KR102491352B1 - Electronic device for efficiently estimating stack distance and operation method of the same - Google Patents

Abstract

: Inter-reference distance)를 획득하고, 상기 현재 액세스되는 오브젝트의 현재 고유 카운트 값 및 상기 현재 액세스되는 오브젝트의 상기 이전 고유 카운트 값에 기초하여, 고유 참조 카운트(

: unique reference count)를 획득하고, 상기 상호 참조 거리 및 상기 고유 참조 카운트에 기초하여 추정 스택 거리를 획득하는 프로세서를 포함할 수 있다.An electronic device for efficiently estimating a stack distance is disclosed. An electronic device for efficiently estimating a stack distance according to various embodiments of the present disclosure stores an index value for an accessed object, a unique index value for the accessed object, and at least one hash table recording the accessed object. Based on the storage unit and the hash table, the previous index value of the currently accessed object and the previous unique count value of the currently accessed object are obtained, and the current index value of the currently accessed object and the currently accessed object Based on the previous index value, a cross-reference distance to the currently accessed object (

: Inter-reference distance) is obtained, and based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: a unique reference count) and an estimated stack distance based on the cross-reference distance and the unique reference count.

Description

Electronic device for efficiently estimating stack distance and its operating method

The present invention relates to an electronic device for efficiently estimating a stack distance and an operating method thereof, and more particularly, to an electronic device and an operating method thereof for efficiently estimating a stack distance through estimation of a stack distance.

Temporal locality means that the first referenced memory location is highly likely to continue to be referenced in the near future. Recency is the most important factor in determining provisional regionality. In order to determine recency, a stack distance may be utilized.

In general, the complexity is high because the stack distance must be calculated for each input workload data. As a method for improving the complexity of the stack distance, Almasi et al. have proposed a new stack distance calculation method called a hole-based algorithm. This method has adopted an interval tree (balanced binary tree) to calculate the stack distance more efficiently.

As an example of a technology behind the present invention, Japanese Patent Registration No. 2000-330827 (November 30, 2000) discloses a method for increasing the efficiency of cache real rate by approximating and calculating the number of duplicate pages in a cache in a stochastic manner. Initiate.

Existing stack distance calculation methods such as the above-mentioned hole-based algorithm have improved the complexity of stack distance calculation to some extent, but, for example, it is possible to use stack distance calculation in a hot/cold data classification process having a greater complexity. No improvement was realized.

The present invention has been made to solve the above problems, and an object of the present invention is to provide a method capable of remarkably reducing the complexity of a stack distance calculation process by obtaining an estimated stack distance.

: Inter-reference distance)를 획득하고, 상기 현재 액세스되는 오브젝트의 현재 고유 카운트 값 및 상기 현재 액세스되는 오브젝트의 상기 이전 고유 카운트 값에 기초하여, 고유 참조 카운트(

: unique reference count)를 획득하고, 상기 상호 참조 거리 및 상기 고유 참조 카운트에 기초하여 추정 스택 거리를 획득하는 프로세서를 포함할 수 있다.An electronic device for efficiently estimating a stack distance according to various embodiments of the present disclosure stores an index value for an accessed object, a unique index value for the accessed object, and at least one hash table recording the accessed object. Based on the storage unit and the hash table, the previous index value of the currently accessed object and the previous unique count value of the currently accessed object are obtained, and the current index value of the currently accessed object and the currently accessed object Based on the previous index value, a cross-reference distance to the currently accessed object (

: Inter-reference distance) is obtained, and based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: a unique reference count) and an estimated stack distance based on the cross-reference distance and the unique reference count.

: Inter-reference distance)를 획득하는 과정, 상기 현재 액세스되는 오브젝트의 현재 고유 카운트 값 및 상기 현재 액세스되는 오브젝트의 상기 이전 고유 카운트 값에 기초하여, 고유 참조 카운트(

: unique reference count)를 획득하는 과정 및 상기 상호 참조 거리 및 상기 고유 참조 카운트에 기초하여 추정 스택 거리를 획득하는 과정을 포함할 수 있다.An operating method of an electronic device for efficiently estimating a stack distance according to various embodiments of the present disclosure includes an index value for an accessed object, a unique index value for the accessed object, and at least one hash recording the accessed object. Storing a table, obtaining a previous index value of the currently accessed object and a previous unique count value of the currently accessed object, based on the hash table, the current index value of the currently accessed object and the current access Based on the previous index value of the object to be accessed, the cross-reference distance to the currently accessed object (

: Inter-reference distance), based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: obtaining a unique reference count) and obtaining an estimated stack distance based on the cross-reference distance and the unique reference count.

