical memory addresses. For example, the memory address in the memory address request may be a logical address known, for example, to a user application executing at host computing device 104. Memory controller 102 may be configured to translate that memory address into a physical address of one of memory devices 112 using memory control logic 110.

[0020] Additionally or alternatively, when processing a memory access request at the processor 106 of the memory controller 102, the memory controller 102 may, for example, in response to receiving a command and / or an address, perform error correction on data associated with the memory access request using the error correction logic 120. For example, in the context of a write operation, after performing an address translation using the memory control logic 110, the processor 106 may control error correction of data associated with the memory access request using the error correction logic 120. In the context of a read operation, the processor 106 may control error correction data read from the memory device 112 at the error correction logic 120 for the memory access request.

[0021] Whether it is a read or write operation, the error correction logic 120 can correct erroneous data associated with that operation (e.g., perform an error correction operation). The error correction logic 120 can correct erroneous data or information obtained from the memory device 112. For example, the error correction logic 120 can correct erroneous data according to an expected bit error rate (BER) for the operation of the memory device 112. For example, the error correction logic 120 can include low-density parity check correction logic that can correct erroneous data according to a low-density parity check (LDPC) code. Therefore, the error correction logic 120 can include an LDPC encoder. Additionally or alternatively, the error correction logic 120 can include a single parity check (SPC) encoder and / or an algebraic error correction circuit, such as one of a group including a Bose-Chaudhuri-Hocquenghem (BCH) encoder and / or a Reed Solomon ECC encoder and other types of error correction circuits. When utilizing error correction logic 120, memory controller 102 may correct errors that may occur to data during memory retrieval from or storage at memory device 112. The desired BER may be specified by host computing device 104 or a user executing a user application at host computing device 104.

[0022] Error correction logic 120 may be implemented using discrete components, such as an application specific integrated circuit (ASIC) or other circuitry, or the components may reflect functionality provided by circuitry within memory controller 102 that is not necessarily in a discrete physical form separate from other portions of memory controller 102. Figure 1 1 as a component within the memory controller 102 , the error correction logic 120 may be external to the memory controller 102 or have one or more components within the memory controller 102 and one or more components external to the memory controller 102 .

[0023] In operation, for erroneous data to be corrected using error correction logic 120, cache 116 may provide data (e.g., data obtained from memory device 112) to error correction logic 120 to correct that data, and subsequently receive the error-corrected data from error correction logic 120. In some implementations, cache 116 may be directly coupled to a storage device (such as a static random access memory (SRAM) or DRAM storage device) that is part of host computing device 104 and obtain data directly from that storage device. For example, a memory access request provided to host interface 114 may include a memory access command provided to cache to access a storage device on host computing device 104 to obtain data associated with the memory access request. In various implementations, cache 116 may be a dynamic memory device (such as DRAM), and may interact with processor 106. For example, cache 116 may be a data cache that includes or corresponds to one or more cache levels L1, L2, L3, L4 (e.g., as a multi-level cache), or any other cache level. In the context of a read operation, data retrieved from the memory device 112 may be stored at the cache 116 (eg, in a buffer or queue) such that the error correction logic 120 corrects the erroneous data as part of the read operation in the memory access request.

[0024] In some embodiments, when one or more memory access requests for memory device 112 are received at processor 106, processor 106 may route or store at least a portion of the one or more memory access requests in a queue or (several) buffers (e.g., request, processing, or data buffers) at cache 116. Data to be corrected at error correction logic 120 may be stored in a data buffer at cache 116. Additionally or alternatively, memory access requests may be stored in a queue or buffer for processing by processor 106, and / or portions of processed memory access requests may be stored in a processing buffer. For example, processor 106 may identify based on the memory access request that a memory address of the memory access request is to be stored in a NAND device. In order to store data in the NAND device, processor 106 may first control a NAND memory device of memory device 112 to erase data at a physical address (e.g., a memory address as translated by memory control logic 110). Thus, after processing the erase operation, processor 106 may store the write operation to be performed in the processing buffer.

[0025] Error correction operations (e.g., generating error correction codes or error-corrected data) may increase resource usage and / or increase latency. In addition, existing error correction techniques may not be able to detect and / or correct certain types of errors, such as errors based on the characteristics of the communication channel between the memory controller 102 and the memory device 112. For example, the characteristics of the communication channel may cause errors in logic levels, such as inversion of logic values ​​(e.g., causing the received bytes 00101010 to be written to the memory and / or read from the memory as 11010101). As used herein, a logic level may refer to a voltage level corresponding to a logic value, such as a relatively high voltage level corresponding to a logic value of 1 and a relatively low voltage level corresponding to a logic value of 0. In other examples, the logic level may be consistently wrong in other respects. In these and other examples, when using existing error correction techniques (e.g., error correction coding), the error will not be detected because the error correction code will also be modified due to the channel characteristics, so that the read data will appear correct when compared to the error correction code (because both are inverted or otherwise wrong). Thus, the disclosed systems and methods determine one or more characteristics of a channel (e.g., a communication channel between the memory controller 102 and one of the memory devices 112) and modify transceiver settings of a transceiver of the memory controller 102 based on the one or more characteristics. For example, the channel characteristic logic 108 may determine channel characteristics using a pilot signal, such as channel characteristics that cause an inversion of logic levels or other errors. The pilot signal is stored at the memory controller 102 (e.g., using the channel characteristic logic 108), and the same pilot signal is written to one of the memory devices 112 via a write operation through the communication channel. Next, a read operation is performed to retrieve a read pilot signal corresponding to the pilot signal written to the memory. Next, the read pilot signal is compared to the stored pilot signal to determine the characteristics of the channel. For example, if the read pilot signal matches the stored pilot signal, it is determined that the channel is operating properly. If the read pilot signal is the inversion of the stored pilot signal, the channel inversion logic value is determined. Based on the channel characteristics, the transceiver settings may be modified for the transceiver of the memory controller 102. For example, the memory control logic 110 may include transceiver settings, and the transceiver settings may be modified, for example, to instruct a particular channel to invert a logic value. The modified transceiver settings may then be used to correct data read from one of the memory devices 112 .

