CN108170634B - A kind of isomerous multi-source data reconstruction transient state reliable treatments method - Google Patents
A kind of isomerous multi-source data reconstruction transient state reliable treatments method Download PDFInfo
- Publication number
- CN108170634B CN108170634B CN201711427893.8A CN201711427893A CN108170634B CN 108170634 B CN108170634 B CN 108170634B CN 201711427893 A CN201711427893 A CN 201711427893A CN 108170634 B CN108170634 B CN 108170634B
- Authority
- CN
- China
- Prior art keywords
- byte
- fpga
- area
- dynamic area
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7867—Architectures of general purpose stored program computers comprising a single central processing unit with reconfigurable architecture
- G06F15/7871—Reconfiguration support, e.g. configuration loading, configuration switching, or hardware OS
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种异构多源数据重构瞬态可靠处理方法,包括:FPGA动态区状态判断;FPGA静态区建立BRAM实现对重构瞬间数据的缓存;在重构完成后,FPGA动态区向静态区发送询问帧,询问帧中包括该动态区在FPGA芯片内部物理区域的坐标和在该动态区上运行的重构代码的功能ID;FPGA静态区解析动态区发送的询问帧,并返回应答帧,应答帧中包括重构瞬间缓存在BRAM中的数据。本发明公开的方法能够解决由于FPGA动态区出现故障或者功能切换导致的动态区重构时出现的动态区与静态区之间的数据交互出现中断的问题,提高异构多源数据处理的可靠性。
The invention discloses a reliable transient processing method for heterogeneous multi-source data reconstruction, including: FPGA dynamic area state judgment; Send an inquiry frame to the static area, which includes the coordinates of the dynamic area in the physical area of the FPGA chip and the function ID of the reconfigured code running on the dynamic area; the FPGA static area parses the inquiry frame sent by the dynamic area and returns Response frame, which includes the data cached in the BRAM at the moment of reconstruction. The method disclosed by the invention can solve the problem of interruption of data interaction between the dynamic area and the static area during the reconstruction of the dynamic area caused by the failure of the FPGA dynamic area or function switching, and improve the reliability of heterogeneous multi-source data processing .
Description
技术领域technical field
本发明属于电子工程和计算机科学领域,具体涉及一种异构多源数据重构瞬态可靠处理方法。The invention belongs to the fields of electronic engineering and computer science, and in particular relates to a transient reliable processing method for heterogeneous multi-source data reconstruction.
背景技术Background technique
随着国家战略“中国制造2025”的提出,智能制造已成为当代中国的热点名词。但是实现智能制造离不开数据,这些数据更具体的表现为制造现场的数据,所以制造现场数据的可靠采集、处理、交换与传输就是实现智能制造的底层技术支撑。制造现场的数据在数据协议上表现为异构,在数据量上表现为多源,如何在高效处理异构多源数据的同时,保证数据处理的可靠性就显得至关重要。由于FPGA具备天生的硬件并行和动态重构特性,在FPGA内部构建一个静态区和多个动态区,静态区完成数据的采集,例如采集机床的电压、电流、转速,采集生产线的实时图像数据以及环境参数等;各个动态区运行不同的处理算法,例如动态区1运行电压滤波处理算法、动态区2运行图像灰度处理算法、动态区3运行环境参数的预处理算法等,这样就能实现异构多源数据的高效处理。With the proposal of the national strategy "Made in China 2025", intelligent manufacturing has become a hot term in contemporary China. However, the realization of intelligent manufacturing is inseparable from data. These data are more specifically expressed as data on the manufacturing site. Therefore, the reliable collection, processing, exchange and transmission of manufacturing site data is the underlying technical support for the realization of intelligent manufacturing. The data at the manufacturing site is heterogeneous in terms of data protocol and multi-source in terms of data volume. How to efficiently process heterogeneous multi-source data while ensuring the reliability of data processing is very important. Due to the inherent hardware parallelism and dynamic reconfiguration characteristics of FPGA, a static area and multiple dynamic areas are built inside the FPGA. The static area completes the data collection, such as collecting the voltage, current, and speed of the machine tool, collecting real-time image data of the production line, and Environmental parameters, etc.; each dynamic area runs different processing algorithms, such as the voltage filter processing algorithm in dynamic area 1, the image grayscale processing algorithm in dynamic area 2, and the preprocessing algorithm for environmental parameters in dynamic area 3, etc., so that different Efficient processing of structured multi-source data.