According to various embodiments of the present disclosure, an object of the present invention is to provide a method capable of remarkably reducing the complexity of a stack distance calculation process by obtaining an estimate of the stack distance.

1 is a diagram of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention.
2 is a flowchart of a method for estimating a stack distance according to an embodiment of the present invention.
3 illustrates characteristics of workload data according to an embodiment of the present invention.
4 shows performance comparison data according to an embodiment of the present invention.
5 shows performance comparison data according to another embodiment of the present invention.
6 shows performance comparison data according to another embodiment of the present invention.
7 shows performance comparison data according to another embodiment of the present invention.
8 is a detailed configuration diagram of an electronic device according to an embodiment of the present invention.
9 is a flowchart of an operating method of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention.

Hereinafter, the operating principle of a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings. In addition, when it is determined that a detailed description of a related known function or configuration may obscure the gist of the present disclosure in describing an embodiment of the present invention, the detailed description will be omitted. In addition, terms used in the following are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definitions of the terms used should be interpreted based on the content throughout this specification and the corresponding functions.

1 is a diagram of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention.

Referring to FIG. 1 , an electronic device 100 that efficiently estimates a stack distance may include a storage unit 110 and a processor 120 .

Here, the electronic device 100 may be various data storage devices such as SSD (Solid State Drive) or various electronic devices such as servers, PCs, tablet PCs, and smart phones.

The stack distance may be defined as the number of unique objects among multiple objects appearing between two identical objects. For example, assuming an array of objects 'a b c c c d e e e a b', a unique object in 'b c c c d e e e' appearing among identical 'a' objects is 'b c d e'. Accordingly, the stack distance of the object enumeration may be defined as 4 (SD(a)=4).

Since the stack distance can be calculated only when the history of all appearing (or accessed) objects is stored, the memory usage is large, and especially in the case of the cache mechanism, the computational complexity is very high because the SD must be obtained for each object.

Accordingly, the present invention aims to improve the complexity of general stack distance calculation by providing a method for efficiently calculating an estimate of the stack distance.

The storage unit 110 may store a hash table. A hash table is a set of buckets that hold one or more records. A hash table is made up of an array of buckets where data is stored, and one bucket can hold one or more records. Hereinafter, information stored in the hash table may be interpreted as being stored in at least one bucket included in the hash table.

The storage unit 110 may store information about an object (or workload data) accessed in at least one bucket included in the hash table. Here, the object may be a Logical Block Address (LBA).

Specifically, the storage unit 110 may record an index value for an accessed object, a unique index value for the accessed object, and the accessed object.

Here, since the index value of the accessed object is updated with the current index value of the accessed object, it may be defined as a previous index value of the accessed object.

Also, since the unique index value of the accessed object is updated with the current unique count value of the accessed object, it may be defined as a previous index value of the accessed object.

For example, at least one bucket included in at least one hash table may record a previous index value, a previous unique index value, and a currently accessed object value. To this end, each of at least one bucket included in the hash table may include a previous index, a previous unique index, and a reference part. In this case, the previous index may record the previous index value, the previous unique index may record the unique index value, and the reference part may record the value of the accessed object.

The processor 120 may control the electronic device 100 as a whole. In particular, the processor 120 may estimate a stack distance for an input object.

For example, the processor 120 may obtain a previous index value of a currently accessed object and a previous unique count value of a currently accessed object based on the above-described hash table.

In this case, the processor 120 may check whether the currently accessed object is included in the bucket reference included in the hash table.

When a currently accessed object is included in the reference of a bucket included in the hash table, the processor 120 may obtain a previous index value of the currently accessed object from a previous index recorded in the bucket included in the hash table. Also, the processor 120 may obtain a previous unique count value of a currently accessed object from a previous unique index recorded in the bucket included in the hash table.

