JP6698455B2 - Memory diagnostic device - Google Patents

Description

  The present invention relates to a memory diagnosing device for diagnosing a memory area by using a free time for program execution in a processor-equipped device or the like with limited computing resources.

  In the memory diagnostic device in the conventional processor-equipped device, the memory is not available when the computing resources are available only when the computing resources are available or when the processing load is variable and the computing resources are temporarily available. Takes the approach of making a diagnosis.

JP, 2014-99097, A

  Since the conventional memory diagnostic device has the above features, it cannot be applied when the processor resource of the target processor-equipped device has a large limitation and the fluctuation of the processing load is small (always high load). was there.

  The present invention has been made in order to solve the above problems, and memory for a processor-equipped device or the like in which the calculation resource is largely restricted and the fluctuation of the processing load is small (always high load). It is an object of the present invention to provide a memory diagnostic device capable of diagnosing the above condition.

The memory diagnostic device according to the present invention is
An execution program including a memory for a program used for executing a program, a plurality of diagnostic processing parameters used for diagnosing the memory, and an error correction code for correcting a bit error of the memory,
A control operation execution unit that executes a control operation by referring to the execution program,
A memory diagnosis execution unit that diagnoses the memory based on the diagnosis processing parameter and the error correction code;
Means for detecting the first time the program starts up,
Means for measuring the processing time of the control calculation of the control calculation execution unit;
A means for storing a measured value of the processing time of the control operation performed a certain number of times,
Means for calculating a statistical value related to the processing time from the measured value of the processing time of the certain number of times,
A means capable of automatically calculating the optimum number of region divisions of a plurality of memory partial regions obtained by dividing the memory from statistical values related to processing time;
Equipped with
From the previous SL multiple diagnostic processing parameters, by selecting and using diagnostic process parameters necessary for the execution of the program, as well as applying the error correction code to the memory portion area identifying the diagnostic portion ,
The idle time of the control operation of the program, to the memory portion area identified by sequentially performing a diagnosis of the memory, have rows diagnosis of the entire memory to be used for execution of the program, to detect the initial rise When the means detects the first rising edge, it performs error correction code generation processing for automatically generating an error correction code .

  According to the present invention, the diagnosis target is divided into sufficiently small units that do not affect the control processing for the entire memory, and the diagnosis is executed for the divided memory by using the free time of the control processing. The present invention has an effect that it is possible to mount a memory diagnostic device capable of diagnosing a memory state even in a processor-mounted device or the like in which the limitation of calculation resources is large and the fluctuation of processing load is small.

It is a figure which shows an example of the memory diagnostic device which concerns on Embodiment 1 of this invention. It is a figure which shows the relationship of the area|region division and diagnostic operation of the memory diagnostic device which concerns on Embodiment 1 of this invention. It is a figure which shows the detail of the diagnostic processing parameter of the memory diagnostic device which concerns on Embodiment 1 of this invention. It is a figure which shows the process flow of the memory diagnostics execution part of the memory diagnostic device which concerns on Embodiment 1 of this invention. It is a figure which shows an example of the memory diagnostic device which concerns on Embodiment 2 of this invention. It is a figure for demonstrating operation|movement of the error correction code production|generation part of the memory diagnostic device which concerns on Embodiment 2 of this invention. It is a figure which shows the detail of the diagnostic processing parameter of the memory diagnostic device which concerns on Embodiment 2 of this invention. It is a figure which shows the starting flow of the error correction code production|generation part in the initialization processing of the memory diagnostic device which concerns on Embodiment 2 of this invention. It is a figure which shows an example of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a figure which shows the detail of the diagnostic processing parameter of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a figure which shows the process flow of starting the area division number N calculation part and the error correction code generation part in the initialization processing of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a conceptual diagram which shows the control operation of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a figure which shows the processing flow of the area|region division number N calculation part of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a figure which shows the statistical value calculated by the area|region division number N calculation part of the memory diagnostic device which concerns on Embodiment 3 of this invention. It is a figure which shows the process flow of the area|region division number N calculation part of the memory diagnostic device which concerns on Embodiment 4 of this invention. It is a figure which shows the statistical value calculated by the area|region division number N calculation part of the memory diagnostic device which concerns on Embodiment 4 of this invention.

