WO2015154298A1

WO2015154298A1 - Data processing method and apparatus

Info

Publication number: WO2015154298A1
Application number: PCT/CN2014/075141
Authority: WO
Inventors: 刘海燕; 徐君
Original assignee: 华为技术有限公司
Priority date: 2014-04-11
Filing date: 2014-04-11
Publication date: 2015-10-15
Also published as: CN105556489B; CN105556489A

Abstract

Disclosed are a data processing method and apparatus. The data processing method comprises: when a target data unit needs to be stored, obtaining the number of first data and the number of second data in the target data unit, with the type of the first data being a first type and the type of the second data being a second type; and if the number of the first data is larger than the number of the second data, obtaining a first target location of the second data in the target data unit, and writing data of the first type into the first target location in a target storage unit prefilled as data of the second type. The use of the present invention enables an efficient storage of the target data unit into the target storage unit, and there is small power consumption.

Description

Data processing method and device

Technical field

The present invention relates to the field of electronic technologies, and in particular, to a data processing method and apparatus. Background technique

With the development of various applications, it is often necessary to store the data used in various applications, usually storing the data of various applications in the memory of the computer. Nowadays, various computer memories use new nonvolatiles. Non-volatile memory (NVM), such as Phase-change Random Access Memory (PCM), which includes multiple storage units. When it is necessary to store various application data, the application data is divided. As a data unit, the corresponding data unit is then stored in the memory unit of the PCM memory. The data unit generally includes one or two types of data, for example: data including a data value of 1 and/or data having a data value of 0.

The existing method of storing the data unit in the storage unit of the PCM memory is to pre-fill all the digits of the storage unit into data with a data value of 1, and when the data unit needs to be stored in the storage unit, the data unit is searched. The data in which the data value is 0 is at the target position in the data unit, and then the data having the digital value of 0 is written into the storage location corresponding to the target location in the storage unit, so that the data unit is stored in the storage unit. In this method, when the number of data having a digital value of 0 included in the data unit is less than the number of data having a digital value of 1, the power consumption and delay of the stored data are reduced, but when included in the data unit When the number of data with a digital value of 0 is greater than the number of data with a digital value of 1, the method needs to find the target position of the data with a digital value of 0 in the data unit, which will increase the power consumption of the stored data. Delay, so this method has a lower efficiency and a higher power consumption when the number of data with a digital value of 0 in the data unit is greater than the number of data with a digital value of 1. Summary of the invention

Embodiments of the present invention provide a data processing method and apparatus, which can efficiently store a target data unit into a target storage unit, and consume less power.

A first aspect of the present invention provides a data processing method, which may include:

When the target data unit needs to be stored, the number of the first data in the target data unit and the number of the second data are obtained, the type of the first data is a first type, and the type of the second data is a Two types; If the number of the first data is greater than the number of the second data, acquiring a first target location of the second data in the target data unit, and pre-populating the second type The first type of data is written in the first target location in a target storage unit of data.

Based on the first aspect, in a first possible implementation, the method further includes: if the number of the first data is less than or equal to the number of the second data, acquiring the first data a second target location in the target data unit, and writing the first type of data into the second target location in a target storage unit pre-filled with the second type of data.

According to the first possible implementation manner of the first aspect, in a second possible implementation, if the number of the first data is greater than the number of the second data, acquiring the second data After the first target location in the target data unit and the first target location in the target storage location pre-filled with the second type of data is written in the first type of data, :

Setting a flag bit of the target storage unit as a first identifier, the first identifier is used to identify that data stored in the target storage unit is not original data in the target data unit.

Based on the second possible implementation manner of the first aspect, in a third possible implementation, if the number of the first data is less than or equal to the number of the second data, a data is in a second target location in the target data unit, and after the first type of data is written in the second target location in a target storage unit pre-filled with the second type of data, Also includes:

Setting a flag bit of the target storage unit as a second identifier, the second identifier is used to identify that the data stored in the target storage unit is original data in the target data unit.

Based on the third possible implementation manner of the first aspect, in a fourth possible implementation manner, the method further includes:

When the target data unit stored in the target storage unit needs to be acquired, reading a flag bit of the target storage unit;

If the flag bit is the first identifier, converting the first type of data in the target storage unit into the second type of data, and the second type of the target storage unit Converting data into the first type of data, and determining the converted data as the target data unit stored in the target storage unit;

Reading the number stored in the target storage unit if the flag bit is the second identifier Yuan.

A second aspect of the present invention provides a data processing apparatus, which may include:

An acquiring module, configured to acquire, when the target data unit needs to be stored, the number of the first data and the number of the second data in the target data unit, where the type of the first data is the first type, the second The type of data is the second type;

a first writing module, configured to acquire, when the number of the first data is greater than the number of the second data, a first target location of the second data in the target data unit, and Writing the first type of data into the first target location in a target storage unit populated with the second type of data.

Based on the second aspect, in a first possible implementation, the device further includes: a second writing module, configured to: if the number of the first data is less than or equal to the number of the second data, And acquiring a second target location of the first data in the target data unit, and writing the first target location in the target storage unit pre-filled with the second type of data into the first target location Type of data.

Based on the first possible implementation manner of the second aspect, in a second possible implementation manner, the apparatus further includes:

a first setting module, configured to set a flag bit of the target storage unit as a first identifier, where the first identifier is used to identify that data stored in the target storage unit is not original data in the target data unit .

Based on the second possible implementation of the second aspect, in a third possible implementation, the second setting module is configured to set a flag of the target storage unit to a second identifier, where the second identifier is The data used to identify the target storage unit is the original data in the target data unit.