但是制造现场存在着一定的辐射和电离,包括FPGA在内的微处理芯片都很有可能出现硬件损坏和代码“跑飞”等故障,但是FPGA通过动态重构可以提高数据处理的可靠性,具体表现为当某个动态区上运行的代码出现“跑飞”时,FPGA静态区通过状态机读取存储在片外flash内的动态代码,并重新加载到出现故障的动态区中,以实现动态区的故障自恢复;或者FPGA静态区读取别另一个动态代码并加载到该动态区中,以实现动态区的功能切换。但是在动态区重构的过程中,静态区和动态区之间的数据交互是中断的,即使FPGA动态的重构的时间一般在毫秒级,但是对于对实时性要求比较苛刻的数据处理场合,重构造成的数据处理中断也直接影响数据处理的可靠性。因此,本发明提出一种异构多源数据重构瞬态可靠处理方法,该方法能够解决FPGA动态重构时静态区和动态区之间的数据交互出现中断的问题,能够实现异构多源数据的可靠处理。However, there is a certain amount of radiation and ionization in the manufacturing site, and micro-processing chips including FPGAs are likely to have hardware damage and code "runaway" failures, but FPGAs can improve the reliability of data processing through dynamic reconfiguration. The performance is that when the code running on a certain dynamic area "runs away", the static area of the FPGA reads the dynamic code stored in the off-chip flash through the state machine, and reloads it into the faulty dynamic area to realize dynamic The fault self-recovery of the area; or the FPGA static area reads another dynamic code and loads it into the dynamic area to realize the function switching of the dynamic area. However, during the reconstruction process of the dynamic area, the data interaction between the static area and the dynamic area is interrupted. Even though the FPGA dynamic reconstruction time is generally at the millisecond level, for data processing occasions with strict real-time requirements, The interruption of data processing caused by reconstruction also directly affects the reliability of data processing. Therefore, the present invention proposes a reliable transient processing method for heterogeneous multi-source data reconstruction, which can solve the problem of interruption of data interaction between the static area and the dynamic area when the FPGA is dynamically reconfigured, and can realize heterogeneous multi-source Reliable processing of data.
发明内容Contents of the invention
本发明要解决的技术问题为:提供一种异构多源数据重构瞬态可靠处理方法,该方法能够解决FPGA动态重构时静态区和动态区之间的数据交互出现中断的问题,能够实现异构多源数据的可靠处理。The technical problem to be solved by the present invention is to provide a reliable transient processing method for heterogeneous multi-source data reconstruction, which can solve the problem of interruption of data interaction between the static area and the dynamic area during FPGA dynamic reconstruction, and can Realize reliable processing of heterogeneous multi-source data.
本发明解决其技术问题是采取以下技术方案实现的:一种异构多源数据重构瞬态可靠处理方法,包括以下步骤:The present invention solves the technical problem by adopting the following technical solutions: a transient and reliable processing method for heterogeneous multi-source data reconstruction, comprising the following steps:
步骤一:FPGA动态区状态判断,具体实现如下:Step 1: Judging the status of the FPGA dynamic area, the specific implementation is as follows:
①建立一个宽度为1,深度为1的双端口BRAM,在FPGA主时钟的驱动下,静态区通过端口A置该BRAM的数值为高电平,在经过10个主时钟周期之后,静态区通过端口A读取判断该BRAM的数值的电平状态:当为高电平时,表明动态区处于重构过程中:当为低电平时,表明动态区处于非重构过程中;① Establish a dual-port BRAM with a width of 1 and a depth of 1. Driven by the main clock of the FPGA, the static area sets the value of the BRAM to a high level through port A. After 10 main clock cycles, the static area passes Port A reads and judges the level state of the value of the BRAM: when it is high, it indicates that the dynamic area is in the process of reconstruction; when it is low, it indicates that the dynamic area is in the process of non-reconstruction;
②动态区在FPGA主时钟的驱动下通过端口B实时读取并判断该BRAM的数值的电平状态,当为高电平时,在下一个时钟周期将该BRAM的数值的电平状态复位为低电平;②The dynamic area reads and judges the level state of the value of the BRAM through port B in real time under the drive of the FPGA main clock. When it is high, the level state of the value of the BRAM is reset to low in the next clock cycle. flat;
③当有k个动态区时,需要在静态区建立k个宽度为1,深度为1的双端口BRAM,各个动态区状态的判断如①和②;③When there are k dynamic areas, k dual-port BRAMs with a width of 1 and a depth of 1 need to be established in the static area, and the status of each dynamic area is judged as ① and ②;
步骤二:FPGA静态区建立数据缓存BRAM实现对重构瞬态数据的缓存,具体实现如下:Step 2: Establish a data cache BRAM in the static area of the FPGA to cache the reconstructed transient data. The specific implementation is as follows:
①FPGA静态区建立一个BRAM,当静态区监测到动态区处于重构过程中时,静态区将待处理的数据缓存在这个BRAM中;① A BRAM is established in the static area of the FPGA. When the static area detects that the dynamic area is in the process of being reconstructed, the static area caches the data to be processed in this BRAM;
②FPGA静态区按照各个动态区在FPGA芯片内部物理区域的坐标和在该动态区上运行的重构代码的功能ID的不同,分别将数据缓存在该BRAM的不同偏移地址中;②The FPGA static area caches data in different offset addresses of the BRAM according to the coordinates of each dynamic area in the physical area of the FPGA chip and the function ID of the reconfigured code running on the dynamic area;
步骤三:在重构完成后,FPGA动态区向静态区发送询问帧,帧格式具体实现如下:Step 3: After the reconstruction is completed, the FPGA dynamic area sends an inquiry frame to the static area. The specific implementation of the frame format is as follows:
①字节0-1为帧头,即十六进制5A、54;①Byte 0-1 is the frame header, that is, hexadecimal 5A, 54;
②字节2-11为数据区,其中字节2-3表示该动态区在FPGA芯片内部物理区域的左上顶点的横坐标;字节4-5表示该动态区在FPGA芯片内部物理区域的左上顶点的纵坐标;字节6-7表示该动态区在FPGA芯片内部物理区域的右下顶点的横坐标;字节8-9表示该动态区在FPGA芯片内部物理区域的右下顶点的纵坐标;字节10-11表示在该动态区上运行的重构代码的功能ID;②Byte 2-11 is the data area, where byte 2-3 indicates the abscissa of the upper left vertex of the dynamic area in the physical area inside the FPGA chip; byte 4-5 indicates that the dynamic area is in the upper left of the physical area inside the FPGA chip The ordinate of the vertex; bytes 6-7 indicate the abscissa of the dynamic area in the lower right vertex of the internal physical area of the FPGA chip; bytes 8-9 indicate the ordinate of the dynamic area in the lower right vertex of the internal physical area of the FPGA chip ;Bytes 10-11 represent the function ID of the refactored code running on this dynamic area;
③字节12为数据区结束标识符,即十六进制00;③Byte 12 is the end identifier of the data area, that is, hexadecimal 00;
④字节13为校验,即数据区中各个字节的逻辑和取低字节;④Byte 13 is the checksum, that is, the logical sum of each byte in the data area takes the low byte;
⑤字节14-15为数据区的长度,其中字节14为高字节;⑤Byte 14-15 is the length of the data area, and byte 14 is the high byte;
⑥字节16-17为帧尾,即十六进制5A、FE;⑥Byte 16-17 is the end of the frame, that is, hexadecimal 5A, FE;
当询问帧中的数据区出现帧尾,即十六进制5A、FE时,需要在该5A、FE前插入转义字符十六进制00;数据区的长度不包括插入的转义字符;When the frame end appears in the data area in the query frame, that is, hexadecimal 5A, FE, the escape character hexadecimal 00 needs to be inserted before the 5A, FE; the length of the data area does not include the inserted escape character;
步骤四:FPGA静态区解析动态区发送的询问帧,在解析询问帧时需要将插入的转义字符去除,得到该动态区在FPGA芯片内部物理区域的坐标和在该动态区上运行的重构代码的功能ID,然后静态区读取数据缓存BRAM中对应的数据;Step 4: The FPGA static area parses the query frame sent by the dynamic area. When parsing the query frame, the inserted escape characters need to be removed to obtain the coordinates of the dynamic area in the physical area inside the FPGA chip and the reconstruction running on the dynamic area. The function ID of the code, and then the static area reads the corresponding data in the data cache BRAM;
步骤五:FPGA静态区向动态区返回应答帧,帧格式具体实现如下:Step 5: The FPGA static area returns a response frame to the dynamic area, and the frame format is specifically implemented as follows:
①字节0-1为帧头,即十六进制5A、54;①Byte 0-1 is the frame header, that is, hexadecimal 5A, 54;
②字节2-(n+1)为数据区,即重构时缓存在BRAM中的数据,其中n为数据字节长度;②Byte 2-(n+1) is the data area, that is, the data cached in the BRAM during reconstruction, where n is the data byte length;
③字节n+2为数据区结束标识符,即十六进制00;③Byte n+2 is the end identifier of the data area, that is, hexadecimal 00;
④字节n+3为校验,即数据区中各个字节的逻辑和取低字节;④Byte n+3 is the checksum, that is, the logical sum of each byte in the data area takes the low byte;
⑤字节n+4、n+5为数据区的长度,其中字节n+4为高字节;;⑤Byte n+4, n+5 are the length of the data area, wherein byte n+4 is the high byte;;
⑥字节n+6、n+7为帧尾,即十六进制5A、FE;⑥Bytes n+6, n+7 are the end of the frame, that is, hexadecimal 5A, FE;
当应答帧中的数据区出现帧尾,即十六进制5A、FE时,需要在该5A、FE前插入转义字符十六进制00;数据区的长度不包括插入的转义字符。When the end of the frame appears in the data area of the response frame, that is, hexadecimal 5A, FE, the escape character hexadecimal 00 needs to be inserted before the 5A, FE; the length of the data area does not include the inserted escape character.