[0026] In operation, in response to one or more memory access requests including read operations, the memory device 112 provides access to the requested data, such that the read data is provided as plaintext data from the memory controller 102 to the host computing device 104 via the host bus 122. The memory interface 118 may provide the data via the memory bus 124 and an internal memory controller bus between the memory interface 118 and the cache 116, such as to be stored in the cache 116 for access by the error correction logic 120. Thus, the cache 116 may obtain the requested data from the memory devices 112 and their respective memory buses 124.

[0027] In the examples described herein, the memory device 112 may be a non-volatile memory device (e.g., a NAND memory device) or a volatile memory device. Typically, volatile memory may have some improved characteristics relative to non-volatile memory (e.g., volatile memory may be faster). The memory device 112 may also include one or more types of memory, including but not limited to: DRAM, SRAM, three-level cell (TLC) NAND, single-level cell (SLC) NAND, solid-state drive (SSD), or 3D XPoint memory device. Data stored in the memory device 112 or data to be accessed from the memory device 112 may be communicated from the memory controller 102 via a memory bus 124. For example, the memory bus 124 may be a peripheral component interconnect express (PCIe) bus operating according to the non-volatile memory express (NVMe) protocol.

[0028] In an example embodiment, processor 106 may include any type of microprocessor, central processing unit (CPU), ASIC, digital signal processor (DSP) implemented as part of a field programmable gate array (FPGA), system on chip (SoC), or other hardware. For example, processor 106 may be implemented using discrete components such as an application specific integrated circuit (ASIC) or other circuit system, or the components may reflect functionality provided by circuit system within memory controller 102, which circuit system does not necessarily have a discrete physical form separate from other parts of memory controller 102. Portions of processor 106 may be implemented by a combination of discrete components. For example, memory control logic 110 may be implemented as an ASIC, while channel characteristic logic 108 may be implemented as an FPGA having various stages in a specified configuration. Although in Figure 1 102 , but the processor 106 may be external to the memory controller 102 or have one or more components located within the memory controller 102 and one or more components located external to the memory controller 102 .

[0029] In various embodiments, the memory controller 102 may be an NVMe memory controller that may be coupled to the host computing device 104 via a host bus 122. The host bus 122 may be implemented as a PCIe bus operating according to the NVMe protocol. In an example, the memory bus 124 may be an NVMe bus operating according to the NVMe protocol. For example, in such embodiments, the memory device 112 may be implemented using a NAND memory device that is coupled to the NVMe memory controller 102 via a corresponding PCIe bus operating according to the NVMe protocol. Therefore, the memory bus 124 may be referred to as an NVMe memory bus. Compared to a memory system that can access a NAND memory device via a single host bus coupled to the host computing device 104, the system 100 may advantageously increase the rate and amount of processing by the number of NVMe memory buses 124 connected to the corresponding memory devices 112. Therefore, in an embodiment in which the processor 106 is an FPGA, the system 100 may be referred to as "accelerating" memory access and storage because the system 100 increases the availability of data transfers performed through the memory bus 124.

[0030] Additionally or alternatively, the memory controller 102 may be a non-volatile dual in-line memory module (NVDIMM) memory controller that is coupled to the host computing device 104 via a host bus 122. The host bus 122 may operate according to an NVDIMM protocol (e.g., NVDIMM-F, NVDIMM-N, NVDIMM-P, or NVDIMM-X). For example, in such implementations, the memory device 112 may be a NAND memory device or a 3D XPoint memory device. Thus, in such implementations, the memory device 112 may operate as a permanent storage device for the cache 116 (which may be a volatile memory device) and / or as a permanent storage device for any volatile memory on the memory controller 102 or the host computing device 104.

[0031] Figure 2 2 is a block diagram illustrating a processing unit 205 arranged in a computing system 200 according to various embodiments. For example, the system 200 may include Figure 1 The host computing device 104 and / or the memory controller 102, and the memory 230 may include Figure 1 The processing unit 205 may be configured to implement a neural network (e.g., Figure 3 A neural network 350), such as a neural network trained to determine channel characteristics of a channel between a memory controller and a memory.

[0032] The processing unit 205 may receive input data (e.g., X(i,j)) 210a-c from a computing system (e.g., a host computing device). In some examples, the input data 210a-c may be data associated with a memory access operation, such as data for a read operation and / or a write operation performed via a channel between a memory controller and a memory. The processing unit 205 may include multiplication units / accumulation units 212a-c, 216a-c and memory lookup units 214a-c, 218a-c that, when mixed with coefficient data retrieved from the memory 230, may generate output data (e.g., B(u,v)) 220a-c. In some examples, the output data 220a-c may be used as input data for another processing stage or as output data, such as one or more channel characteristics associated with a channel between a memory controller and a memory. In other words, the processing unit 205 may include one or more stages of a neural network such that the processing unit 205 receives input data 210a-c including data associated with a memory access operation and generates output data 220a-c including one or more of the channels through which the memory access operation is performed.