Based on the third possible implementation manner of the second aspect, in a fourth possible implementation manner, the apparatus further includes:

a reading module, configured to read a flag bit of the target storage unit when the target data unit stored in the target storage unit needs to be acquired;

a conversion determining module, configured to: if the flag bit is the first identifier, the target storage list Transforming the first type of data into the second type of data, converting the second type of data in the target storage unit into the first type of data, and converting the processed Determining data as the target data unit stored in the target storage unit;

And a read determining module, configured to: if the flag bit is the second identifier, read the target to store the target data unit.

A third aspect of the present invention provides a data processing apparatus, which may include a processor, where: the processor is configured to acquire, when the target data unit needs to be stored, the number of the first data in the target data unit and the second The number of the data, the type of the first data is a first type, and the type of the second data is a second type;

The processor is further configured to: if the number of the first data is greater than the number of the second data, acquire a first target location of the second data in the target data unit, and pre-populate Writing the first type of data into the first target location in a target storage unit of the second type of data.

According to the third aspect, in a first possible implementation, the processor is further configured to acquire the first data if the number of the first data is less than or equal to the number of the second data. And writing, in the second target location in the target data unit, the first type of data in the second target location in a target storage unit pre-filled with the second type of data.

Based on the first possible implementation manner of the third aspect, in a second possible implementation, the processor is further configured to set a flag of the target storage unit as a first identifier, where the first identifier is used The data stored in the target storage unit is not the original data in the target data unit.

According to a second possible implementation manner of the third aspect, in a third possible implementation, the processor is further configured to set a flag of the target storage unit to a second identifier, where the second identifier is The data used to identify the target storage unit is the original data in the target data unit.

According to a third possible implementation manner of the third aspect, in a fourth possible implementation, the processor is further configured to: when the target data unit stored in the target storage unit needs to be acquired, read Taking the flag of the target storage unit;

The processor is further configured to: if the flag bit is the first identifier, then the target storage unit Converting the first type of data into the second type of data, converting the second type of data in the target storage unit into the first type of data, and converting the processed Data is determined to be the target data unit stored in the target storage unit;

The processor is further configured to read the target storage target data unit if the flag bit is the second identifier.

In the embodiment of the present invention, when the target data unit needs to be stored, the number of the first data of the first type and the second type of the second type of the type in the target data unit are obtained, when the first When the number of data is greater than the number of second data, a target position of the second data in the target data unit is obtained, and a target in the target storage unit of the second type of data is pre-filled The location is written to the first type of data, in place of the second data in the target data unit. In the embodiment of the present invention, the first type of data in the target storage unit is used to replace the second type of data in the target data unit, in the target data. When there is more data of the first type in the unit, and less data of the second type, only less data of the first type needs to be written to replace the second type of data in the target data unit, so the efficiency is relatively high. And because the write data is less, the power consumption is also lower. DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some of the present invention. For the embodiments, those skilled in the art can obtain other drawings according to the drawings without any creative work.

1 is a schematic flow chart of a data processing method provided by the present invention;

2 is a schematic flow chart of another data processing method provided by the present invention;

3 is a storage structure diagram provided by the present invention;

4 is a schematic structural diagram of a data processing apparatus according to the present invention;

FIG. 5 is a schematic structural diagram of another data processing apparatus according to the present invention; FIG.

FIG. 6 is a schematic structural diagram of still another data processing apparatus according to the present invention; The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

In the embodiment of the present invention, the first type of data may be data with a data value of 0, and the second type of data may be data with a data value of 1. The first type of data may be data with a data value of 1. The second type of data may be data having a data value of zero. The data processing method of the embodiment of the present invention can be applied to an application scenario for storing data in a computer memory. With the development of various applications, computer memory is generally stored by a non-volatile memory NVM, such as PCM memory, and its expansion. Better performance, greater density, greater capacity, and lower energy consumption. The data stored in the memory can be binary data. When writing '0' to the PCM, add a higher voltage for a shorter duration. When writing T to the PCM, add a lower voltage for the duration. Longer time. The data processing method provided by the embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart diagram of a data processing method according to an embodiment of the present invention; the method may include the following steps S100-S101.

S100, when the target data unit needs to be stored, acquiring the number of the first data and the number of the second data in the target data unit, the type of the first data is a first type, and the type of the second data For the second type;

In an embodiment, when the target data unit needs to be stored in the target storage unit, firstly, the number of the first data and the second data in the target data unit needs to be acquired, and the data is stored in the computer system. Generally, it is stored in the form of data units, and one data unit can include 8 bits of data. Therefore, there are multiple data in the target data unit, and the types of data included in the target data unit may also be various. For example, when the data is stored in binary form, the types included in the target data unit are Two types, the first type and the second type, the first type of data may be data having a data value of 0, and the second type of data may be data having a data value of 1, then the first data in the target data unit is All data with a data value of 0, the second data is data with a total data value of 1. It should be noted that the first type of data may also be data with a data value of 1, second. The type of data may be data with a data value of 0, and the first data in the target data unit is data with all data values of 1, and the second data is data with all data values of 0.

S101. If the number of the first data is greater than the number of the second data, obtain a first target location of the second data in the target data unit, and pre-populate the second data. The first type of data is written in the first target location in the target storage unit of the type of data.

In one embodiment, when the data is stored in the computer memory, in order to reduce the amount of data written to the data, and reduce the delay, the computer memory is generally pre-filled, that is, each storage unit is pre-filled with one type. Type data, when storing data to a storage unit, directly modify the number of bits of the data value directly in the storage unit. Because the number of bits that need to be modified is too large, and a large amount of data needs to be written, the power consumption is long and the delay is long. Therefore, in the embodiment of the present invention, the pre-filled data type is the second type of data. When the number of the first data of the first type in the target data unit is greater than the number of the second data of the second type, the first target position of the second type of data in the target data unit is directly obtained, and Writing the first type of data into the first target location in the target storage unit, replacing the second type of data in the target data unit with the first type of data, and replacing the first type of the target data unit with the second type of data Data is equivalent to flipping the data in the target data unit.