本发明设计的一种异构多源数据重构瞬态可靠处理方法适用于Xilinx公司Virtex-5FPGA芯片。A heterogeneous and multi-source data reconstruction transient reliable processing method designed by the invention is suitable for Virtex-5FPGA chip of Xilinx company.
本发明与现有技术相比的优点在于:The advantage of the present invention compared with prior art is:
(1)传统的采用三模冗余等来提高FPGA动态重构可靠性的方法,不仅增加了FPGA资源的消耗,而且仅仅是通过多备份的方式来提高动态区的可靠性,根本没有解决重构时的瞬态问题。本发明能够解决FPGA动态重构时静态区和动态区之间的数据交互出现中断的问题,能够实现异构多源数据的可靠处理。(1) The traditional method of using three-mode redundancy to improve the reliability of FPGA dynamic reconfiguration not only increases the consumption of FPGA resources, but also only improves the reliability of the dynamic area through multiple backups, and does not solve the problem of reconfiguration at all. Transient problem of construction time. The invention can solve the problem that the data interaction between the static area and the dynamic area is interrupted when the FPGA is dynamically reconfigured, and can realize reliable processing of heterogeneous multi-source data.
(2)本发明提出的FPGA动态区状态判断、建立BRAM来缓存重构时的数据以及静态区和动态区之间的询问帧、应答帧,能够从根本上解决FPGA重构瞬态问题。(2) The state judgment of the FPGA dynamic area proposed by the present invention, the establishment of BRAM to cache data during reconstruction, and the query frame and response frame between the static area and the dynamic area can fundamentally solve the transient problem of FPGA reconstruction.
附图说明Description of drawings
图1为本发明的流程图。Fig. 1 is a flowchart of the present invention.
具体实施方式Detailed ways
下面结合附图对本发明做进一步详细的描述。The present invention will be described in further detail below in conjunction with the accompanying drawings.
本发明涉及一种异构多源数据重构瞬态可靠处理方法,采用Xilinx公司的Virtex-5FPGA芯片。该方法针对基于FPGA动态重构的异构多源数据处理中的重构瞬态问题,所谓FPGA的重构瞬态问题就是FPGA动态重构时静态区和动态区之间的数据交互出现中断。本发明提出方法能够解决FPGA重构瞬态问题,实现异构多源数据的可靠处理。The invention relates to a transient reliable processing method for heterogeneous multi-source data reconstruction, which adopts Virtex-5FPGA chip of Xilinx company. This method aims at the reconstruction transient problem in heterogeneous multi-source data processing based on FPGA dynamic reconstruction. The so-called FPGA reconstruction transient problem means that the data interaction between the static area and the dynamic area is interrupted during FPGA dynamic reconstruction. The method proposed by the invention can solve the transient problem of FPGA reconstruction and realize reliable processing of heterogeneous multi-source data.