Embodiment 1.
The first embodiment of the present invention will be described below with reference to FIGS. Here, FIG. 1 is a diagram showing an example of the memory diagnostic device according to the present embodiment, and FIG. 2 is a diagram showing the relationship between the area division and the diagnostic operation of the memory diagnostic device according to the present embodiment. .. Further, FIG. 3 is a diagram showing details of diagnostic processing parameters of the memory diagnostic apparatus according to the present embodiment, and FIG. 4 shows a processing flow of the memory diagnostic execution unit of the memory diagnostic apparatus according to the present embodiment. It is a figure.

  First, FIG. 1 shows an example of the memory diagnostic device according to the present embodiment. The memory diagnostic device 1 is for performing a diagnosis for detecting a bit abnormality in a memory of a program, and includes a control operation execution unit 10 that performs an operation for controlling an execution program, a diagnostic processing parameter 22, and an error correction. The execution program 21 has a memory diagnosis execution unit 11 that executes a diagnosis for detecting a bit abnormality of the memory based on the reference numeral 23. In addition, the arrow in the drawing indicates a reference destination, and the black triangle on the upper right of the rectangle indicates that it has an actual value (the same applies to the following drawings).

Next, the contents of FIG. 2 will be described. In the present embodiment, the execution program 21 is divided into N memory partial areas P1 to PN, respectively. The control cycle U is a time interval in which the control operation is executed. The processing time T of the control operation is the processing time required for the control operation performed by the control calculation execution unit 10 of FIG. The free time V is a period obtained by removing the processing time T of the control operation from the control cycle U, and the diagnostic processing of the memory diagnosis execution unit 11 is executed using this time.

  Here, one memory diagnostic process is performed for one of the memory partial areas. It is possible to diagnose all the areas of the execution program 21 by sequentially performing the processing on each area by the number N of the area divisions of the memory partial area. In this figure, the error correction code 23 is calculated in advance and written in the device before the memory diagnosis of this device, that is, the memory diagnosis device is executed.

Next, the processing operation of the memory diagnosis execution unit for one cycle will be described based on FIGS. 3 and 4.
First, each element of the diagnostic processing parameter 22a shown in FIG. 3 will be described. A indicates the top address of the storage area of the execution program 21 to be diagnosed. B indicates the size of the execution program area to be diagnosed.
Subsequently, C indicates the number N of area divisions of the row program. The area division number N is a sufficiently large value so that the diagnostic process for one partial area can be executed in advance in the free time, that is, assuming that the free time is 1, for the length 1 of the free time. A time less than 1 (especially, a time of about 0.5 when variation is taken into consideration) is set. The value of N is typically set to 1000 or more.
Subsequently, D indicates the start address of the storage area of the error correction code 23. E indicates the length of one error correction code.
Finally, F stores the number of the divided area to be processed next. In F, the first number of the divided area (1 in this description) is stored as an initial value.

Next, the flow of FIG. 4 will be described.
First, in step S1, the execution program partial area to be diagnosed this time is specified using the diagnosis processing parameters A, B, and C. The error correction code is generated by performing calculation on the specified area.
Then, in step S2, the error correction code area corresponding to the current partial area is specified by using the diagnostic processing parameters D, E, and F, and the error correction code is acquired.
Then, in step S3, the error correction codes generated or acquired in step S1 and step S2 are compared.
If the determination results of step S3 do not match, it is determined that an abnormality has occurred and the abnormality processing of step S4 is performed. If the determination results of step S3 match, it can be determined that no garbled error has occurred in the processing target partial area, and the processing of updating the processing target area of steps S5 to S7 is performed.
The update processing of the processing target area from step S5 to step S7 determines whether the diagnostic processing is completed up to the end of the partial area in step S5, and if YES, in order to execute the diagnostic processing again from the leading partial area, The processing target divided area counter F is returned to the initial value (here, 1). If NO, the processing target divided area counter F is incremented (incremented by 1).