Here, the binary data is stored in the target storage unit as an example. Since power consumption and delay are comprehensively considered, data of a data value of 1 is generally pre-filled in the target storage unit, that is, the second type of data is a data value. For data of 1, the first type of data is data with a data value of zero. When the number of data whose data value is 0 in the target data unit is larger than the number of data whose data value is 1, for example, the target data unit is 10000100, the data value is 0, the data number is 6, and the data value is 1. If the number of data with the data value of 0 is greater than the number of data with the data value of 1, the first target position of the data with the data value of 1 in the target data unit is obtained. In this embodiment, the first target When the position is the first bit and the sixth bit, the data having the data value of 0 is written in the first bit and the sixth bit of the target memory unit, and the data having the data value of 1 in the target data unit is replaced in the target storage unit. The stored data is 01111011, and the stored data is not the original data of the target data unit, but the inversed data of the original data.

In the embodiment of the present invention, when the target data unit needs to be stored, the number of the first data of the first type and the second type of the second type of the type in the target data unit are obtained. When the number of the first data is greater than the number of the second data, the target position of the second data in the target data unit is obtained in a relatively small number, and the target storage unit of the second type of data is pre-filled In the embodiment of the present invention, the first type of data is used to replace the second type of data in the target data unit. In the embodiment of the present invention, the second type of data in the target data unit is replaced by the first type of data in the target storage unit. There is more data of the first type in the target data unit. When the data of the second type is less, only less first type of data needs to be written to replace the second type of data in the target data unit, so the efficiency is It is relatively high, and since the write data is small, the power consumption is also low. FIG. 2 is a schematic flowchart diagram of another data processing method according to an embodiment of the present invention; the method may include the following steps S200-S207.

5200, when the target data unit needs to be stored, acquiring the number of the first data and the number of the second data in the target data unit, the type of the first data is a first type, and the type of the second data For the second type;

Step S200 of the embodiment of the present invention can refer to step S100 shown in FIG. 1 , and no further description is provided herein.

5201, if the number of the first data is greater than the number of the second data, acquiring a first target location of the second data in the target data unit, and pre-populating the second data The first type of data is written in the first target location in the target storage unit of the type of data.

Step S201 of the embodiment of the present invention can refer to step S101 shown in FIG. 1 , and no further description is provided herein.

5202. Set a flag of the target storage unit to a first identifier, where the first identifier is used to identify that data stored in the target storage unit is not original data in the target data unit.

As an optional implementation manner, after the target data unit is stored, in order to facilitate the reading of the data, the flag of the target storage unit needs to be set, when the data stored in the target storage unit is not the original of the target data unit. The data, that is, when stored, is stored according to the method of step S201, and the flag bit of the target storage unit is set as the first identifier, and the first identifier is the data non-target data unit stored in the identifier target storage unit. The original data in FIG. 3 is a scene graph for storing binary data in the PCM memory. In the first target storage unit, the flag bit is set with the first identifier, and the first identifier is replaced by the data with the data value of 0. . Then the number stored in the target storage unit According to 01111011, it is not the original data of the target data unit. When it is necessary to read the target data unit stored in the target storage unit, the data in the target storage unit needs to be bit-inverted.

5203. If the number of the first data is less than or equal to the number of the second data, acquire a second target location of the first data in the target data unit, and pre-populate the The first type of data is written in the second target location in a target storage unit of the second type of data.

As an optional implementation manner, the type of the first data is a first type, and the type of the second data is a second type. The type of the data pre-filled in the target storage unit is the second type. Since the number of the first data in the target data unit is less than or equal to the number of the second data, in order to write a smaller amount of data in the target storage unit, Then, the first type of data can be directly written in the corresponding position in the target storage unit, that is, the data stored in the target storage unit is the original data in the target data unit.

Here, the binary data is stored in the target storage unit as an example. Since power consumption and delay are comprehensively considered, data of a data value of 1 is generally pre-filled in the target storage unit, that is, the second type of data is a data value. For data of 1, the first type of data is data with a data value of zero. When the number of data whose data value is 0 in the target data unit is less than or equal to the number of data whose data value is 1, for example, the target data unit is 11111010, the data value is 0, the data number is 2, and the data value is 1. The number of data is 6, the number of data whose data value is 0 is smaller than the number of data whose data value is 1, and the first target position of the data whose data value is 0 in the target data unit is obtained. In this embodiment, When the target position is the sixth bit and the eighth bit, the data with the data value of 0 is written in the sixth and eighth bits of the target storage unit, and the data of the data value of 0 in the target data unit is replaced, and the target storage is performed. The data stored in the unit is 11111010, and the stored data is the original data of the target data unit, specifically, the second storage unit in the PCM memory as described in FIG.

S204: Set a flag of the target storage unit to a second identifier, where the second identifier is used to identify that the data stored in the target storage unit is original data in the target data unit.

As an optional implementation manner, after the target data unit is stored, in order to facilitate the reading of the data, the flag of the target storage unit needs to be set, when the data stored in the target storage unit is the original of the target data unit. The data, that is, stored, according to the method of step S203, sets the flag of the target storage unit to the second identifier, and the second identifier is the scene graph for storing the binary data in the target memory. In the two target storage units, the flag is set. The second identifier, the second identifier is replaced by data having a data value of 1. Then, the data 11111010 stored in the target storage unit is the original data of the target data unit, and when the target data unit stored in the target storage unit needs to be read, the data in the target storage unit is directly read.