If the currently accessed object is not included in the bucket reference included in the hash table, that is, if the currently accessed object is not recorded in the hash table, the processor 120 sets the estimated stack distance of the currently accessed object to 0. or can return In this case, the processor 120 may increase the unique count value.

: Inter-reference distance)를 획득하는 과정 및 고유 참조 카운트(

: unique reference count)를 획득하는 과정을 수행할 수 있다.When the currently accessed object is recorded in the hash table, the processor 120 determines the cross-reference distance (

: Inter-reference distance) acquisition process and unique reference count (

: You can perform the process of acquiring a unique reference count).

First, the processor 120 may obtain a cross-reference distance for a currently accessed object. Here, the cross-reference distance may be defined as a counting value for all accessed objects included between the current access point of view of the currently accessed object and the previous access point of the currently accessed object.

: Inter-reference distance)를 획득할 수 있다. 여기서, 상기 현재 인덱스 값은 글로벌 인덱스일 수 있다. 프로세서(120) 오브젝트가 액세스 되는 때마다 글로벌 인덱스의 카운트 값을 1씩 증가시키고 이를 해시 테이블의 이전 인덱스에 저장할 수 있다.For example, the processor 120 may perform a cross-reference distance (with respect to a currently accessed object) based on a current index value of the currently accessed object and a previous index value of the currently accessed object.

: Inter-reference distance) can be obtained. Here, the current index value may be a global index. Each time the processor 120 object is accessed, the count value of the global index may be increased by 1 and stored in the previous index of the hash table.

The processor 120 may obtain a difference value between a current index value of a currently accessed object and a previous index value of the currently accessed object as a cross-reference distance.

Also, the processor 120 may obtain a unique reference count based on a current unique count value of the currently accessed object and a previous unique count value of the currently accessed object.

Here, the processor 120 may increase the current unique count value (global unique count) by 1 whenever a unique object (an object not previously present) is accessed. Processor 120 may store the global unique count of when a unique object is accessed in the previous unique index of the hash table.

The processor 120 may obtain a difference value between a current unique count value of a currently accessed object and a previous unique count value of a currently accessed object as a unique reference count.

Meanwhile, the processor 120 may obtain an estimated stack distance based on the obtained cross-reference distance and the obtained unique reference count.

Specifically, the processor 120 may obtain the estimated stack distance based on the following equation.

는 상기 추정 스택 거리,

는 상기 상호 참조 거리,

는 상기 고유 참조 카운트이다.here,

is the estimated stack distance,

is the cross-reference distance,

is the unique reference count.

According to Equation 1, the estimated stack distance can be calculated by a simple operation of averaging the cross-reference distance and the unique reference count, so complexity can be greatly reduced compared to the conventional stack distance calculation. Here, the cross-reference distance and the unique reference count can be quickly referenced in the hash table, so the calculation speed can be greatly improved.

The processor 120 may return the estimated stack distance according to the above-described process. In this case, the processor 120 may update a previous index value recorded in at least one table to a current index value. Also, the processor 120 may update a previous unique index value recorded in at least one table to a current unique count value.

2 is a flowchart of a method for estimating a stack distance according to an embodiment of the present invention.

Hereinafter, in the description of FIG. 2 , detailed descriptions of overlapping contents with those of FIG. 1 will be omitted for convenience of description.

Referring to FIG. 2 , when an object is accessed (S201), the processor 120 performs a process of estimating a stack distance for the corresponding object, which will be described later.

The processor 120 may determine whether the accessed object is recorded in the hash table (S202).

When the accessed object is not recorded in the hash table (S202-No), the processor 120 may return the estimated stack distance as 0 (S203). Also, the processor 120 may increase the current unique count value by 1 (S204). This is because the processor 120 may determine that the accessed object is a unique object not recorded in the hash table.

When the accessed object is recorded in the hash table (S202-Yes), the processor 120 may obtain a cross-reference distance to the accessed object (S205). For example, the processor 120 may obtain a difference value between a current index value of a currently accessed object and a previous index value of the currently accessed object as a cross-reference distance.