The content of the abnormality processing in step S4 varies depending on the reliability required for the memory diagnostic device, the presence/absence of an abnormality notification interface (I/F) with the outside, and the like.
For example, when a correctable error occurs, error correction and log registration are performed to continue the process. When an uncorrectable error occurs, the LED is turned on to notify the user, It is possible to perform processing of dropping to a failure mode, registering an error log, and notifying other devices connected via a network of an abnormality.

By sequentially performing the processing operation of the memory diagnosis execution unit for one cycle described above, it becomes possible to finally diagnose the area of the entire memory. As a method of realizing the processing to be sequentially executed, a program that manages the execution of the program (a function generally called a scheduler)
You can enroll in.

  In the present embodiment, the time required for diagnosing the entire execution program to be diagnosed is “control cycle U×number of area divisions N”, which is the MAX time required for detection after occurrence of an abnormality. Become. In order to effectively use this embodiment, it is necessary for the designer to judge that the MAX time is appropriate in view of the reliability required for the device.

  In the first embodiment, the program memory to be diagnosed is divided into sufficiently small units that do not affect the control processing, that is, if the entire memory is divided and the processing time of the actual control operation is 1000, the program memory is divided. The processing time per memory is set to be about 1 to 10 so that the control processing idle time (about 0.2 to 0.4 time when the total processing time of control operation is 1) Since the memory diagnosis is performed by using, the memory state is diagnosed even in a processor-equipped device, etc., in which the limitation of the calculation resource is large and the fluctuation of the processing load is small, in other words, the load is always high. It is possible to mount a memory diagnostic device capable of performing the above.

Embodiment 2.
The second embodiment of the present invention will be described below with reference to FIGS. Here, FIG. 5 is an example of the memory diagnostic device according to the present embodiment, and FIG. 6 is a diagram for explaining the operation of the error correction code generation unit of the memory diagnostic device according to the present embodiment. .. 7 is a diagram showing details of the diagnostic processing parameters of the memory diagnostic device according to the present embodiment, and FIG. 8 is an error correction code in the initialization process of the memory diagnostic device according to the embodiment of the present invention. It is a figure which shows the starting flow of a production|generation part.

  First, FIG. 5 shows an addition of the error correction code generation unit 12 to the constituent elements of the memory diagnostic device shown in FIG. Based on FIG. 1, an error correction code generation unit 12 (an arrow in the drawing indicates a reference destination or a writing destination) that generates an error correction code 23 based on the execution program 21 and the diagnostic processing parameter 22 is added. ing. Further, FIG. 6 shows an operation relationship among the error correction code generation unit 12, the execution program 21, the error correction code generation unit 12, and the error correction code 23.

  Next, an outline of the operation of the error correction code generation unit 12 will be described with reference to FIG. The error correction code generation unit 12 calculates error correction codes for all areas P1 to PN, which are N memory partial areas of the execution program 21, and calculates the codes from the code Q1 that is the error correction code corresponding to each area. Write QN, respectively.

  Next, the activation process of the error correction code generation unit will be described with reference to FIGS. 7 and 8. The diagnostic processing parameter 22b in FIG. 7 is obtained by adding an error correction code addition flag G to the diagnostic processing parameter 22a in FIG. A magic number (a numerical value written in the program used as an identifier) is written in the error correction code addition flag when the execution program is written in the device.

Next, the startup flow of FIG. 8 will be described. First, in step S11, the error correction code addition flag is referred to and it is determined whether or not it matches the magic number. If it matches with the magic number, it is determined that the device is being activated for the first time (step S12), and then the error correction code generation unit is executed in step S13. When the error correction code is added by the error correction code generation unit, a value other than the magic number is written and cleared in the error correction code addition flag in the next step S14.
Then, regarding the processing of the error correction code generation unit 12, each area is specified by using the diagnostic processing parameter 22 and the error correction code generation processing is executed, as in the first embodiment.

  In the first embodiment described above, it was necessary to write the error correction code into the device in advance by using, for example, batch processing or a dedicated personal computer S/W, but in the present embodiment, the first startup of the device is performed. Since error correction codes are automatically added at times, there is no possibility of making mistakes that may occur in human work.

Embodiment 3.
Hereinafter, a third embodiment of the present invention will be described with reference to FIGS. Here, FIG. 9 is an example of the memory diagnostic device according to the third embodiment. 10 is a diagram showing the details of the diagnostic processing parameters of the memory diagnostic device according to the present embodiment, and FIG. 11 is a diagram showing the number N of divided regions in the initialization process of the memory diagnostic device according to the present embodiment. It is a figure which shows the process flow of starting the part and the error correction code generation part. Further, FIG. 12 is a conceptual diagram showing the control operation of the memory diagnostic device according to the present embodiment, and FIG. 13 shows a processing flow of the area division number N calculation unit of the memory diagnostic device according to the present embodiment. FIG. 14 is a diagram showing statistical values calculated by the area division number N calculation unit of the memory diagnostic device according to the present embodiment.

  First, in the memory diagnostic device of FIG. 9, in addition to the components shown in the memory diagnostic device according to the second embodiment of FIG. 5, a region division number N calculation unit 13 and measurement data 24 of control processing are added. The area division number N calculation unit 13 executes the control calculation execution unit 10, measures the processing time, writes the measured processing time in the measurement data 24 of the control processing, and based on the measurement data of the control processing, the area division number N Is calculated and written in the diagnostic processing parameter 22.

  Next, the activation process of the area division number N calculation unit will be described with reference to FIGS. FIG. 10 shows a diagnostic processing parameter 22c in which the area division number N maximum size H, the area division number N calculation flag I, and the control cycle measurement number M are added to FIG. As the area division number N maximum size H, the maximum value of the area division number predetermined by the designer is set from the time until abnormality detection. As a typical value of this H, a value of about 4000 is set. A magic number is written in the area division number N calculation flag I when the execution program is written in the device.

  Next, FIG. 11 is based on FIG. 8 and is obtained by adding steps S21 to S23, which are processes relating to the calculation of the number N of region divisions. Since it is necessary to simulate the control operation in the area division number N calculation unit, the activation process of FIG. 11 needs to be performed at the end of the initialization process.

  Details of FIG. 11 will be described below. First, in step S21, the area division number N calculation flag is referred to, and it is determined whether or not it matches the magic number. If it matches the magic number, it is determined that the device is first started, and the area division number N calculation unit is executed in step S22. When the error correction code is added by the area division number N calculation processing, a value other than the magic number is written and cleared in the area division number N calculation flag in step S23. Since steps S24 to S26 are the same as steps S11 to S13 of FIG. 8, detailed description thereof will be omitted here.

Next, details of the processing of the area division number N calculation unit will be described based on FIGS. 10, 12, 13, and 14. FIG. 13 shows a processing flow of the area division number N calculation unit. In step S31 to step S33 of this figure, the control cycle measurement number M times is looped, the control operation execution unit measures the processing time of the control operation corresponding to the number of control cycle measurement times M, and the control processing is executed. The measurement data 24 is written and stored. FIG. 12 is a diagram showing details of the processing contents of steps S31 to S33.
As described with reference to FIG. 2, each of the K control cycles is composed of the control operation and the idle time, and the processing time of the control operation of each control cycle is T1, T2,..., TK. Also,
The processing time is measured for each of the processing times T1, T2,..., TK and stored as the measured value 1, the measured value 2,. Here, K=M.

  Then, as a process of step S34, a statistical value is calculated from the measurement data 24 of the control process. The calculated statistical values are the average value 101 and the standard deviation 102, as shown in FIG. Succeedingly, in a step S35, an error correction code generation process is executed for the entire execution program 21, and a processing time is measured. In step S36, an estimated value is obtained for the maximum value of the processing time of the control operation by considering the variation by calculating "average value 101+(standard deviation 102×5)". Next, an estimated value of the minimum free time is obtained by "control cycle U-temporary estimated value (for maximum value of processing time of control operation)". Further, the number of area divisions is calculated by “measured value of step S35×1.1/minimum available time (result is rounded up)”. Finally, the smallest power of 2 among the numbers larger than the obtained region division number is set as the region division number N calculated in step S36.

  Subsequently, in step S37, it is confirmed that the calculated area division number N is equal to or smaller than the area division number N maximum size H. If the maximum size is equal to or less than H, N is determined to be an appropriate value and written in the diagnostic processing parameter 22 in the processing of step S38. If the size is equal to or larger than the maximum size H, abnormal processing is performed in step S39. An example of the content of the abnormality processing is to leave a log and drop to the failure mode.

  In the above-described second embodiment, the area division number N had to be designed and determined in advance, but the area division number N is automatically calculated by implementing the device of FIGS. Therefore, it is possible to reduce the design cost and obtain an economically excellent memory diagnostic device. In particular, a great effect can be obtained when the memory diagnostic device has a large repertoire.

Fourth Embodiment
Hereinafter, a fourth embodiment of the present invention will be described with reference to FIGS. Here, FIG. 15 is a diagram showing a processing flow of the region division number N calculation unit of the memory diagnostic device according to the present embodiment, and FIG. 16 is a region division number N of the memory diagnostic device according to the present embodiment. It is a figure which shows the statistical value calculated by a calculation part.

  First, FIG. 15 is based on the process flow of FIG. 13 and additionally includes the determination process of step S40. 16 shows the contents of the statistical value calculated in step S34, and the maximum value 103 is added as compared with FIG. Then, the determination process using the maximum value 103 is performed in step S40. If the determination result is NO, the process branches to the abnormality process.

  Next, the details of the determination process using the maximum value 103 in step S40 will be described. The specific processing procedure is as follows. First, the minimum free time is calculated by "control cycle U-maximum value 103", and then this value and "one part calculated by the measured value of step S35/area division number N". When the processing time required for the diagnostic processing of the area is compared and “the processing time required for the diagnostic processing of one partial area>the minimum free time” is satisfied, the process branches to NO in step S40 to perform the abnormal processing, Becomes

Here, the details of the determination process using the maximum value 103 in step S40 described above will be further described with reference to specific numerical examples.
For example, assuming that the control cycle U is 10 ms and the processing time T of the control operation is 20 cycles as one set, the specific value is “(19 times 2 ms continues)→8 ms”→“(19 times 2 ms continues)→8 ms Consider a control operation with a characteristic that fluctuates such as “→→→→ ((2 ms continues 19 times)→8 ms”). In this case, the average value of the processing time T of the control operation is 2.3, the standard deviation is 1.34, and the maximum value is 8 (the minimum free time is 10-8=2) (unit of each numerical value). Is ms). In such a case, when the processing time of one partial area of the area division number N calculated according to the third embodiment is 3 ms, "processing time of one partial area (=3)>minimum free time"(=2)", and the processing time of one partial area exceeds the minimum free time, which affects the control operation, so it is determined to be abnormal (step S40 branches to NO). ..

  In addition, in the third embodiment, it is assumed that the processing time of the control operation follows statistical variations, and if this assumption is broken, a proper value of the area division number N cannot be set. For example, when the control operation having the characteristic that the processing time is greatly increased once every several cycles, the number of area divisions N is erroneously set to be small, and the memory diagnosis processing is performed at a cycle with a long processing time. It is conceivable that the free time of will be insufficient and will affect the control operation. By checking the validity of the area division number N automatically calculated using the maximum value of the measured values, the above-mentioned problem can be prevented and reliability is improved.

  It should be noted that, in the present invention, the respective embodiments can be freely combined, or the respective embodiments can be appropriately modified or omitted within the scope of the invention.

DESCRIPTION OF SYMBOLS 1 memory diagnostic device, 10 control calculation execution unit, 11 memory diagnostic execution unit, 12 error correction code generation unit, 13 calculation unit, 21 execution program, 22, 22a, 22b, 22c diagnostic processing parameter, 23 error correction code, 24 control Processing measurement data, 101 average value, 102 standard deviation, 103 maximum value, F processing target divided area counter, H maximum size, I calculation flag, M control cycle measurement count, N area division count, T processing time, U control cycle , V free time, P1 memory partial area, Q1 error correction code

Claims (5)

An execution program including a memory for a program used for executing a program, a plurality of diagnostic processing parameters used for diagnosing the memory, and an error correction code for correcting a bit error of the memory,
A control operation execution unit that executes a control operation by referring to the execution program,
A memory diagnosis execution unit that diagnoses the memory based on the diagnosis processing parameter and the error correction code;
Means for detecting the first time the program starts up,
Means for measuring the processing time of the control calculation of the control calculation execution unit;
A means for storing a measured value of the processing time of the control operation performed a certain number of times,
Means for calculating a statistical value related to the processing time from the measured value of the processing time of the certain number of times,
A means capable of automatically calculating the optimum number of area divisions of a plurality of memory partial areas obtained by dividing the memory from statistical values related to processing time;
Equipped with
From the plurality of diagnostic processing parameters, by selecting and using the diagnostic processing parameters necessary for the execution of the program, while giving the error correction code to the memory partial area that specifies the diagnostic location,
Means for diagnosing the entire memory used for executing the program by sequentially diagnosing the memory with respect to the specified memory partial area in the idle time of the control operation of the program, and detecting the first rising edge. When the first rising edge is detected, an error correction code generation process for automatically generating an error correction code is performed,
A memory diagnostic device characterized by the above. An execution program including a memory for a program used for executing a program, a plurality of diagnostic processing parameters used for diagnosing the memory, and an error correction code for correcting a bit error of the memory,
A control operation execution unit that executes a control operation by referring to the execution program,
A memory diagnosis execution unit that diagnoses the memory based on the diagnosis processing parameter and the error correction code;
Means for detecting the first time the program starts up ,
Means for measuring the processing time of the control calculation of the control calculation execution unit;
A means for storing a measured value of the processing time of the control operation performed a certain number of times,
Means for calculating a statistical value related to the processing time from the measured value of the processing time of the certain number of times,
A means capable of automatically calculating the optimum number of area divisions of a plurality of memory partial areas obtained by dividing the memory from statistical values related to processing time;
Equipped with
The processing time of the diagnosis of the memory per one divided memory partial area is 1/100 to 1/1000 of the processing time of the control calculation of the program,
When the first rising edge is detected, an error correction code generation process for automatically generating an error correction code is performed, and a diagnostic processing parameter necessary for executing the program is selected from the plurality of diagnostic processing parameters and used. By doing so, while adding the error correction code to the memory partial area that has identified the diagnostic location,
A memory diagnostic device , wherein the entire memory used for executing the program is diagnosed by sequentially diagnosing the memory with respect to the specified memory partial area in the idle time of the control operation of the program. . The first error correction code is generated for the specified memory partial area, the error correction code area corresponding to the specified memory partial area is specified, and the second error correction code is acquired. The memory diagnostic device according to claim 1, wherein a first error correction code is compared with the second error correction code, and when the results do not match, it is determined that an abnormality has occurred. Means for measuring a processing time of the control operation of the prior SL control operation performing unit,
A means for storing a measured value of the processing time of the control operation performed a certain number of times,
Means for calculating a statistical value related to the processing time from the measured value of the processing time of the predetermined number of times
Means for automatically calculating the optimum number of area divisions of the memory partial area from a statistical value related to processing time;
Memory diagnostic apparatus according to 請 Motomeko 3 further comprising a. In the process of automatically calculating the optimum number of divided areas of the memory partial area,
Having a means for detecting a case where the fluctuation of the processing time is larger than a preset value, and when detecting a case where the fluctuation of the processing time is larger than a preset value, another device connected through the network. 5. The memory diagnostic device according to claim 1 , wherein the memory diagnostic device is notified to the user.

Images