S205, when the target data unit stored in the target storage unit needs to be acquired, reading a flag bit of the target storage unit;

As an optional implementation manner, after the target data unit is stored to the target data unit, when the target data unit is to be called, the target data unit needs to be acquired from the target storage unit. In the embodiment of the present invention, the method for acquiring the target data unit is based on the rule of storing the target data unit in the target storage unit, so when the target data unit stored in the target storage unit needs to be acquired, the target storage unit is first read. The flag bit is used to identify whether the data stored in the target storage unit is the original data in the target data unit.

S206, if the flag bit is the first identifier, converting the first type of data in the target storage unit into the second type of data, and the second in the target storage unit Converting data of the type into the data of the first type, and determining the data after the conversion processing as the target data unit stored in the target storage unit;

As an optional implementation manner, if the flag of the target storage unit is the first identifier, indicating that the data stored in the target storage unit is the original data of the non-target data unit, when it is required to acquire the target stored in the target storage unit. In the case of a data unit, it is necessary to perform a series of conversion processing on the data stored in the target storage unit. If the data in the target storage unit is the first type of data, the first type of data is converted into the second type of data, and if the data in the target storage unit is the second type of data, the second type of data is Convert to the first type of data. The target data units stored in the target storage unit are sequentially.

Here, the description is continued by taking the binary data stored in the target storage unit as an example. As shown in FIG. 3, when the flag of the first target storage unit is the first identifier, that is, the data with the data bit value of 0 is It indicates that the data stored in the target storage unit needs to be converted. The first type of data, that is, the data with the data value of 0 needs to be converted into the second type of data, that is, the data with the data value of 1; the second type of data, That is, the data with a data value of 1 needs to be converted into the first type of data, that is, the data with the data value of 0. Therefore, the data stored in the target storage unit is sequentially converted. The obtained binary data is: 10000100, and the data 10000100 is determined as the target data unit stored in the target storage unit.

S207. If the flag bit is the second identifier, read the unit stored in the target storage unit.

As an optional implementation manner, if the flag bit of the target storage unit is the second identifier, when the target data unit stored in the target storage unit is taken, the target storage unit stored in the target storage unit is directly read to continue to store the target. The binary data is stored in the unit as an example. As shown in FIG. 3, in the second target storage unit, the flag of the target storage unit is the second identifier, that is, the data with the data value of 1, the target storage unit. The data 11111010 stored in the target data unit is the original data in the target data unit, so when it is necessary to acquire the target data unit stored in the target storage unit, only the stored data 11111010 needs to be read from the target storage unit, and the data 11111010 is determined. The target data unit stored for the target storage unit.

In the embodiment of the present invention, when the target data unit needs to be stored, the number of the first data of the first type and the second type of the second type of the type in the target data unit are obtained, when the first When the number of data is greater than the number of second data, a target position of the second data in the target data unit is obtained, and a target in the target storage unit of the second type of data is pre-filled The location is written to the first type of data, in place of the second data in the target data unit. In the embodiment of the present invention, the first type of data in the target storage unit is used to replace the second type of data in the target data unit, in the target data. When there is more data of the first type in the unit, and less data of the second type, only less data of the first type needs to be written to replace the second type of data in the target data unit, so the efficiency is relatively high. And because the write data is less, the power consumption is also lower. The structure of the data processing apparatus according to the embodiment of the present invention will be described in detail below with reference to Figs. It should be noted that the data processing device described below can be applied to the above method.

FIG. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention; the data processing apparatus may include: an obtaining module 100 and a first writing module 101. The obtaining module 100 is configured to acquire, when the target data unit needs to be stored, the number of the first data and the second data in the target data unit, where the type of the first data is a first type, The type of the second data is the second type;

In an embodiment, when the target data unit needs to be stored in the target storage unit, the first acquiring module 100 needs to acquire the number of the first data and the second data in the target data unit, and compare the data in the computer system. When storing, it is generally stored in the form of data units, and one data unit can include 8 bits of data. Therefore, there are multiple data in the target data unit, and the types of data included in the target data unit may also be various. For example, when the data is stored in binary form, the types included in the target data unit are Two types, the first type and the second type, the first type of data may be data having a data value of 0, and the second type of data may be data having a data value of 1, then the first data in the target data unit is All data with a data value of 0, the second data is data with a total data value of 1. It should be noted that the first type of data may also be data with a data value of 1, and the second type of data may be data with a data value of 0, and the first data in the target data unit is all data values of 1. Data, the second data is all data with a data value of 0

The first writing module 101 is configured to: if the number of the first data is greater than the number of the second data, acquire a first target location of the second data in the target data unit, and The first type of data is written in the first target location in a target storage unit pre-filled with the second type of data.

In one embodiment, when the data is stored in the computer memory, in order to reduce the amount of data written to the data, and reduce the delay, the computer memory is generally pre-filled, that is, each storage unit is pre-filled with one type. Type data, when storing data to a storage unit, directly modify the number of bits of the data value directly in the storage unit. Because the number of bits that need to be modified is too large, and a large amount of data needs to be written, the power consumption is long and the delay is long. Therefore, in the embodiment of the present invention, the pre-filled data type is the second type of data. When the number of the first data of the first type in the target data unit is greater than the number of the second data of the second type, the first writing module 101 directly acquires the second type of data in the target data unit. a first target location, and writing the first type of data in the first target location in the target storage unit, replacing the second type of data in the target data unit with the first type of data, and replacing the target data with the second type of data The first type of data in the unit is equivalent to flipping the data in the target data unit. Here, the binary data is stored in the target storage unit as an example. Since power consumption and delay are comprehensively considered, data of a data value of 1 is generally pre-filled in the target storage unit, that is, the second type of data is a data value. For data of 1, the first type of data is data with a data value of zero. When the number of data whose data value is 0 in the target data unit is larger than the number of data whose data value is 1, for example, the target data unit is 10000100, the data value is 0, the data number is 6, and the data value is 1. If the number of data with the data value of 0 is greater than the number of data with the data value of 1, the first target position of the data with the data value of 1 in the target data unit is obtained. In this embodiment, the first target When the position is the first bit and the sixth bit, the data having the data value of 0 is written in the first bit and the sixth bit of the target memory unit, and the data having the data value of 1 in the target data unit is replaced in the target storage unit. The stored data is 01111011, and the stored data is not the original data of the target data unit, but the inversed data of the original data.