[0033] When one or more processing units 205 are implemented, a computer-readable medium at an electronic device (e.g., host computing device 104) may execute corresponding control instructions to perform operations through executable instructions 215 within the processing unit 205. For example, the control instructions provide instructions to the processing unit 205 that, when executed by the electronic device, cause the processing unit 205 to configure the multiplication units 212a-c to multiply the input data 210a-c with the coefficient data and to configure the accumulation units 216a-c to accumulate the processing results to generate the output data 220a-c.

[0034] The multiplication unit / accumulation unit 212a-c, 216a-c multiplies two operands from the input data 210a-c to produce a multiplication process result that is accumulated by the accumulation unit portion of the multiplication unit / accumulation unit 212a-c, 216a-c. The multiplication unit / accumulation unit 212a-c, 216a-c adds the multiplication process results to update the process results stored in the accumulation unit portion, thereby accumulating the multiplication process results. For example, the multiplication unit / accumulation unit 212a-c, 216a-c can perform a multiplication-accumulation operation such that two operands M and N are multiplied and then added to P to produce a new version of P stored in its corresponding multiplication unit / accumulation unit. The memory lookup unit 214a-c, 218a-c retrieves coefficient data stored in the memory 230. For example, the memory lookup unit can be a lookup table that retrieves a specific coefficient. The output of the memory lookup unit 214a-c, 218a-c is provided to the multiplication unit / accumulation unit 212a-c, 216a-c, which can be used as a multiplication operand in the multiplication unit portion of the multiplication unit / accumulation unit 212a-c, 216a-c. Using this circuit system arrangement, output data (e.g., B(u,v)) 220a-c can be generated from input data (e.g., X(i,j)) 210a-c.

[0035] In some examples, for example, coefficient data from memory 230 may be mixed with input data X(i, j) 210a to c to generate output data B(u, v) 220a to c. Based on the input data X(i, j) 210a to c, the relationship between the coefficient data and the output data B(u, v) 220a to c may be expressed as:

[0036]

[0037] where a' k,l 、a” m,n , respectively, are the coefficients of the first group of multiplication / accumulation units 212a to c and the second group of multiplication / accumulation units 216a to c, where f(·) represents the mapping relationship performed by the memory lookup unit 214a to c, 218a to c. As described above, the memory lookup unit 214a to c, 218a to c retrieves the coefficients to mix with the input data. Therefore, the output data can be provided by manipulating the input data by the multiplication / accumulation unit using a group of coefficients associated with the characteristics of the channel between the memory controller and the memory stored in the memory. The resulting mapped data can be manipulated by an additional multiplication / accumulation unit using a group of additional coefficients associated with the characteristics of the channel stored in the memory. A group of coefficients multiplied at each stage of the processing unit 205 can represent or provide an estimate of processing the input data in specially designed hardware (e.g., FPGA).

[0038] Furthermore, it can be shown that, as represented by Equation 1, system 200 can approximate any nonlinear mapping with arbitrarily small error in some instances and by coefficients a′ k,l 、a” m,n The mapping of system 200 is determined. For example, if such coefficient data is specified, system 200 can perform any mapping and processing between input data X(i,j) 210a to c and output data B(u,v) 220a to c. This relationship (as derived from the circuit system arrangement depicted in system 200) can be used to train the entities of computing system 200 to generate coefficient data. For example, using equation (1), the entities of computing system 200 can compare input data with output data to generate coefficient data.

[0039] In an example of system 200, processing unit 205 mixes coefficient data with input data X(i,j) 210a to c using memory lookup units 214a to c, 218a to c. In some examples, memory lookup units 214a to c, 218a to c may be referred to as lookup table units. Coefficient data may be associated with a mapping relationship between input data X(i,j) 210a to c and output data B(u,v) 220a to c. For example, coefficient data may represent a nonlinear mapping of input data X(i,j) 210a to c and output data B(u,v) 220a to c. In some examples, the nonlinear mapping of coefficient data may represent a Gaussian function, a piecewise linear function, a sigmoid function, a thin plate spline function, a multi-quadratic function, a cubic approximation, an inverse multi-quadratic function, or a combination thereof. In some examples, some or all of memory lookup units 214a to c, 218a to c may be deactivated. For example, one or more of the memory lookup units 214a-c, 218a-c may operate as gain units with unity gain. In this case, executable instructions (e.g., executable instructions 215) may facilitate selecting a unity gain processing mode for some or all of the memory lookup units 214a-c, 218a-c.

[0040] Each of the multiplication units / accumulation units 212a to c, 216a to c may include multiple multipliers, multiple accumulation units, and / or multiple adders. Any of the multiplication units / accumulation units 212a to c, 216a to c may be implemented using an arithmetic logic unit (ALU). In some examples, any of the multiplication units / accumulation units 212a to c, 216a to c may include one multiplier and one adder that each perform multiple multiplications and multiple additions, respectively. The input-output relationship of the multiplication / accumulation units 212, 216 may be represented as:

[0041]

[0042] where “I” represents the number of multiplications performed in that unit, and Ci represents the coefficients accessible from the memory (memory 230), and B in (i) represents a factor from the input data X(i,j) 210a to c or from the output of the multiplication unit / accumulation unit 212a to c, 216a to c. In the example, the output B of a group of multiplication units / accumulation units out Equal to coefficient data C i Multiply by the output B of another set of multiplication unit / accumulation unit in The sum of (i). in (i) It is also possible to make the output B of a group of multiplication units / accumulation units out Equal to coefficient data C i Multiply the sum of the input data.