本发明的流程图如图1所示,具体实施方式如下:Flow chart of the present invention is as shown in Figure 1, and specific implementation is as follows:
(1)FPGA动态区状态判断,具体实现如下:(1) FPGA dynamic area state judgment, the specific implementation is as follows:
①建立一个宽度为1,深度为1的双端口BRAM,在FPGA主时钟的驱动下,静态区通过端口A置该BRAM的数值为高电平,在经过10个主时钟周期之后,静态区通过端口A读取判断该BRAM的数值的电平状态:当为高电平时,表明动态区处于重构过程中:当为低电平时,表明动态区处于非重构过程中;① Establish a dual-port BRAM with a width of 1 and a depth of 1. Driven by the main clock of the FPGA, the static area sets the value of the BRAM to a high level through port A. After 10 main clock cycles, the static area passes Port A reads and judges the level state of the value of the BRAM: when it is high, it indicates that the dynamic area is in the process of reconstruction; when it is low, it indicates that the dynamic area is in the process of non-reconstruction;
②动态区在FPGA主时钟的驱动下通过端口B实时读取并判断该BRAM的数值的电平状态,当为高电平时,在下一个时钟周期将该BRAM的数值的电平状态复位为低电平;②The dynamic area reads and judges the level state of the value of the BRAM through port B in real time under the drive of the FPGA main clock. When it is high, the level state of the value of the BRAM is reset to low in the next clock cycle. flat;
③当有k个动态区时,需要在静态区建立k个宽度为1,深度为1的双端口BRAM,各个动态区状态的判断如①和②;③When there are k dynamic areas, k dual-port BRAMs with a width of 1 and a depth of 1 need to be established in the static area, and the status of each dynamic area is judged as ① and ②;
(2)FPGA静态区建立数据缓存BRAM实现对重构瞬态数据的缓存,具体实现如下:(2) The data cache BRAM is established in the static area of the FPGA to realize the cache of the reconstructed transient data. The specific implementation is as follows:
①FPGA静态区建立一个BRAM,当静态区监测到动态区处于重构过程中时,静态区将待处理的数据缓存在这个BRAM中;① A BRAM is established in the static area of the FPGA. When the static area detects that the dynamic area is in the process of being reconstructed, the static area caches the data to be processed in this BRAM;
②FPGA静态区按照各个动态区在FPGA芯片内部物理区域的坐标和在该动态区上运行的重构代码的功能ID的不同,分别将数据缓存在该BRAM的不同偏移地址中;②The FPGA static area caches data in different offset addresses of the BRAM according to the coordinates of each dynamic area in the physical area of the FPGA chip and the function ID of the reconfigured code running on the dynamic area;
(3)在重构完成后,FPGA动态区向静态区发送询问帧,帧格式具体实现如下:(3) After the reconstruction is completed, the FPGA dynamic area sends an inquiry frame to the static area, and the frame format is specifically implemented as follows:
①字节0-1为帧头,即十六进制5A、54;①Byte 0-1 is the frame header, that is, hexadecimal 5A, 54;
②字节2-11为数据区,其中字节2-3表示该动态区在FPGA芯片内部物理区域的左上顶点的横坐标;字节4-5表示该动态区在FPGA芯片内部物理区域的左上顶点的纵坐标;字节6-7表示该动态区在FPGA芯片内部物理区域的右下顶点的横坐标;字节8-9表示该动态区在FPGA芯片内部物理区域的右下顶点的纵坐标;字节10-11表示在该动态区上运行的重构代码的功能ID;②Byte 2-11 is the data area, where byte 2-3 indicates the abscissa of the upper left vertex of the dynamic area in the physical area inside the FPGA chip; byte 4-5 indicates that the dynamic area is in the upper left of the physical area inside the FPGA chip The ordinate of the vertex; bytes 6-7 indicate the abscissa of the dynamic area in the lower right vertex of the internal physical area of the FPGA chip; bytes 8-9 indicate the ordinate of the dynamic area in the lower right vertex of the internal physical area of the FPGA chip ;Bytes 10-11 represent the function ID of the refactored code running on this dynamic area;