In the embodiment of the present invention, when the target data unit needs to be stored, the number of the first data of the first type and the second type of the second type of the type in the target data unit are obtained, when the first When the number of data is greater than the number of second data, a target position of the second data in the target data unit is obtained, and a target in the target storage unit of the second type of data is pre-filled The location is written to the first type of data, in place of the second data in the target data unit. In the embodiment of the present invention, the first type of data in the target storage unit is used to replace the second type of data in the target data unit, in the target data. When there is more data of the first type in the unit, and less data of the second type, only less data of the first type needs to be written to replace the second type of data in the target data unit, so the efficiency is relatively high. And because the write data is less, the power consumption is also lower. FIG. 5 is a schematic structural diagram of another data processing apparatus according to an embodiment of the present invention. The data processing apparatus may include: an obtaining module 100, a first writing module 101, a first setting module 102, and a second writing. The module 103, the second setting module 104, the reading module 105, the conversion determining module 106, and the reading determining module 107, wherein the obtaining module 100 and the first writing module 101 are referred to FIG. 4, and details are not described herein.

a first setting module 102, configured to set a flag bit of the target storage unit as a first identifier, where the first identifier is used to identify that data stored in the target storage unit is not original in the target data unit data. As an optional implementation manner, after storing the target data unit, in order to facilitate reading data, the first setting module 102 needs to set the flag bit of the target storage unit, when the data stored in the target storage unit is not The original data of the target data unit, the first setting module 102 sets the flag bit of the target storage unit as the first identifier, where the first identifier is the original data in the non-target data unit of the data stored in the target storage unit, such as As shown in FIG. 3, a scene graph for storing binary data in the PCM memory, in the first target storage unit, the flag bit is set with the first identifier, and the first identifier is replaced by data with a data value of 0. Then, the data 01111011 stored in the target storage unit is not the original data of the target data unit. When the target data unit stored in the target storage unit needs to be read, the data in the target storage unit needs to be bit-inverted.

a second writing module 103, configured to acquire a second target position of the first data in the target data unit, if the number of the first data is less than or equal to the number of the second data, And writing the first type of data into the second target location in a target storage unit pre-filled with the second type of data.

As an optional implementation manner, the type of the first data is a first type, and the type of the second data is a second type. The type of the data pre-filled in the target storage unit is the second type. Since the number of the first data in the target data unit is less than or equal to the number of the second data, in order to write a smaller amount of data in the target storage unit, Then the second write module 103 can directly source the corresponding data of the corresponding bits in the target storage unit.

Here, the binary data is stored in the target storage unit as an example. Since power consumption and delay are comprehensively considered, data of a data value of 1 is generally pre-filled in the target storage unit, that is, the second type of data is a data value. For data of 1, the first type of data is data with a data value of zero. When the number of data whose data value is 0 in the target data unit is less than or equal to the number of data whose data value is 1, for example, the target data unit is 11111010, the data value is 0, the data number is 2, and the data value is 1. The number of data is 6, the number of data having a data value of 0 is smaller than the number of data having a data value of 1, and the second writing module 103 acquires the first target position of the data having the data value of 0 in the target data unit. In this embodiment, the first target position is the sixth bit and the eighth bit, and the second writing module 103 writes the data with the data value of 0 in the sixth and eighth bits of the target storage unit, and replaces the target data. If the data value of the unit is 0, the data stored in the target storage unit is 11111010, and the stored data is the target. The raw data of the data unit, specifically, the second storage unit in the PCM memory as described in FIG.

a second setting module 104, configured to set a flag bit of the target storage unit as a second identifier, where the second identifier is used to identify that data stored in the target storage unit is original in the target data unit data.

As an optional implementation manner, after storing the target data unit, in order to facilitate reading data, the second setting module 104 needs to set the flag bit of the target storage unit, when the data stored in the target storage unit is The raw data of the target data unit, the second setting module 104 sets the flag bit of the target storage unit as the second identifier, and the second identifier is that the data stored in the target storage unit is the original data in the target data unit, such as As shown in FIG. 3, which is a scene graph for storing binary data in the PCM memory, in the second target storage unit, the flag bit is set with the second identifier, and the second identifier is replaced with the data with the data value of 1. Then, the data 11111010 stored in the target storage unit is the original data of the target data unit, and when the target data unit stored in the target storage unit needs to be read, the data in the target storage unit is directly read.

The reading module 105 is configured to read a flag bit of the target storage unit when the target data unit stored in the target storage unit needs to be acquired;

As an optional implementation manner, after the target data unit is stored to the target data unit, when the target data unit is to be called, the target data unit needs to be acquired from the target storage unit. In the embodiment of the present invention, the method for acquiring the target data unit is based on the rule of storing the target data unit in the target storage unit, so when the target data unit stored in the target storage unit needs to be acquired, the reading module 105 reads first. The flag bit of the target storage unit is used to identify whether the data stored in the target storage unit is the original data in the target data unit.

The conversion determining module 106 is configured to: if the flag bit is the first identifier, convert the first type of data in the target storage unit into the second type of data, and use the target storage unit The second type of data is converted into the first type of data, and the conversion processed as an optional implementation manner, if the target storage unit flag is the first identifier, indicating the target The data stored in the storage unit is not the original data of the target data unit. When it is required to acquire the target data unit stored in the target storage unit, the conversion determination module 106 needs to target the storage unit. The data stored in is subjected to a series of conversion processing. If the data in the target storage unit is the first type of data, the conversion determining module 106 converts the first type of data into the second type of data, and if the data in the target storage unit is the second type of data, the conversion determines Module 106 converts the second type of data into the first type of data. The conversion determination module 106 sequentially pairs the target data units stored in the target storage unit.

Here, the description is continued by taking the binary data stored in the target storage unit as an example. As shown in FIG. 3, when the flag of the first target storage unit is the first identifier, that is, the data with the data bit value of 0 is It indicates that the data stored in the target storage unit needs to be converted. The first type of data, that is, the data with the data value of 0 needs to be converted into the second type of data, that is, the data with the data value of 1; the second type of data, That is, the data with the data value of 1 needs to be converted into the first type of data, that is, the data with the data value of 0. Therefore, the conversion determining module 106 sequentially converts the binary data obtained by converting each data stored in the target storage unit into : 10000100, the data 10000100 is determined as the target data unit stored by the target storage unit.

The read determining module 107 is configured to read the target data unit of the target storage if the flag bit is the second identifier.

As an optional implementation manner, if the flag of the target storage unit is the second identifier, it indicates that the data stored in the target storage unit is the original data of the target data unit, and therefore, when it is required to acquire the storage in the target storage unit. When the target data unit is reached, the read determination module 107 directly reads the destination target data unit.

Here, the description is continued by taking the binary data stored in the target storage unit as an example. As shown in FIG. 3, in the second target storage unit, the flag of the target storage unit is the second identifier, that is, the data with the data value of 1. Then, the data 11111010 stored in the target storage unit is the original data in the target data unit, and therefore, when the target data unit stored in the target storage unit needs to be acquired, only the read determination module 107 needs to read from the target storage unit. The stored data 11111010 is determined as the target data unit stored by the target storage unit.

In the embodiment of the present invention, when the target data unit needs to be stored, the target data unit is acquired. The number of the first data of the first type and the number of the second data of the second type are relatively small when the number of the first data is greater than the number of the second data The second data is in a target location in the target data unit, and the target location in the target storage unit pre-filled with the second type of data is written into the first type of data, in place of the second data in the target data unit, In the embodiment of the present invention, the first type of data in the target storage unit is used to replace the second type of data in the target data unit. When the first type of data is more in the target data unit, and the second type of data is less, only The lesser first type of data is written to replace the relatively smaller second type of data in the target data unit, so the efficiency is higher, and since the write data is less, the power consumption is also lower. FIG. 6 is a schematic structural diagram of still another data processing apparatus according to an embodiment of the present invention; the data processing apparatus may include: a processor 200.

The processor 200 is configured to acquire, when the target data unit needs to be stored, the number of the first data and the second data in the target data unit, where the type of the first data is the first type, The type of the second data is the second type;

Optionally, when the target data unit needs to be stored in the target storage unit, first, the number of the first data and the second data in the target data unit are acquired, and when the data is stored in the computer system, generally It is stored in the form of data units, and one data unit can include 8 bits of data. Therefore, there are multiple data in the target data unit, and the types of data included in the target data unit may also be various. For example, when the data is stored in binary form, the types included in the target data unit are Two types, the first type and the second type, the first type of data may be data having a data value of 0, and the second type of data may be data having a data value of 1, then the first data in the target data unit is All data with a data value of 0, the second data is data with a total data value of 1. It should be noted that the first type of data may also be data with a data value of 1, and the second type of data may be data with a data value of 0, and the first data in the target data unit is all data values of 1. The second data is the data with all data values of 0.

The processor 200 is further configured to: if the number of the first data is greater than the number of the second data, acquire a first target location of the second data in the target data unit, and pre-populate Writing the first type of data into the first target location in a target storage unit of the second type of data. Optionally, when the data is stored in the computer memory, in order to reduce the amount of data written in the data, and reduce the delay, the computer memory is generally pre-filled, that is, each type of storage unit is pre-filled with a type. Data, when storing data to a storage unit, directly modify the number of bits of the data value directly in the storage unit. Because the number of bits that need to be modified is too large, and a large amount of data needs to be written, the power consumption is long and the delay is long. Therefore, in the embodiment of the present invention, the pre-filled data type is the second type of data. When the number of the first data of the first type in the target data unit is greater than the number of the second data of the second type, the first target position of the second type of data in the target data unit is directly obtained, and Writing the first type of data into the first target location in the target storage unit, replacing the second type of data in the target data unit with the first type of data, and replacing the first type of the target data unit with the second type of data Data is equivalent to flipping the data in the target data unit.

As an optional implementation manner, the processor 200 is further configured to: if the number of the first data is less than or equal to the number of the second data, acquire the first data in the target data. a second target location in the cell, and writing the first type of data in the second target location in a target storage unit pre-filled with the second type of data.

Optionally, the type of the first data is a first type, and the type of the second data is a second type. The type of data pre-filled in the target storage unit is the second type, since the number of the first data in the target data unit is less than or equal to the number of the second data, in order to write less data in the target storage unit Quantity, then the first type of data can be directly written in the corresponding position in the target storage unit, that is, the target is described here by storing binary data in the target storage unit as an example, due to comprehensive consideration of power consumption and delay, generally Data having a data value of 1 is pre-filled in the target storage unit, that is, data of the second type is data having a data value of 1, and data of the first type is data having a data value of zero. When the number of data whose data value is 0 in the target data unit is less than or equal to the number of data whose data value is 1, for example, the target data unit is 11111010, the data value is 0, the data number is 2, and the data value is 1. The number of data is 6, the number of data whose data value is 0 is smaller than the number of data whose data value is 1, and the first target position of the data whose data value is 0 in the target data unit is obtained. In this embodiment, When the target position is the sixth bit and the eighth bit, the data with the data value of 0 is written in the sixth and eighth bits of the target storage unit, and the data of the data value of 0 in the target data unit is replaced, and the target storage is performed. The data stored in the unit is 11111010, and the stored data is the original data of the target data unit, specifically, the second storage unit in the PCM memory as described in FIG.

As an optional implementation manner, the processor 200 is further configured to set a flag of the target storage unit as a first identifier, where the first identifier is used to identify data stored in the target storage unit. Not raw data in the target data unit.

Optionally, after the target data unit is stored, in order to facilitate the reading of the data, the flag of the target storage unit needs to be set, and when the data stored in the target storage unit is not the original data of the target data unit, that is, When the storage is performed according to the method of step S201, the flag bit of the target storage unit is set as the first identifier, and the first identifier is the original data in the non-target data unit of the data stored in the target storage unit. As shown in FIG. 3, for the scene graph in which the binary data is stored in the PCM memory, in the first target storage unit, the flag bit is set with the first identifier, and the first identifier is replaced by the data with the data value of 0. Then, the data 01111011 stored in the target storage unit is not the original data of the target data unit. When the target data unit stored in the target storage unit needs to be read, the data in the target storage unit needs to be bit-inverted.

As an optional implementation manner, the processor 200 is further configured to set a flag bit of the target storage unit as a second identifier, where the second identifier is used to identify data stored in the target storage unit. Is the raw data in the target data unit.

Optionally, after storing the target data unit, in order to facilitate the reading of the data, the target needs to be The flag of the storage unit is set. When the data stored in the target storage unit is the original data of the target data unit, that is, when stored, according to the method of step S203, the flag of the target storage unit is set. Set as the second identifier, the second identifier is that the data stored in the target storage unit is the original data in the target data unit, as shown in FIG. 3, is a scene graph for storing binary data in the PCM memory, in the second In the target storage unit, the flag bit is set with the second identifier, and the second identifier is replaced by the data with the data value of 1. Then, the data 11111010 stored in the target storage unit is the original data of the target data unit, and when the target data unit stored in the target storage unit needs to be read, the data in the target storage unit is directly read.

As an optional implementation manner, the processor 200 is further configured to: when the target data unit stored in the target storage unit needs to be acquired, read a flag of the target storage unit; After the target data unit is stored to the target data unit, when the target data unit is to be called, the target data unit needs to be acquired from the target storage unit. In the embodiment of the present invention, the method for acquiring the target data unit is based on the rule of storing the target data unit in the target storage unit, so when the target data unit stored in the target storage unit needs to be acquired, the target storage unit is first read. The flag bit is used to identify whether the data stored in the target storage unit is the original data in the target data unit.

The processor 200 is further configured to: if the flag bit is the first identifier, convert the first type of data in the target storage unit into the second type of data, and store the target Converting the second type of data in the unit into the first type of data, and determining the converted data as the target data unit stored in the target storage unit;

Optionally, if the flag of the target storage unit is the first identifier, indicating that the data stored in the target storage unit is the original data of the non-target data unit, when it is required to acquire the target data unit stored in the target storage unit, A series of conversion processing is performed on the data stored in the target storage unit. If the data in the target storage unit is the first type of data, converting the first type of data into the second type of data, and if the data in the target storage unit is the second type of data, the second type of data is Convert to the first type of data. The following is a description of all the data stored in the target storage unit, and the binary data stored in the target storage unit is taken as an example. As shown in FIG. 3, the flag of the first target storage unit is the first identifier, that is, Is the flag bit as the data value is 0 The data indicates that the data stored in the target storage unit needs to be converted. The first type of data, that is, the data with the data value of 0 needs to be converted into the second type of data, that is, the data with the data value of 1; The second type of data, that is, the data having the data value of 1 needs to be converted into the first type of data, that is, the data having the data value of 0. Therefore, the binary data obtained by converting the respective data stored in the target storage unit in turn is : 10000100, the data 10000100 is determined as the target data unit stored by the target storage unit.

The processor 200 is further configured to read the target data unit of the target storage if the flag bit is the second identifier.

Optionally, if the flag bit of the target storage unit is the second identifier, it indicates that the data stored in the target storage unit is the original data of the target data unit, and therefore, when the target data unit stored in the target storage unit needs to be acquired, And directly reading the data stored in the target storage unit, and determining the read data as the target data unit stored in the target storage unit.

Here, the description is continued by taking the binary data stored in the target storage unit as an example. As shown in FIG. 3, in the second target storage unit, the flag of the target storage unit is the second identifier, that is, the data with the data value of 1. The data 11111010 stored in the target storage unit is the original data in the target data unit. Therefore, when the target data unit stored in the target storage unit needs to be acquired, only the stored data 11111010 needs to be read from the target storage unit. The data 11111010 is determined as the target data unit stored by the target storage unit.

In the embodiment of the present invention, when the target data unit needs to be stored, the number of the first data of the first type and the second type of the second type of the type in the target data unit are obtained, when the first When the number of data is greater than the number of second data, a target position of the second data in the target data unit is obtained, and a target in the target storage unit of the second type of data is pre-filled The location is written to the first type of data, in place of the second data in the target data unit. In the embodiment of the present invention, the first type of data in the target storage unit is used to replace the second type of data in the target data unit, in the target data. When there is more data of the first type in the unit, and less data of the second type, only less data of the first type needs to be written to replace the second type of data in the target data unit, so the efficiency is relatively high. And because the write data is less, the power consumption is also lower.

One of ordinary skill in the art can understand all or part of the process in implementing the above embodiments. This may be accomplished by a computer program instructing the associated hardware, which may be stored in a computer readable storage medium, which, when executed, may include the flow of an embodiment of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only the preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, and the equivalent changes made by the claims of the present invention are still within the scope of the present invention.

Claims

Rights request

1. A data processing method, characterized in that the method includes:

When it is necessary to store the target data unit, the number of first data and the number of second data in the target data unit are obtained, the type of the first data is the first type, and the type of the second data is the first type. Type II;

If the number of the first data is greater than the number of the second data, obtain the first target position of the second data in the target data unit, and prefill it as the second type. The first type of data is written in the first target location in the data target storage unit.

2. The method of claim 1, characterized in that, the method further includes:

If the number of the first data is less than or equal to the number of the second data, obtain the second target position of the first data in the target data unit, and prefill it as the second The data of the first type is written in the second target location of the target storage unit.

3. The method of claim 2, wherein if the number of the first data is greater than the number of the second data, obtaining the second data in the target data unit the first target location, and after writing the first type of data into the first target location in the target storage unit prefilled with the second type of data, the method further includes:

The flag bit of the target storage unit is set to a first identification, and the first identification is used to identify that the data stored in the target storage unit is not the original data in the target data unit.

4. The method of claim 3, wherein if the number of the first data is less than or equal to the number of the second data, obtaining the first data in the target data and writing the first type of data into the second target location in the target storage unit that is prefilled with the second type of data. The method further includes:

The flag bit of the target storage unit is set to a second identification, and the second identification is used to identify that the data stored in the target storage unit is the original data in the target data unit.

5. The method of claim 4, further comprising: when it is necessary to obtain the target data unit stored in the target storage unit, reading the flag bit of the target storage unit. ;

If the flag bit is the first identifier, the first type of data in the target storage unit is converted into the second type of data, and the second type of data in the target storage unit is converted into Convert the data into the first type of data, and determine the converted data as the target data unit stored in the target storage unit;

If the flag bit is the second identifier, read the number stored in the target storage unit.

6. A data processing device, characterized in that the device includes:

An acquisition module, configured to acquire the number of first data and the number of second data in the target data unit when the target data unit needs to be stored, where the type of the first data is the first type, and the second type The type of data is the second type;

A first writing module, configured to obtain the first target position of the second data in the target data unit if the number of the first data is greater than the number of the second data, and store the preset data in the target data unit. The first type of data is written into the first target location in the target storage unit filled with the second type of data.

7. The device according to claim 6, characterized in that, the device further includes:

A second writing module, configured to obtain the second target position of the first data in the target data unit if the number of the first data is less than or equal to the number of the second data, and The first type of data is written into the second target location in the target storage unit prefilled with the second type of data.

8. The device according to claim 7, wherein the device further includes:

A first setting module, configured to set the flag bit of the target storage unit to a first identifier, and the first identifier is used to identify that the data stored in the target storage unit is not in the target data unit. of raw data.

9. The device according to claim 8, characterized in that, the device further includes:

The second setting module is used to set the flag bit of the target storage unit to a second identification, and the second identification is used to identify the data stored in the target storage unit as the original data in the target data unit. .

10. The device according to claim 9, wherein the device further includes: a reading module, configured to read the target data unit stored in the target storage unit when it is necessary to obtain the target data unit. The flag bit of the target storage unit;

A conversion determination module, configured to convert the first type of data in the target storage unit into the second type of data if the flag bit is the first identification, and convert the first type of data in the target storage unit to the second type of data. Convert the second type of data into the first type of data, and determine the converted data as the target data unit stored in the target storage unit;

A reading determination module, configured to read the data stored in the target storage unit if the flag bit is the second identification, ^

The target data unit.

11. A data processing device, characterized in that it includes a processor, wherein:

The processor is configured to obtain the number of first data and the number of second data in the target data unit when it is necessary to store the target data unit, and the type of the first data is a first type, and the The type of the second data is the second type;

The processor is also configured to obtain the first target position of the second data in the target data unit if the number of the first data is greater than the number of the second data, and pre-fill the Writing the first type of data into the first target location in the target storage unit for the second type of data.

12. The data processing device according to claim 11, characterized in that,

The processor is also configured to: if the number of the first data is less than or equal to the number of the second data number, then obtain the second target position of the first data in the target data unit, and write the second target position in the target storage unit prefilled with the second type of data. Describe the first type of data.

13. The data processing device according to claim 12, characterized in that,

The processor is further configured to set a flag bit of the target storage unit to a first identification, and the first identification is used to identify that the data stored in the target storage unit is not the original data in the target data unit. .

14. The data processing device according to claim 13, characterized in that,

The processor is further configured to set the flag bit of the target storage unit to a second identification, and the second identification is used to identify that the data stored in the target storage unit is the original data in the target data unit. .

15. The data processing device according to claim 14, characterized in that,

The processor is also configured to read the flag bit of the target storage unit when it is necessary to obtain the target data unit stored in the target storage unit;

The processor is also configured to convert the first type of data in the target storage unit into the second type of data if the flag bit is the first identification, and convert the target storage unit to the second type of data. Convert the second type of data into the first type of data, and determine the converted data as the target data unit stored in the target storage unit;

The processor is also configured to read the data stored in the target storage unit if the flag bit is the second identification, ^

Describe the target data unit.