Also, when the accessed object is recorded in the hash table (S202-Yes), the processor 120 may obtain a unique reference count for the accessed object (S206). For example, the processor 120 may obtain a difference value between a current unique count value of a currently accessed object and a previous unique count value of a currently accessed object as a unique reference count.

The processor 120 may obtain an estimated stack distance based on the obtained cross-reference distance and unique reference count (S207). Here, the estimated stack distance may be defined as the average of the cross-reference distance and the unique reference count (see Equation 1 above).

The processor 120 may return the estimated stack distance according to the above-described process. In this case, the processor 120 may update the previous index value recorded in at least one table to the current index value (S208). Also, the processor 120 may update the previous unique index value recorded in at least one table to the current unique count value (S209).

The above estimated stack distance can be calculated by a simple operation of averaging the cross-reference distance and the unique reference count. Accordingly, the complexity of the stack distance estimation process according to an embodiment of the present invention can be greatly reduced compared to the conventional stack distance calculation. Here, the cross-reference distance and the unique reference count can be quickly referenced in the hash table, so the calculation speed can be greatly improved.

In the above, the method for estimating the stack distance according to an embodiment of the present invention has been described in detail. Hereinafter, with reference to FIGS. 3 to 7 , the performances of the conventional method for calculating a stack distance and the method for estimating a stack distance according to an embodiment of the present invention will be compared.

3 illustrates characteristics of workload data according to an embodiment of the present invention.

The table in FIG. 3 contains the characteristics of four traces (sets of workload data).

Referring to FIG. 3, as inputs to the stack distance estimation method according to an embodiment of the present invention, financial traces collected from traces related to online transactions occurring in financial companies and collected from the printer server of the Microsoft Cambridge Research Institute We used MSR project trace (MSRproj trace), MSR printer trace (MSprn trace) collected from the project server of Microsoft Cambridge Research Institute, and distilled trace (distilled trace) collected from NATIONAL TAIWAN UNIVERSITY.

For each trace described above, 9 million experiments were performed. That is, for each trace described above, the stack distance estimation method according to an embodiment of the present invention and the existing stack distance calculation method (eg, ONM method; dissertation at the University of Illinois, USA) were respectively applied to derive the result. The results are shown in FIGS. 4 to 7 below.

FIG. 4 is an experiment for financial traces, FIG. 5 is an experiment for MSR project traces, FIG. 6 is an experiment for MSR printer traces, and FIG. 7 is an experiment for distilled traces.

4 to 7, the stack distance estimation method according to an embodiment of the present invention has significantly lower complexity than the conventional stack distance calculation method, but the stack distance estimation result is the same as or close to the actual stack distance calculation value. . That is, it can be seen that the method for estimating the stack distance according to an embodiment of the present invention exhibits very good performance.

8 is a detailed configuration diagram of an electronic device according to an embodiment of the present invention.

Referring to FIG. 8 , an electronic device 800 includes a communication unit 810 , a storage unit 820 and a processor 830 .

The communication unit 810 performs communication. The communication unit 810 may communicate with an external electronic device through various communication methods such as BlueTooth (BT), Wireless Fidelity (WI-FI), ZigBee, Infrared (IR), and Near Field Communication (NFC).

The storage unit 820 may store an O/S (Operating System) software module for driving the electronic device 800 and data for configuring various UI screens provided in the display area.

For example, the storage unit 820 may store a hash table. The storage unit 820 may store information about an object (or workload data) accessed in at least one bucket included in the hash table. Here, the object may be a Logical Block Address (LBA). Specifically, the storage unit 820 may record an index value for an accessed object, a unique index value for the accessed object, and the accessed object.

The processor 830 generally controls the operation of the electronic device 800 using various programs stored in the storage unit 820 .

Specifically, the processor 830 includes a RAM 831, a ROM 832, a main CPU 833, a graphic processing unit 834, first to n interfaces 835-1 to 835-n, and a bus 836. include

Here, the RAM 831, the ROM 832, the main CPU 833, the graphics processing unit 834, and the first to n interfaces 835-1 to 835-n may be connected to each other through a bus 836. .

The first to n interfaces 835-1 to 835-n are connected to the various components described above. One of the interfaces may be a network interface connected to an external device through a network.

The ROM 832 stores command sets for system booting and the like. When a turn-on command is input and power is supplied, the main CPU 833 copies the O/S stored in the storage unit 820 to the RAM 831 according to the command stored in the ROM 832 and executes the O/S. boot up the system

When booting is completed, the main CPU 833 copies various application programs stored in the RAM 831 and executes the copied application programs in the RAM 831 to perform various operations.

The main CPU 833 accesses the storage unit 830 and performs booting using the O/S stored in the storage unit 830 . Also, the main CPU 833 performs various operations using various programs, contents, data, and the like stored in the storage unit 830 .

The graphic processing unit 834 creates a screen including various objects such as icons, images, and texts by using a calculation unit and a rendering unit.

For example, the processor 830 may estimate a stack distance for an input object. For example, the processor 830 may obtain a previous index value of a currently accessed object and a previous unique count value of a currently accessed object based on the above-described hash table. Here, if the currently accessed object is recorded in the hash table, the processor 830 may perform a process of obtaining a cross-reference distance and a process of obtaining a unique reference count based on the hash table. Processor 830 may obtain an estimated stack distance based on the cross-reference distance and the unique reference count.

는

가 과도하게 큰 경우나,

가 과도하게 작은 경우 과도하게 큰 값이 출력될 수 있다. 이하에서는, 스택 거리의 추정 값

가 과도하게 큰 값으로 출력되는 경우 이를 부드럽게 하는 방안을 추가적으로 설명한다.Meanwhile, according to Equation 1 described above, the estimated value of the stack distance according to an embodiment of the present invention

Is

is excessively large, or

If is excessively small, an excessively large value may be output. In the following, the estimated value of the stack distance

If is output as an excessively large value, a method for smoothing it will be additionally described.

가 과도하게 크게 계산될 수 있다. 또는, 현재 액세스되는 오브젝트의 이전 액세스 전에 고유한 오브젝트들이 반복적으로 액세스된 경우,

가 과도하게 작게 계산될 수 있다. 다만, 이러한 상황은 매우 드물 것이다.For example, if an object that has been accessed a long time ago is accessed,

may be calculated excessively large. Or, if unique objects were repeatedly accessed before the previous access of the currently accessed object,

may be calculated excessively small. However, this situation will be very rare.

가 과도하게 큰 값으로 출력되는 경우를 스무스(smooth)하게 만드는 방법의 일 예로, 프로세서(120)는 획득된

가 평균

보다 기정의된 배수 이상(예를 들면, 5배)으로 과도하게 큰 경우,

를 기정의된 비율로 감할 수 있다. 여기서, 기정의된 비율은 1/2일 수 있다.An estimate of the stack distance

As an example of a method for smoothing the case where is output as an excessively large value, the processor 120

is average

overly large by more predefined multiples (e.g., 5 times);

can be subtracted at a predefined rate. Here, the predefined ratio may be 1/2.

가 기정의된 횟수(예를 들면, 5회)로 연속적으로 출력되는 경우, 프로세서(120)는 과도한 크기의

에 대한 스무딩 없이, 상기

를 그대로 리턴할 수 있다.However, the above-mentioned excessive size

If is continuously output a predefined number of times (eg, 5 times), the processor 120 has an excessive size

without smoothing on

can be returned as is.

9 is a flowchart of an operating method of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention.

Referring to FIG. 9 , an operating method of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention records an index value for an accessed object, a unique index value for the accessed object, and an accessed object. The process of storing at least one hash table (S910), the process of obtaining the previous index value of the currently accessed object and the previous unique count value of the currently accessed object based on the hash table (S920), of the currently accessed object Obtaining a cross-reference distance for the currently accessed object based on the current index value and the previous index value of the currently accessed object (S930), the current unique count value of the currently accessed object and the previous uniqueness of the currently accessed object A process of obtaining a unique reference count based on the count value (S940) and a process of obtaining an estimated stack distance based on the cross-reference distance and the unique reference count (S950) may be included.

The above-described operating method of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention includes obtaining a cross-reference distance based on a hash table when a currently accessed object is recorded in a hash table, and a unique reference It may include a process of obtaining a count.

In this case, the operating method of the electronic device for efficiently estimating the stack distance according to an embodiment of the present invention described above may include a process of increasing a unique count value when a currently accessed object is not recorded in the hash table. there is.

The above-described operating method of an electronic device for efficiently estimating a stack distance according to an embodiment of the present invention may further include setting the estimated stack distance to 0 when a currently accessed object is not recorded in the hash table. there is.

The aforementioned cross-reference distance may be a difference between a current index value of a currently accessed object and a previous index value of a currently accessed object.

The aforementioned unique reference count may be a difference value between a current unique count value of a currently accessed object and a previous unique count value of a currently accessed object.

The above-described estimated stack distance may be obtained based on the following equation.

는 상기 추정 스택 거리,

는 상기 상호 참조 거리,

는 상기 고유 참조 카운트다.here,

is the estimated stack distance,

is the cross-reference distance,

is the unique reference count.

In one embodiment of the present invention described above, the previous index value included in at least one hash table is updated to a current index value, and the previous unique index value included in at least one hash table is updated to a current unique count value. there is.

In one embodiment of the present invention described above, an object to be accessed may be an LBA.

In addition, in one embodiment of the present invention described above, at least one bucket included in at least one hash table may record a previous index value, a previous unique index value, and a currently accessed object value.

Meanwhile, the method of operating an electronic device for efficiently estimating the stack distance according to various embodiments of the present disclosure described above is implemented as computer-executable program code and stored in various non-transitory computer readable media. State can be provided to each server or device to be executed by a processor.

For example, a process of storing at least one hash table in which an index value for an accessed object, a unique index value for the accessed object, and the accessed object are recorded, and a previous index value of the currently accessed object based on the hash table. and obtaining a previous unique count value of the currently accessed object, obtaining a cross-reference distance to the currently accessed object based on the current index value of the currently accessed object and the previous index value of the currently accessed object; Obtaining a unique reference count based on a current unique count value of the currently accessed object and a previous unique count value of the currently accessed object, and obtaining an estimated stack distance based on the cross-reference distance and unique reference count. A non-transitory computer readable medium in which a program to be stored may be provided.

For example, in a non-transitory computer readable medium storing computer instructions that, when executed by a processor of an electronic device, cause an operation of the electronic device to be performed, the operation includes an index value for an object being accessed, and an index value for an object being accessed. Storing at least one hash table that records a unique index value for and accessed objects, obtaining a previous index value of a currently accessed object and a previous unique count value of a currently accessed object based on the hash table; The process of obtaining a cross-reference distance to the currently accessed object based on the current index value of the currently accessed object and the previous index value of the currently accessed object, the current unique count value of the currently accessed object and the currently accessed object It may include obtaining a unique reference count based on a previous unique count value and obtaining an estimated stack distance based on the cross-reference distance and unique reference count.

A non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, the various applications or programs described above may be stored and provided in non-transitory readable media such as CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

While embodiments of the present invention have been shown and described above, those skilled in the art may make various changes in form and detail without departing from the spirit and scope of the present embodiments as defined by the appended claims and equivalents thereto. you will understand that you can

Electronics: 100, 800
Reservoir: 110, 820
Processor: 120, 830
Department of Communications: 810

Claims (21)

In an electronic device for efficiently estimating a stack distance,
a storage unit for storing at least one hash table recording an index value of an accessed object, a unique index value of the accessed object, and the accessed object; and
Based on the hash table, obtain a previous index value of the currently accessed object and a previous unique count value of the currently accessed object;
Based on the current index value of the currently accessed object and the previous index value of the currently accessed object, a cross-reference distance to the currently accessed object (

: Obtain Inter-reference distance),
Based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: acquire a unique reference count),
An electronic device for efficiently estimating a stack distance, comprising: a processor obtaining an estimated stack distance based on the cross-reference distance and the unique reference count.
According to claim 1,
the processor,
When the currently accessed object is recorded in the hash table, an electronic device for efficiently estimating a stack distance, performing a process of obtaining the cross-reference distance and a process of obtaining the unique reference count based on the hash table .
According to claim 1 or 2,
the processor,
An electronic device for efficiently estimating a stack distance by increasing the unique count value when the currently accessed object is not recorded in the hash table.
According to claim 3,
the processor,
The electronic device for efficiently estimating a stack distance, wherein the estimated stack distance is set to 0 when the currently accessed object is not recorded in the hash table.
According to claim 1,
The cross-reference distance,
The electronic device for efficiently estimating a stack distance, which is a difference between the current index value of the currently accessed object and the previous index value of the currently accessed object.
According to claim 1,
The unique reference count is
The electronic device for efficiently estimating a stack distance, which is a difference between the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object.
According to claim 1,
The electronic device for efficiently estimating the stack distance, wherein the estimated stack distance is obtained based on the following equation.

here,

is the estimated stack distance,

is the cross-reference distance,

is the unique reference count.
According to claim 1,
The previous index value included in the at least one hash table is updated to the current index value,
The electronic device for efficiently estimating a stack distance, wherein a previous unique index value included in the at least one hash table is updated with the current unique count value.
According to claim 1,
The electronic device for efficiently estimating a stack distance, wherein the accessed object is a Logical Block Address (LBA).
According to claim 1,
At least one bucket included in the at least one hash table,
Electronic device for efficiently estimating the stack distance, recording the previous index value, the previous unique index value and the currently accessed object value.
In the operating method of an electronic device for efficiently estimating a stack distance,
storing an index value for an accessed object, a unique index value for the accessed object, and at least one hash table recording the accessed object;
obtaining a previous index value of the currently accessed object and a previous unique count value of the currently accessed object, based on the hash table;
Based on the current index value of the currently accessed object and the previous index value of the currently accessed object, a cross-reference distance to the currently accessed object (

: Obtaining Inter-reference distance);
Based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: process of acquiring a unique reference count); and
A method of operating an electronic device for efficiently estimating a stack distance, including obtaining an estimated stack distance based on the cross-reference distance and the unique reference count.
According to claim 11,
When the currently accessed object is recorded in the hash table, obtaining the cross-reference distance based on the hash table and obtaining the unique reference count; How the device works.
According to claim 11 or 12,
and increasing the unique count value when the currently accessed object is not recorded in the hash table.
According to claim 13,
The method of operating an electronic device for efficiently estimating a stack distance, further comprising setting the estimated stack distance to 0 when the currently accessed object is not recorded in the hash table.
According to claim 11,
The cross-reference distance,
An operating method of an electronic device for efficiently estimating a stack distance, which is a difference between the current index value of the currently accessed object and the previous index value of the currently accessed object.
According to claim 11,
The unique reference count is
A method of operating an electronic device for efficiently estimating a stack distance, which is a difference between the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object.
According to claim 11,
The method of operating an electronic device for efficiently estimating the stack distance, wherein the estimated stack distance is obtained based on the following equation.

here,

is the estimated stack distance,

is the cross-reference distance,

is the unique reference count.
According to claim 11,
The previous index value included in the at least one hash table is updated to the current index value,
A method of operating an electronic device for efficiently estimating a stack distance, wherein a previous unique index value included in the at least one hash table is updated with the current unique count value.
According to claim 11,
The method of operating an electronic device for efficiently estimating a stack distance, wherein the accessed object is a logical block address (LBA).
According to claim 11,
At least one bucket included in the at least one hash table,
A method of operating an electronic device for efficiently estimating a stack distance by recording a previous index value, a previous unique index value, and a currently accessed object value.
A non-transitory computer-readable medium storing computer instructions that, when executed by a processor of an electronic device, cause an operation of the electronic device to be performed, the operation comprising:
storing an index value for an accessed object, a unique index value for the accessed object, and at least one hash table recording the accessed object;
obtaining a previous index value of the currently accessed object and a previous unique count value of the currently accessed object, based on the hash table;
Based on the current index value of the currently accessed object and the previous index value of the currently accessed object, a cross-reference distance to the currently accessed object (

: Obtaining Inter-reference distance);
Based on the current unique count value of the currently accessed object and the previous unique count value of the currently accessed object, a unique reference count (

: process of acquiring a unique reference count); and
and obtaining an estimated stack distance based on the cross-reference distance and the unique reference count.

Images