③字节12为数据区结束标识符,即十六进制00;③Byte 12 is the end identifier of the data area, that is, hexadecimal 00;
④字节13为校验,即数据区中各个字节的逻辑和取低字节;④Byte 13 is the checksum, that is, the logical sum of each byte in the data area takes the low byte;
⑤字节14-15为数据区的长度,其中字节14为高字节;⑤Byte 14-15 is the length of the data area, and byte 14 is the high byte;
⑥字节16-17为帧尾,即十六进制5A、FE;⑥Byte 16-17 is the end of the frame, that is, hexadecimal 5A, FE;
当询问帧中的数据区出现帧尾,即十六进制5A、FE时,需要在该5A、FE前插入转义字符十六进制00;数据区的长度不包括插入的转义字符;When the frame end appears in the data area in the query frame, that is, hexadecimal 5A, FE, the escape character hexadecimal 00 needs to be inserted before the 5A, FE; the length of the data area does not include the inserted escape character;
(4)FPGA静态区解析动态区发送的询问帧,在解析询问帧时需要将插入的转义字符去除,得到该动态区在FPGA芯片内部物理区域的坐标和在该动态区上运行的重构代码的功能ID,然后静态区读取数据缓存BRAM中对应的数据;(4) The FPGA static area parses the query frame sent by the dynamic area. When parsing the query frame, the inserted escape character needs to be removed to obtain the coordinates of the dynamic area in the physical area of the FPGA chip and the reconstruction running on the dynamic area. The function ID of the code, and then the static area reads the corresponding data in the data cache BRAM;
(5)FPGA静态区向动态区返回应答帧,帧格式具体实现如下:(5) The FPGA static area returns a response frame to the dynamic area, and the frame format is specifically implemented as follows:
①字节0-1为帧头,即十六进制5A、54;①Byte 0-1 is the frame header, that is, hexadecimal 5A, 54;
②字节2-(n+1)为数据区,即重构时缓存在BRAM中的数据,其中n为数据字节长度;②Byte 2-(n+1) is the data area, that is, the data cached in the BRAM during reconstruction, where n is the data byte length;
③字节n+2为数据区结束标识符,即十六进制00;③Byte n+2 is the end identifier of the data area, that is, hexadecimal 00;
④字节n+3为校验,即数据区中各个字节的逻辑和取低字节;④Byte n+3 is the checksum, that is, the logical sum of each byte in the data area takes the low byte;
⑤字节n+4、n+5为数据区的长度,其中字节n+4为高字节;;⑤Byte n+4, n+5 are the length of the data area, wherein byte n+4 is the high byte;;
⑥字节n+6、n+7为帧尾,即十六进制5A、FE;⑥Bytes n+6, n+7 are the end of the frame, that is, hexadecimal 5A, FE;
当应答帧中的数据区出现帧尾,即十六进制5A、FE时,需要在该5A、FE前插入转义字符十六进制00;数据区的长度不包括插入的转义字符。When the end of the frame appears in the data area of the response frame, that is, hexadecimal 5A, FE, the escape character hexadecimal 00 needs to be inserted before the 5A, FE; the length of the data area does not include the inserted escape character.
综上所述,本发明公开了一种异构多源数据重构瞬态可靠处理方法,包括:FPGA动态区状态判断;FPGA静态区建立BRAM实现对重构瞬间数据的缓存;FPGA动态区向静态区发送的询问帧以及FPGA静态区向动态区返回的应答帧。该方法能够解决基于FPGA动态重构的异构多源数据处理中的重构瞬态问题,实现异构多源数据的可靠处理。In summary, the present invention discloses a reliable transient processing method for heterogeneous multi-source data reconstruction, including: FPGA dynamic area state judgment; The query frame sent by the static area and the response frame returned by the FPGA static area to the dynamic area. The method can solve the reconstruction transient problem in heterogeneous multi-source data processing based on FPGA dynamic reconstruction, and realize reliable processing of heterogeneous multi-source data.
本发明说明书中未作详细描述的内容属于本领域专业技术人员公知的现有技术。The contents not described in detail in the description of the present invention belong to the prior art known to those skilled in the art.