[0043] Figure 3 is a schematic diagram illustrating a neural network 350 according to various embodiments. The neural network 350 may be used Figure 1 The host computing device 104 and / or the memory controller 102 and / or Figure 2 The computing system 200 includes a processing unit 205.

[0044] Neural network 350 includes three levels (e.g., layers). Figure 3 360, 362, 364, and 366. Additional, fewer, and / or different components may be used in other examples.

[0045] Typically, a neural network including multiple levels of nodes may be used, such as neural network 350. The nodes may use processing units (e.g., Figure 2 The neural network may be implemented as a processing unit 205 that performs one or more functions on inputs received from a previous stage and provides outputs of the functions to the next stage of the neural network. The processing unit may be implemented using, for example, one or more processors, controllers, and / or custom circuitry, such as an application specific integrated circuit (ASIC) and / or a field programmable gate array (FPGA). The processing unit may be implemented as a combiner and / or summer and / or any other structure for performing the functions assigned to the processing unit. In some examples, certain elements of the neural network described herein perform weighted summations, such as may be implemented using one or more multiply / accumulate units, which may be implemented using processor(s) and / or other circuitry.

[0046] exist Figure 3 In the example of , neural network 350 may have an input layer, which may be a first level of a neural network including nodes 368, 369, 372, and 374. Nodes 368, 369, 372, and 374 may implement a linear function that converts input signals (e.g., x1(n), x2(n), . . . x) into N (n)) is provided to another level (e.g., a 'hidden level' or 'hidden layer') of the neural network. Thus, in Figure 3 In an example of , N signals of input data may be provided to an input stage (e.g., an input layer) of the neural network during operation. In some examples, the input data may be data associated with a memory access operation (e.g., a read and / or write operation) performed via a channel between a memory controller and a memory. The N signals of input data may be output by a first stage of the neural network 350 to a next stage of the neural network 350. In some examples, the connection between the first and second stages of the neural network 350 may not be weighted—e.g., in some examples, a processing unit in the second stage may receive an unchanged signal from the first stage. Each of the input signals may be provided to a plurality of the processing units in the next stage. Although an input layer is shown, in some examples, an input layer may not be present.

[0047] Neural network 350 may have a next layer, which in some instances may be referred to as a 'hidden layer'. The next layer may include combiner 352, combiner 354, combiner 356, and combiner 358, although any number of elements may be used. Although the processing elements in the second stage of neural network 350 are referred to as combiners, typically the processing elements in the second stage may perform a non-linear activation function using the input signal received at the processing element. Any number of non-linear activation functions may be used. Examples of functions that may be used include Gaussian functions, such as:

[0048]

[0049] Examples of functions that can be used include polyquadratic functions, such as f(r)=(r 2 +σ 2 ) 1 / 2 Examples of functions that can be used include inverse multiquadratic functions, such as f(r) = (r 2 +σ 2 ) -1 / 2 Examples of functions that can be used include thin plate spline functions, such as f(r) = r 2 log(r). Examples of functions that can be used include piecewise linear functions, such as:

[0050]

[0051] Examples of functions that can be used include cubic approximation functions, such as:

[0052]

[0053] In these example functions, σ represents a real parameter (eg, a scaling parameter) and r is the distance between the input vector and the current vector. The distance can be measured using any of a variety of metrics, including the Euclidean norm.

[0054] Each element in the 'hidden layer' may receive as input a selected signal (e.g., some or all) of the input data. For example, each element in the 'hidden layer' may receive as input the output of a plurality of selected units (e.g., some or all of the units) in the input layer. For example, combiner 352 may receive as input the output of node 368, node 369, node 372, and node 374. Although in Figure 3 A single 'hidden layer' is shown by way of example in , but any number of 'hidden layers' may be present and may be connected in series. Although four units are shown in the 'hidden layer', any number may be used, and the number of units may be the same or different than the number of nodes in the input layer and / or the number of nodes in any other hidden layer. The nodes in the hidden layer may evaluate at least one nonlinear function using a combination of data received at the hidden layer nodes (e.g., elements). In this manner, the hidden layer may provide intermediate data at the output of one or more hidden layers.

[0055] Neural network 350 may have an output layer. Figure 3The output layer in the example of may include combiner 360, combiner 362, combiner 364 and combiner 366, but any number of elements may be used. Although the processing elements in the output stage of neural network 350 are referred to as combiners, the processing elements in the output layer may generally use the intermediate processing results from the last 'hidden layer' in the neural network to perform any combination or other operations. Each element in the output layer may receive the selected intermediate processing results (e.g., some or all) of the data provided by the last 'hidden layer' as input. For example, combiner 360 may receive the outputs of combiner 352, combiner 354, combiner 356 and combiner 358 as input. The connection between the hidden layer and the output layer may be weighted. For example, a set of weights W may be specified. In some examples, each connection between a hidden layer node and an output layer node may have a weight. In some examples, each hidden layer node may have a weight that may be applied to the data provided by that node to each connected output node. Other weight distributions may also be used. The weight may be multiplied with the output of the hidden layer before the output is provided to the output layer. In this manner, the output layer can perform a summation of weighted inputs. Thus, the output of the neural network 350 (e.g., the output of the output layer) can be referred to as a weighted sum. The output layer can accordingly combine intermediate data received from one or more hidden layers using weights to provide output data.

[0056] In some examples, neural network 350 may be used to provide L output signals representing processed data corresponding to N input signals. Figure 3 In the example, N input signals (x1(n), x2(n), . . . x N (n)) and provide L output signals (y1(n), y2(n), .. L The neural network 350 may be trained so that the weights W used and / or the functions provided by the elements of the hidden layer cause the neural network 350 to provide output signals representing processed data corresponding to the N input signals. The input signals may be data associated with memory access operations (e.g., read operations and / or write operations), and the weights and / or functions provided by the elements of the hidden layer may be selected according to corresponding channel characteristics of the channel through which the memory access operation is performed.

[0057] Examples of trainable neural networks. Training generally refers to the process of determining weights, functions, and / or other properties to be used by a neural network to create a desired transformation of input data to output data. In some examples, the neural networks described herein can be trained to determine one or more characteristics of a channel based on read-write data of the channel.

[0058] In various examples, the training described herein can be supervised or unsupervised. In some examples, training can be performed using known pairs of expected input and expected output data. For example, training can utilize known pairs of input data and output data to train a neural network to receive subsequent input data (e.g., read-write data of a channel) and process the subsequent input data into output data (e.g., one or more characteristics of a channel). Examples of training can include determining a sequence of inputs to be processed by a neural network (e.g., Figure 3 The weights used by the neural network 350 of the training program are stored in memory. In some examples, the same neural network hardware is used during training as will be used during operation. However, in some examples, different neural network hardware may be used during training, and the weights, functions, or other properties determined during training may be stored for use by other neural network hardware during operation.

[0059] The training examples can be described mathematically. For example, consider the input data given as follows at time (n): X(n) = [x1(n), x2(n), ... x N (n)] T The center vector of each element (e.g., combiner 352, combiner 354, combiner 356, and combiner 358) in the hidden layer(s) of neural network 350 may be represented as C i (for i=1,2,...,H, where H is the element number in the hidden layer).

[0060] The output of each element in the hidden layer can be given as:

[0061] h i (n) = f i (∥X(n)-C i ∥) for (i=1,2,...,H) (Equation 3)

[0062] The connection between the last hidden layer and the output layer can be weighted. Each element in the output layer can have a linear input-output relationship so that it can perform a summation (e.g., a weighted summation). Therefore, the output of the i-th element in the output layer at time n can be written as:

[0063]

[0064] For (i=1,2,...,L), where L is the element number of the output layer and W ij is the connection weight between the jth element in the hidden layer and the ith element in the output layer.

[0065] Typically, a neural network architecture (e.g. Figure 3The neural network 350 may include several elements and may have center vectors distributed in the input domain. In general, the choice of transfer function used by the elements in the hidden layer may not affect the mapping performance of the neural network, and therefore, in some examples, functions that can be easily implemented in hardware may be used. For example, thin plate spline functions and / or Gaussian functions may be used in various examples and may provide sufficient approximation capabilities. Other functions may also be used.

[0066] An instance of a neural network may be specified by attributes (e.g., parameters) accordingly. In some examples, two sets of parameters may be used to specify a neural network: connection weights and a center vector (e.g., threshold). The parameters may be determined from selected input data (e.g., encoded input data) by solving an optimization function. An example optimization function may be given as:

[0067]

[0068] Where M is the number of trained input vectors (e.g., trained encoded data inputs) and Y(n) is the output vector calculated from the sample input vector using Equations 3 and 4 above, and is the corresponding expected (eg, known) output vector. The output vector Y(n) can be written as: Y(n) = [y1(n), y2(n), ...y L (n)] T .

[0069] Various methods (e.g., gradient descent procedures) can be used to solve the optimization function. However, in some examples, another method can be used to determine the parameters of the neural network, which can generally include two steps: (1) determine the center vector C i (i=1,2,...,H) and (2) determine the weight.

[0070] In some instances, the center vector may be selected from a subset of available sample vectors. In such instances, the number of elements in the (several) hidden layers may be relatively large to cover the entire input domain. Therefore, in some instances, it may be desirable to apply the k-means clustering algorithm. Typically, the k-means clustering algorithm distributes the center vector according to the natural measure of the attractor (e.g., if the density of data points is high, the density of the center is also high). The k-means clustering algorithm can find a set of cluster centers and divide the training samples into subsets. Each cluster center may be associated with one of the H hidden layer elements in this network. The data can be divided in a way that the training points are assigned to the cluster with the nearest center. The cluster center corresponds to one of the minimum values ​​of the optimization function. The example optimization function used with the k-means clustering algorithm can be given as:

[0071]

[0072] Among them B jn is a cluster partition or membership function forming an H×M matrix. Each column may represent an available sample vector (eg, known input data) and each row may represent a cluster. Each column may contain a single '1' in the row corresponding to the cluster closest to that training point, and zeros elsewhere.

[0073] The center of each cluster can be initialized to a different randomly selected training point. Each training instance can then be assigned to the element closest to it. When all training points have been assigned, the average position of the training points for each cluster can be found and the cluster center moved to that point. The cluster can become the desired center of the hidden layer element.

[0074] In some examples, for some transfer functions (e.g., Gaussian functions), a scaling factor σ may be determined, and the scaling factor may be determined before determining the connection weights. The scaling factor may be selected to cover the training points to allow for a smooth fit of the desired network output. Typically, this refers to any point within the convex hull of the processing element center that may significantly activate more than one element. To achieve this goal, each hidden layer element may activate at least one other hidden layer element to a significant extent. A suitable method for determining the scaling parameter a may be based on the P nearest neighbor heuristic, which may be given as:

[0075]

[0076] Among them C j (for i=1,2,...,H) are the P nearest neighbors of Ci.

[0077] Connection weights may additionally or alternatively be determined during training. In the example of a neural network (e.g. Figure 3 In a neural network 350 with one hidden layer of weighted connections and an output element as a summing unit, once the center vector and scaling parameters have been determined, the optimization function of Equation 5 can be transformed into a linear least squares problem. The linear least squares problem can be written as

[0078]

[0079] where W = {Wij} is the L×H matrix of connection weights, F is the H×M matrix of the outputs of the hidden layer processing elements and its matrix elements are expressed using F in =f i ∥X(n)-C i ∥)(i=1,2,...,H;n=1,2,...,M)calculate, and is an L×M matrix of desired (eg, known) outputs. The connection weight matrix W can be found from Equation 7 and can be written as follows:

[0080]

[0081] where F + is the pseudo-inverse of F. In this way, the above can provide a batch method for determining the connection weights of a neural network. The batch method can be applied, for example, to situations where all input sample sets are available at the same time. In some examples, each new sample set may become available recursively, for example in a recursive least squares algorithm (RLS). In such cases, the connection weights may be determined as follows.

[0082] First, the connection weights can be initialized to any value (for example, random values ​​can be used). The output vector Y(n) can be calculated using Equation 4. The error term e for each output element in the output layer can be calculated as follows i (n):

[0083]

[0084] Next, the connection weights can be adjusted based on the error term, for example as follows:

[0085] W ij (n+1)=W ij (n)+γe i (n)f j (∥X(n)-C i ∥)(i=1,2,...,L;j=1,2,...,M)(Equation 9)where γ is the learning rate parameter, which can be fixed or time-varying.

[0086] The total error can be calculated based on the output from the output layer and the expected (known) data:

[0087]

[0088] The process can be iterated by again calculating the new output vector, the error term, and again adjusting the connection weights. The process can continue until a weight that reduces the error to equal to or less than a threshold error is identified.

[0089] Therefore, it is trainable Figure 3 The neural network 350 may be trained to determine parameters (e.g., weights) used by the neural network 350 to perform a particular mapping between input and output data. For example, training the neural network 350 may provide a set of parameters to use to determine characteristics of the channel data when receiving input data. Additionally or alternatively, training the neural network 350 may provide that set of parameters to use to select a logic error level when receiving input data. For example, the neural network 350 (and / or another neural network) may be trained multiple times using different known input / output data pairs. Multiple trainings may produce multiple sets of connection weights.

[0090] To recap, Figure 3The structure of the neural network 350 is provided by way of example only. Other multi-layer neural network structures may be used in other examples. In addition, the training procedures described herein are also provided by way of example. For example, other training techniques (e.g., learning algorithms) may be used to solve the local minimum problem and / or the vanishing gradient problem. The determined weights and / or vectors of each decoder may be obtained through an offline learning mode of the neural network, which may advantageously provide more resources and data. Such implementations that have accumulated intermediate processing results in corresponding processing elements (e.g., corresponding MAC units) may also include a memory lookup (MLU) unit that is configured to retrieve a plurality of coefficients and provide the plurality of coefficients as connection weights (e.g., determined weights) of that corresponding layer of the MAC unit to be mixed with the input data.

[0091] Figure 4 4 is a flow chart illustrating a process 400 for training a neural network to determine channel characteristics according to various embodiments. The process 400 may be performed, for example, using Figure 1 At least a portion of the system 100 (e.g., the host computing device 104 and / or the memory controller 102) and / or Figure 2 The neural network trained using process 400 may be Figure 3 Neural Network 350.

[0092] Process 400 includes, at 402, receiving a channel (eg, Figure 1 The channel data may include channel data of a channel between the memory controller 102 and one of the memory devices 112. The channel data includes characteristics of the channel and read-write data of the channel. The characteristics of the channel may include or be related to the logic level of data written to or read from the memory through the channel. The read-write data of the channel may include write data associated with a pilot signal written to the memory and read data associated with a pilot signal read from the memory.

[0093] Process 400 further includes, at 404, generating a training data set using the channel data. The training data set includes correlations between read-write data of a channel and channel characteristics. For example, the training data set may include correlations between read data of a particular channel and write data of the same channel. When the read data of a particular channel matches the write data of the particular channel, this may indicate that the channel is functioning properly. When the read data and the write data are inverted relative to each other, this may indicate that the channel inverts the data (e.g., when performing a read operation). In other examples, other correlations may be included in the training data set, such as correlations between logic levels of the read data compared to the write data.

[0094] Process 400 further includes, at 406, training a neural network using the training data set to determine channel characteristics of the channel based on the read-write data of the channel. The training neural network may be as described in reference to Figure 2 and 3 For example, when trained, a neural network may receive read-write data associated with a channel (e.g., data read from a memory via a channel and / or data written to a memory via a channel), and the neural network may determine channel characteristics based on the received read-write data.

[0095] In some implementations, process 400 further includes applying the trained neural network to determine channel characteristics of the channel based on the read-write data of the channel. In some implementations, process 400 includes modifying transceiver settings of a transceiver of a memory controller associated with the channel based on the determined channel characteristics.

[0096] Once trained, the neural network can be stored for use, for example, in Figure 1 The channel characteristic logic 108 is used.

[0097] In some implementations, process 400 includes testing the trained neural network. For example, a portion of the channel characteristics may be excluded from the training data set and used as test data to evaluate the accuracy of the trained neural network. The trained neural network may be applied to the test data to determine whether the trained neural network correctly determines the characteristics of the channel with an accuracy exceeding a threshold level (e.g., 70%, 80%, 90%, etc.). If the trained neural network does not exceed the threshold accuracy, the neural network may be retrained or discarded in favor of a more accurate model.

[0098] Retraining the neural network can include training the neural network at least a second time using the training data set, training the neural network with a different (e.g., expanded) training data set, applying different weights to the training data set, rebalancing the training data set, and so on.

[0099] Figure 5 is a flow chart illustrating a process 500 for modifying transceiver settings of a transceiver of a memory controller according to various embodiments. For example, the process 500 may use Figure 1 At least a portion of the system 100 (eg, the memory controller 102) and / or Figure 2 In some embodiments, process 500 may be performed at least in part using a neural network (e.g. Figure 3 Neural Network 350 and / or use Figure 4 The process 400 of training the neural network) is performed.

[0100] Process 500 includes, at 502, determining, at a memory controller, a characteristic of a communication channel between the memory controller and a memory. The characteristic may be related to a logic level of data written to or read from the memory via the communication channel. For example, the characteristic may indicate a relationship or correlation between logic levels in data written to the memory via the channel and data read from the memory via the same channel. As described herein, for example, when the logic level in the read data matches the logic level in the written data within an acceptable error margin, the characteristic indicates that the channel is functioning properly. Additionally or alternatively, the characteristic may indicate that the logic level in the read data is inverted compared to the logic level in the written data. In some embodiments, the characteristic is determined using a neural network.

[0101] In some embodiments, determining the characteristics of the communication channel includes storing a pilot signal at a memory controller and causing the pilot signal to be written to the memory via a write operation. Then, a read operation is performed to retrieve a read pilot signal corresponding to the pilot signal from the memory. In other words, a read operation is performed to retrieve the pilot signal written to the memory. Then, the read pilot signal is compared with the stored pilot signal to determine the characteristics of the channel. For example, when the read pilot signal matches the stored pilot signal, this may indicate that the channel is operating properly. When the read pilot signal has an inverted logic value compared to the stored pilot signal, this may indicate that the channel inverts the logic value in the read data.

[0102] Process 500 further includes, at 504, modifying settings of a transceiver of the memory controller based on the determined characteristic. For example, read and / or write settings may be modified based on the logic level of the data. In embodiments where the read pilot signal is compared to the stored pilot signal, when the read pilot signal does not match the stored pilot signal, the settings of the transceiver may be modified. For example, the logic level in the read pilot signal may be inverted compared to the logic level in the stored pilot signal, and the settings of the transceiver may be modified to correct for this inversion (e.g., by inverting a signal read via a communication channel). In some embodiments, modifying the settings of the transceiver may be optional, such as when it is determined that the channel is functioning properly.

[0103] Figure 6 is a flow chart illustrating a process 600 for modifying transceiver settings of a transceiver of a memory controller using a pilot signal according to various embodiments. For example, the process 600 may use Figure 1 At least a portion of the system 100 (eg, the memory controller 102) and / or Figure 2 In some embodiments, process 600 may be performed at least in part using a neural network (e.g. Figure 3 Neural Network 350 and / or use Figure 4 The process 400 of training the neural network) is performed.

[0104] Process 600 includes storing a pilot signal at a memory controller, at 602. The pilot signal includes known data stored at the memory controller as a reference to be compared with a pilot signal read from a memory via a channel.

[0105] Process 600 further includes, at 604, causing, by the memory controller, the pilot signal to be written to the memory.

[0106] Process 600 further includes performing a read operation to retrieve a read pilot signal from the memory at 606. The read pilot signal corresponds to the pilot signal written to the memory at 604.

[0107] Process 600 further includes comparing the read pilot signal retrieved at 606 with the stored pilot signal stored at 602 to determine a channel characteristic of the channel between the memory and the memory controller, at 608. For example, the comparison may indicate a match between the logic levels in the read pilot signal and the stored pilot signal, indicating that the channel is operating as expected. In another example, the comparison may indicate a mismatch between the read pilot signal and the stored pilot signal, such as an inversion of one or more logic values. Thus, the comparison may indicate that the channel inverts logic values.

[0108] Process 600 further includes, at 610, modifying a transceiver setting at a transceiver of the memory controller when the read pilot signal is different from the stored pilot signal. For example, as discussed above, the comparison performed at 608 may indicate that the read pilot signal includes an inverted logic level compared to the stored pilot signal, which may indicate that the channel inverts a signal written and / or read via the channel. Thus, the transceiver setting may be modified to correct the inversion.

[0109] Although processes 400, 500, and 600 include certain operations depicted as being performed in a certain order, it will be appreciated that without departing from the teachings of the present disclosure, more or fewer operations may be included in processes 400, 500, and 600. Additionally, the operations of processes 400, 500, and / or 600 may be performed in a different order, including performing one or more operations in parallel.

[0110] It should be understood that any of the examples, embodiments, or processes described herein may be combined with one or more other examples, embodiments, and / or processes, or separated and / or performed in a separate device or device portion according to the present systems, devices, and methods.

[0111] Although the present technology has been disclosed in the context of certain preferred embodiments and examples, it will be understood by those skilled in the art that the disclosed technology extends beyond the specifically disclosed embodiments to other alternative embodiments and / or uses of the technology and obvious modifications and equivalents thereof. In addition, based on the present disclosure, other modifications within the scope of the disclosed technology will be readily apparent to those skilled in the art. It is also contemplated that various combinations or sub-combinations may be made to the specific features and aspects of the embodiments and still fall within the scope of the disclosed technology. It should be understood that the various features and aspects of the disclosed embodiments may be combined or permuted with each other to form different modes of the disclosed technology. Therefore, the scope of at least some of the present technology disclosed herein is intended not to be limited by the specific disclosed embodiments described above.

Claims

1. A method comprising: determining, at a memory controller, a characteristic of a communication channel between the memory controller and a memory, wherein the characteristic is related to a logic level of data written to or read from the memory through the communication channel; and Transceiver settings of a transceiver of the memory controller are modified for the communication channel based on the determined characteristics.

2. The method of claim 1 , wherein determining the characteristic of the communication channel comprises: storing a pilot signal at the memory controller; causing the pilot signal to be written into the memory via a write operation; performing a read operation to retrieve a read pilot signal corresponding to the pilot signal from the memory; and The read pilot signal is compared to a stored pilot signal to determine the characteristic of the channel.

3. The method of claim 1, wherein the characteristic indicates that the logic level of the data read from the memory is inverted compared to the logic level of the data written to the memory, and wherein the logic level comprises a voltage level corresponding to a respective logic value. 4 . The method of claim 2 , further comprising modifying a transceiver setting of a transceiver of the memory controller for the channel in response to determining that the read pilot signal is different from the stored pilot signal.

5. The method of claim 1, further comprising determining the characteristics of the channel using a neural network.

6. A method comprising: receiving channel data of a channel between a memory controller and a memory, wherein the channel data includes characteristics of the channel and read-write data of the channel; generating a training data set using the channel data, wherein the training data set includes correlations between the read-write data of the channel and the characteristics of the channel; and A neural network is trained using the training data set to determine channel characteristics of the channel based on the read-write data of the channel.

7. The method of claim 6, wherein the read-write data of the channel includes write data associated with a pilot signal written to the memory and read data associated with the pilot signal read from the memory.

8. The method according to claim 6, further comprising: applying a trained neural network to determine the channel characteristics of the channel based on the read-write data of the channel; and Transceiver settings of a transceiver of the memory controller associated with the channel are modified based on the determined channel characteristics.

9. The method according to claim 6, further comprising: Generate a test data set using the channel data; testing the trained neural network using the test data set; and When the trained neural network does not exceed a threshold accuracy level, the trained neural network is retrained using a different training data set.

10. A device comprising: A memory controller comprising a transceiver, the memory controller being configured to: determining a characteristic of a communication channel between the memory controller and a memory, wherein the characteristic is related to a logic level of data written to or read from the memory through the communication channel; and Transceiver settings of the transceiver are modified for the communication channel based on the determined characteristics.

11. The apparatus of claim 10, further comprising the memory.

12. The apparatus of claim 10, wherein determining the characteristic of the communication channel comprises causing the memory controller to: storing a pilot signal at the memory controller; causing the pilot signal to be written into the memory via a write operation; performing a read operation to retrieve a read pilot signal corresponding to the pilot signal from the memory; and The read pilot signal is compared to a stored pilot signal to determine the characteristic of the channel.

13. The apparatus of claim 10, wherein the characteristic indicates that the logic level of the data read from the memory is inverted compared to the logic level of the data written to the memory.

14. The apparatus of claim 12, wherein the memory controller is configured to modify the transceiver settings of the transceiver in response to determining that the read pilot signal is different from the stored pilot signal.

15. The apparatus of claim 10, further comprising a neural network configured to determine the characteristic of the communication channel.

16. A non-transitory computer-readable medium carrying instructions that, when executed by at least one processor, cause the processor to perform operations comprising: receiving channel data of a channel between a memory controller and a memory, wherein the channel data includes characteristics of the channel and read-write data of the channel; generating a training data set using the channel data, wherein the training data set includes correlations between the read-write data of the channel and the characteristics of the channel; and A neural network is trained using the training data set to determine channel characteristics of the channel based on read-write data of the channel.

17. The non-transitory computer-readable medium of claim 16, wherein the read-write data of the channel includes write data associated with a pilot signal written to the memory and read data associated with the pilot signal read from the memory.

18. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise: applying a trained neural network to determine the channel characteristics of the channel based on the read-write data of the channel; and Transceiver settings of a transceiver of the memory controller associated with the channel are modified based on the determined channel characteristics.

19. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise: Generate a test data set using the channel data; testing the trained neural network using the test data set; and When the trained neural network does not exceed a threshold accuracy level, the trained neural network is retrained using a different training data set.