以上所述仅是本发明的优选实施方式,应当指出,对于本技术领域的普通技术人员来说,在不脱离本发明原理的前提下,还可以做出若干改进和润饰,这些改进和润饰也应视为本发明的保护范围。The above is only a preferred embodiment of the present invention, it should be pointed out that, for those of ordinary skill in the art, without departing from the principle of the present invention, some improvements and modifications can also be made, and these improvements and modifications can also be made. It should be regarded as the protection scope of the present invention.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711427893.8A CN108170634B (en) | 2017-12-26 | 2017-12-26 | A kind of isomerous multi-source data reconstruction transient state reliable treatments method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711427893.8A CN108170634B (en) | 2017-12-26 | 2017-12-26 | A kind of isomerous multi-source data reconstruction transient state reliable treatments method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108170634A CN108170634A (en) | 2018-06-15 |
| CN108170634B true CN108170634B (en) | 2018-12-07 |
Family
ID=62520597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711427893.8A Expired - Fee Related CN108170634B (en) | 2017-12-26 | 2017-12-26 | A kind of isomerous multi-source data reconstruction transient state reliable treatments method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108170634B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804232B (en) * | 2018-06-26 | 2022-02-18 | 郑州云海信息技术有限公司 | Method, host server and system for supporting cloud FPGA deployment |
| CN110045691B (en) * | 2019-03-13 | 2021-03-16 | 东北大学 | Multi-task processing fault monitoring method for multi-source heterogeneous big data |
| CN112214448B (en) * | 2020-10-10 | 2024-04-09 | 声龙(新加坡)私人有限公司 | Data dynamic reconstruction circuit and method of heterogeneous integrated workload proving operation chip |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104603750A (en) * | 2012-08-30 | 2015-05-06 | 微软公司 | Layout and execution of software applications using BPRAM |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7065764B1 (en) * | 2001-07-20 | 2006-06-20 | Netrendered, Inc. | Dynamically allocated cluster system |
| US7539967B1 (en) * | 2006-05-05 | 2009-05-26 | Altera Corporation | Self-configuring components on a device |
| US8710864B2 (en) * | 2010-04-23 | 2014-04-29 | Utah State University | Dynamically reconfigurable systolic array accelorators |
| CN104008024A (en) * | 2014-06-12 | 2014-08-27 | 北京航空航天大学 | Dynamic reconstruction technology application platform based on FPGA |
| CN106372032B (en) * | 2016-09-08 | 2018-02-13 | 北京航空航天大学 | A kind of FPGA dynamic reconfiguration methods |
| CN106682294B (en) * | 2016-12-15 | 2019-12-24 | 西安交通大学 | A Layout Method for Dynamically Reconfigurable FPGA |
-
2017
- 2017-12-26 CN CN201711427893.8A patent/CN108170634B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104603750A (en) * | 2012-08-30 | 2015-05-06 | 微软公司 | Layout and execution of software applications using BPRAM |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108170634A (en) | 2018-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108170634B (en) | A kind of isomerous multi-source data reconstruction transient state reliable treatments method | |
| US9898206B2 (en) | Memory access processing method, apparatus, and system | |
| CN113746893B (en) | An FPGA-based intelligent network card data forwarding method, system and terminal | |
| CN102591964A (en) | Implementation method and device for data reading-writing splitting system | |
| CN104319878B (en) | Chip digital relay protection system | |
| CN102710763B (en) | The method and system of a kind of distributed caching pond, burst and Failure Transfer | |
| CN105302739A (en) | Memory management method and device | |
| CN102123090A (en) | IP (Internet protocol) fragment processing method based on two-level table storage and transport layer information inquiry | |
| CN108197008A (en) | A kind of log collecting method, system, device and computer readable storage medium | |
| CN204425370U (en) | A kind of FC switch supervisory circuit | |
| CN103618620A (en) | Front-end processor system of multi-layer structure | |
| CN105119926A (en) | Multichannel duplex communication method based on Socket connection | |
| CN103139018A (en) | Network card condition monitoring and transmission control protocol (TCP) communication method in dispatching and transformer substation integrated system | |
| CN103812860A (en) | FPGA based high-speed network strategy matching method | |
| CN103488585B (en) | For realizing the controller of configuration information buffer update in reconfigurable system | |
| CN106533621A (en) | Communication method for monitoring permanent magnet synchronous motor in real time based on simplified MODBUS protocol | |
| CN104077343B (en) | A kind of Hash table failure elements delet method | |
| CN103095595B (en) | A kind of network data management method and system based on unidirectional parallel multilinked list | |
| Jin et al. | Optimizing B+-tree for hybrid memory with in-node hotspot cache and eADR awareness | |
| CN108958667A (en) | A kind of method for reading data based on distributed memory system, system and device | |
| CN104636284A (en) | Implementation method and device of a flash storage array | |
| CN111611463A (en) | A Distributed Web Crawler Optimization Method Based on Scrapy-Redis | |
| CN110058885A (en) | A kind of efficient cpu instruction reading method based on RISC_V serial FLASH system architecture | |
| CN114443616B (en) | An FPGA-based parallel heterogeneous database acceleration method and device | |
| CN103886075B (en) | Distributed network perception information stores and inquiry system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181207 Termination date: 20201226 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |