JPH0371226A - Data processor - Google Patents

Abstract

PURPOSE:To speed up various arithmetic processing by selectively inverting all bits in accordance with the ascending/descending specification at every field to obtain a key to be arithmetic object and executing the specified operation based upon the key. CONSTITUTION:In the case of extracting key parts from respective records of an objective file in a main storage 4 based upon an instruction outputted from a CPU 1, plural fields of one record are extracted in accordance with a specified priority order, all the bits are selectively inverted in accordance with the ascending/descending order at every field to obtain the key to be computed and the specified operation is executed by a means 5 based upon the key. Consequently, respective operations based upon a multikey can be collectively executed and the arithmetic processing of various data bases based upon the multikey can be rapidly and efficiently executed.

Description

DETAILED DESCRIPTION OF THE INVENTION [Object of the Invention] (Industrial Application Field) The present invention relates to a data processing device having arithmetic processing functions including sorting and relational operations in a relational database.

(Prior Art) Conventionally, there is a "selection device" disclosed in Japanese Patent Application No. 62-24751 as a data processing mechanism for databases. This "selection device" is placed in the input/output channel or disk control device, and directly receives data read from a magnetic disk device used as a large-capacity data file, and selects data that satisfies conditions. It has developed an efficient data retrieval mechanism using on-the-fly processing.

However, the above-mentioned device still has the following problems. That is, in the above device configuration,
When only a simple selection process is targeted, even if the target files are distributed across multiple magnetic disk drives, the desired selection result can be obtained by summing up the selection result information of each magnetic disk drive. be able to. However, sorting or relational database (RDB)
When the target is complex calculations such as relational calculations in This method cannot be put to practical use because it requires arithmetic processing of each piece of target data again, resulting in complicated processing and a corresponding drop in processing performance.

Furthermore, in the conventional device configuration described above, the magnetic disk device is directly connected to the selection device, and a means is adopted in which data read from the magnetic disk device is directly stored in a buffer within the selection device. Therefore, the extraction processing speed of some keys and the disk read processing speed interact with each other, and due to this, there are restrictions on file format, number of extraction keys (number of keys for multi-key), etc. There was also the problem that processing performance, processing speed, etc. were restricted.

In order to solve the above-mentioned problems, the applicant invented a "database processing mechanism" as disclosed in Japanese Patent Application No. 327542/1983.

This database processing mechanism performs predetermined arithmetic processing on a system bus on a single or multiple external memories that store files to be processed, and on databases that include sorting and relational operations in relational databases. The relational processing unit is connected to a CPU that controls the entire system, and a main memory that is accessed under the control of the CPU. A means for extracting a part of keys according to a specified key from a record of the target file stored in the first area on the main memory according to the instructions, and a means for extracting a part of keys according to the specified key, and for each of the extracted keys, position information of that key on the main memory. a means for adding the key and identifier as an identifier and performing an operation on each extraction key in accordance with the operation instruction of the CPU using the key and identifier pair as manual data; and a means for sequentially extracting the identifier from the data string obtained as a result of the operation. and means for outputting to the second area on the main memory.

By using a data processing mechanism with such a configuration in a data processing system that processes databases, it is possible to easily control advanced data processing that targets complex operations such as sorting or relational operations in RDB. can be executed efficiently.

(Problem to be Solved by the Invention) In the above-mentioned data processing device, when a multi-key operation is performed, if multiple keys have different ascending order and descending order specifications, The calculations must be performed in separate calculation modes for each, and therefore the calculation processing takes a lot of time, which poses a problem in terms of processing performance.

The present invention has been made in view of the above circumstances, and it is an object of the present invention to provide a data processing device that can process multi-key operations at high speed even if the ascending order and descending order specifications for each key are different. With the goal.

[Configuration of the Invention (Means and Actions for Solving the Problems) The present invention is based on CP
Based on instructions from U, when extracting a portion of keys from each record of the target file, multiple fields on one record are extracted according to the specified priority order, and all bits are selectively extracted according to the ascending/descending order specification for each field. It has a structure that includes a means to invert the key to be the target of the operation and execute the specified operation on that key.This allows multi-key operations to be executed at once, and allows for the use of various multi-key databases. Arithmetic processing can be executed quickly and efficiently.

That is, the present invention provides a control unit and an arithmetic unit that perform predetermined arithmetic processing on an external storage storing files to be processed and a database that includes sorting and relational operations in a relational database. The system has a system configuration in which an arithmetic processing unit having a section, a CPU that controls the entire system, and a main memory that is accessed under the control of the CPU are respectively connected on a system bus,
The CPU includes means for importing a file to be processed stored in the external storage into the main memory, and a means for sending information and calculation instructions regarding the file to the processing unit, extracts a single field or multiple fields with a specified key from the record of the target file stored in the main memory according to the information regarding the file and the calculation command, and performs the calculation of the extracted field by the calculation processing unit. means for converting the converted data into data that can be processed by the processing unit; means for inverting all bits of the converted data according to instructions from the control unit of the processing unit; and a means for executing an operation in accordance with the above operation instruction, and when extracting a portion of keys from each record of the target file, multiple fields on one record are extracted according to a specified priority order, and each field is arranged in ascending/descending order. It is configured to selectively invert all bits according to the specification to obtain the key to be operated on, and execute the specified operation on that key.This allows each key of the multi-key to be assigned in ascending/descending order. Even if there is a specification, the calculation can be executed at once, and multi-key calculation processing for the database can be executed quickly and efficiently.

(Example) The present invention will be described in detail below with reference to the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention. In order to simplify the explanation, here, a configuration is exemplified in which only one human output channel for controlling a magnetic disk device is provided on the system bus.

In the figure, l is the CPU that controls the entire system, and here the input/output channel 2 connected to the system bus (5-BLIS) 6, the relational processing unit 5, etc. are placed under control, and the sorting Or, when processing data for relational calculations in RDH, input/output channel 2
The magnetic disk devices 3, 3 . ... has a control function to read the target file and write it to the first area on the main memory 4, and also has a control function to read the target file from the main memory 4 and write it to the first area on the main memory 4. A relational operation is performed on file information (including information indicating priority order and ascending/descending order specification information for each field), operation instructions for the file, and instructions for a second area on the main memory 4 in which the operation results are stored. It has a control function to send data to the processing device 5. Furthermore, according to the data string (result identifier string) of the operation result written to the second area on the main memory 4 by the relational operation processing device 5, the target file in the first area on the main memory 4 is transferred to the second area on the main memory 4. It has a processing means for sorting the calculation results in the order of the area.

2 is the human output channel (I
OC), which controls access to the input/output devices under the control of the CPUI, and here a plurality of magnetic disk drives 3, 3... are under the access control.

3.3. ... are magnetic disk devices (DISK) placed under the control of the human output channel 2, and data groups of various file structures constituting the database are stored.

4 is a main memory (MEN) connected to the system bus B, which includes a first area for storing files to be processed, and information regarding the files to be processed (file format, A second area is provided for storing various pieces of information such as information such as information such as information such as information such as file information, record length, etc.), calculation instructions, and calculation results.

5 is a relational processing unit (
DBE), and the processing target stored in the first area of the main memory 4 according to the information regarding the processing target file stored in the second area of the main memory 4 (i.e., the file information specified by the CPUI) Extracts one or more specified fields from the records of the file in order of priority, and
The data is converted according to the input format, and all bits of a specific designated field (for example, a descending designated field) are inverted according to the ascending/descending order specification for each field. A processing function that adds the head position information (main memory address) on the main memory 4 as an identifier, and uses the key and identifier pair as input data to perform calculations on the key value of the same data according to the calculation instructions specified by the CPUI. It has a processing function to execute, and a processing function to sequentially extract identifiers from a data string obtained as a result of the calculation and store them in a second area on the main memory 4, and the control unit 51. It consists of components such as a calculation unit 52 and a buffer memory (work buffer) 53.

Among these components, the control unit 51 extracts one or more specified fields in priority order from the records of the processing target file stored in the first area on the main memory 4 according to the file information specified by the CPU 1. Then, it is converted into a data type that can be processed by /1′1 arithmetic in the a calculation unit 52 (a data type that can perform binary absolute value comparison) in accordance with the manual format (for example, binary comparison calculation format) of the calculation unit 52, and further All bits of a specific designated field (for example, a descending designated field) are inverted according to the ascending/descending order designation for each field, and this is used as one key, and the head position information ( It has a control function that adds a main memory address (main memory address) to the key as an identifier and sends it to the arithmetic unit 52, as well as a control function that stores output data received from the arithmetic unit 52 in a second area on the main memory 4. .

The calculation unit 52 has a buffer memory (work buffer) 53
Using the key and identifier pair received from the control unit 51 as input data, calculations are performed on the key values of the same data according to the calculation instructions. At this time, in multi-key calculations, even if the ascending order and descending order specifications for each key are different, the control unit 51 sends binary data, for example, binary data in which all bits of only the field designated in descending order are inverted, as manual data to the arithmetic unit. 52, the calculation unit 52 only needs to perform calculation processing in ascending order, regardless of whether the fields to be calculated are specified in ascending or descending order. Multi-key operations can be processed at high speed by treating the keys as one key. Furthermore, the calculation unit 52 sequentially extracts identifiers from the data string on the buffer memory 53 obtained as a result of the above calculation, and sends these to the control unit 51 as output data. This output data is stored in the second area on the main memory 4 via the control unit 5L.

511 to 515 each constitute a component of the control unit 51, and 511 is a microprocessor (MPU) that controls the entire control unit 51, as shown in FIG.
It has key extraction processing functions including data conversion and data inversion control. 512 is a memory (C8) in which a control program for the microprocessor 511 is stored. 513 is a DMA (
Direct Memory Access) controller (DMAC). 514 transfers the data received from this DMA controller 513 to the microprocessor 511.
This is a data conversion unit that converts the data into a data type (for example, a data type that allows binary absolute value comparison) according to the instructions given to the calculation unit 52 in accordance with the manual input format. 515 performs all-bit inversion processing only for a specific specified field (for example, a descending order specified field) according to the ascending/descending order specification of each field extracted from the record, and then outputs the inverted field data or the field data that is passed through as is (data The data converted by the conversion unit 514) is sent to the calculation unit 5.
This is a data inverting unit that sends data to 2.

FIG. 2 shows a microprocessor 511 in the control section 51.
3 is a flowchart showing a key extraction process flow executed under the control of.

In FIG. 2, Sl is the step of finding the head position of a record from the file to be processed placed on the main entry taJ, and the head memory address of the record in the target file of t&4 is found. Step s2 is a step of finding the start position of a field, and the start storage address of the field in the record found in step S1 is found in the order according to the file information instructed by the CPUI. S3 is a step in which instructions are issued to the DMA controller 513, data converter 514, and data inverter 515. The data such as the position and length of the field found in step S2 is set in the DMA controller 513, and the data type is set to data. The data is set in the converter 514, and the ascending/descending order designation is set in the data inverter 515. S4 is a step of detecting the last field of the target record, and it is determined whether the field found in step S2 is the last field of the plurality of fields specified by the file information from the CPUI. S5 is main memory 4
This is the step of detecting the last record of the file to be processed above, and it is determined whether the record found in step S1 is the last record of the file to be processed stored in the main memory 4. .

The operation of an embodiment of the present invention will now be described with reference to FIGS. 1 and 2.

When the CPU receives processing targets and calculation instructions such as sorting (ascending/descending) or relational calculations from a human-powered mechanism on the terminal side (not shown) via the system bus 6, the CPU receives the processing targets via the system bus 6 and the human output channel 2. A file is read from the magnetic disk devices 3, 3°, . . . and written to a predetermined first area on the main memory 4. At this time, a plurality of human output channels 2, 2 . ... are connected, the file to be processed is connected to a plurality of input/output channels 2, 2, . . . connected to the system bus 6. The magnetic disk devices 3, 3 . . . ..., the CPUI selectively specifies the input/output channel according to the file structure of the file to be processed, issues an access instruction, and reads the file under the control of human output channel 2. The data of the target file is stored in the main memory 4.

Once the target file is read into the first area of the main memory 4 as described above, the CPU File information including ascending/descending field designations, etc.), computation instructions for the file, and second area designation information on the main memory 4 that stores the computation results (result identifier string) are sent to the relational computation processing device 5. Then, the relational arithmetic processing device 5 is activated.

When the relational arithmetic processing device 5 receives the above information from the CPUI, it sets up the operation mode of the arithmetic unit 51 according to the instructions, and then performs sorting or RD according to the instructions.
Execute the relational calculation process in B.

That is, the control unit 51 in the relational arithmetic processing device 5
According to the file information sent from
From each record of the file to be processed stored in the area, extract multiple (or single) specified fields in the specified order, and use the data of the multiple fields sorted according to the specified order as one key information for each key. ,
The location information (main memory address) of the key in the main memory 4 is added as an identifier, and data is generated in which a part of the key and the identifier are paired. At this time, the data in each field constituting the key is converted into a data type that can be processed by the calculation unit 52, and all bits of the field are selectively inverted according to the ascending/descending order specification for each field. is set as one piece of key information, paired with the above-mentioned identifier, and sent to the calculation unit 52.

That is, as shown in the flowchart of FIG. 2, the control unit 5 extracts a plurality of fields according to the file information from the record of the file to be processed stored in the first area of the main memory 4 in the designated priority order. Then, a key for a plurality of field columns is obtained (steps SL-S5 in FIG. 2). Furthermore,
After adding the head position information (main memory address) in the main memory 4 of the record having the key to the key as an identifier, the input format of the calculation unit 52 (for example, binary comparison calculation format) is applied to the key. The arithmetic unit 52 converts the data into a data type that can be processed (a data type that allows binary absolute value comparison), and further inverts all bits of a specific designated field (for example, a descending designated field) according to the ascending/descending order designation for each field. Then, this is set as one key (key field), paired with the above-mentioned identifier, and sent to the calculation unit 52.

The key extraction processing operation in the control section 5t at this time will be explained with reference to FIG.

The microprocessor 511 of the control unit 51 detects the first record storage address (record start address) from the processing target file on the main memory 4 according to the file information instructed by the CPU 1, and extracts unextracted records from that record according to the specified priority order. Field position (field start address)
is detected, the field position information, that is, the field start address is set in the DMA controller 513, the designated data type is set in the data converter 514, and the ascending order/descending order designation for each extracted field is data inverted. section 515 and activates the DMA controller 513 (steps 81 to S3 in FIG. 2).

The DMA controller 513 is a microprocessor 51
When the field start address of the unextracted highest priority field is received from 1, the main memory 4 is accessed according to this specified address, the data of the unextracted highest priority field is read from the main memory 4, and the data is transferred to the data converter 514. do. Upon receiving the field data read out and transferred from the main memory 4 under the access control of the DMA controller 513, the data conversion unit 514 converts this data into a data type (for example, binary data) that matches the manual format of the calculation unit 52. It is sent to the reversing section 515. The data inversion unit 515 selectively performs all-bit inversion processing on the field data received from the data conversion unit 514 according to the ascending/descending order designation of the field (for example, when the field is in descending order, all bit inversion processing is performed on the data of that field) Then, this is set as one key (key field), paired with the above-mentioned identifier, and sent to the calculation unit 52.

On the other hand, when the microprocessor 511 detects the field start address of the unextracted highest priority field, it detects the start address of the next priority unextracted field. This field address search process is executed for all records of the file to be processed (Step S in Figure 2).
4. S5. Sl-S3).

In this way, for each record of the file to be processed, key extraction processing for multiple fields (multi-key), data type conversion processing, and selective field data inversion processing according to ascending/descending order specification are performed. etc. are executed. During this key (multi-key) extraction process, a flag is added to the last data of the last designated field to indicate that it is the end of the key.

When the calculation unit 52 receives the input data generated by the control unit 5I that uses multiple fields as one key (multi-key data with matching data types), the calculation unit 52 calculates the input data from the CPUI under the control of the control unit 5i. The calculation according to the calculation instruction is executed for each extraction key.

At this time, in a multi-key operation, even if the ascending order and descending order specifications for each key are different, the control section 51 sends binary data, for example, in which all bits of only the field designated in descending order are inverted, as input data to the operation section. 52, the calculation unit 52 arranges the fields to be calculated in ascending order/
No matter which order is specified in descending order, it is only necessary to perform calculations in ascending order. Therefore, data in multiple fields that make up a multi-key can be regarded as one key, and calculations using that multi-key can be performed at once at high speed. Can be processed.

Further, the calculation section 52 sequentially extracts identifiers from the data string obtained as a result of the above calculation to obtain output data (an identifier string after the calculation result), and sends the output data to the control section 51.

The control unit 51 stores the output data received from the calculation unit 52 in a prespecified second area on the main memory 4, and performs calculations on the identified money extracted from the target file on the main memory 4. When it is finished, it notifies the CPUI.

When the CPUI receives the above calculation completion notification from the control unit 51 of the relational calculation processing unit 5, it converts each record of the target file in the first area of the main memory 4 into the calculation results (result identification thousands) in the second area. column), create a new file according to the specified calculation result, and then edit that file (
output file) information is output to the magnetic disk device 3 via the human output channel 2 and stored therein.

In the above data processing, if the file to be processed exceeds the work area of the main memory 4, the file is processed in units of work size and finally merged to obtain the processing result.

Further, in the above embodiment, upon receiving the above calculation completion notification from the control unit 51 of the relational calculation processing unit 5, the CPUI converts each record of the target file in the first area of the main memory 4 into the second Sort the calculation results (result identifier column) in the area, create a new file according to the specified calculation result, and create the reorganized file (output file).
Although information has been output to and stored in the magnetic disk device 3 via the input/output channel 2, by providing this processing function to the relational arithmetic processing unit 5, the CPU load can be reduced.

With the configuration of the embodiment described above, advanced data processing for complex operations such as sorting or relational operations in RDB can be efficiently executed with simple control. Also, when extracting the key part from each record of the target file based on instructions from the CPUI, multiple fields on one record are extracted according to the priority order specified by the CPUI, and each field is selected according to the ascending/descending order specification. As a result, we inverted all bits and used them as part of one key to perform the specified operation and obtain the result information, so specifying ascending/descending order for each field by multi-key is a big brother. Multi-key database calculations can be performed quickly and efficiently.

[Effects of the Invention] As detailed above, according to the data processing device of the present invention,
an arithmetic processing device having a control unit and an arithmetic unit that executes predetermined arithmetic processing on an external storage that stores files to be processed, and a database that includes sorting and relational operations in a relational database; The system configuration consists of a CPU that controls the entire system and a main memory that is accessed under the control of the CPU, each connected to a system bus.
The arithmetic processing device has means for importing a processing target file stored in the external storage into the main memory, and a means for sending information and calculation instructions regarding the file to the arithmetic processing device. A single field or multiple fields with a specified key are extracted from the record of the target file stored in the main memory according to information and calculation instructions, and the extracted fields can be processed by the calculation unit of the processing unit. means for converting the converted data into data; means for inverting all bits of the converted data according to instructions from the control unit of the arithmetic processing device; and means for following the arithmetic commands for the converted data or the inverted data. and a means for executing an operation, when extracting a portion of keys from each record of the target file, extracting multiple fields in one record according to the specified priority order, and selectively according to the ascending/descending order specification for each field. By inverting all bits to obtain the key to be operated on, and performing the specified operation on that key, it is possible to perform multi-key operations even if the ascending/descending order specification is different for each key. , these calculations can be executed at once, and various multi-key calculations for databases can be executed quickly and efficiently.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing the configuration of an embodiment of the present invention, and FIG. 2 is a flowchart showing the key extraction process flow in the above embodiment. 1-CPU, 2--input/output channel (IOC), 3゜3,...magnetic disk device (DISK), 4...
Main machine memory (MEM), 5...Relational processing unit (DB)
B), 6... System bus (S-Bus), 51...control unit,
52... Arithmetic unit, 53... Buffer memory (work buffer) 511... Microprocessor (MPU)
, 512...Control memo! J (C8), 513-D
MA:7>) O-La (DHAC), 514...
-Data converter, 515...data inverter.

Claims (1)

[Claims] On the system bus, it has a control unit and a calculation unit that execute predetermined calculation processing on an external storage that stores files to be processed, and a database that includes sorting and relational operations in a relational database. A system configuration in which an arithmetic processing unit, a CPU that controls the entire system, and a main memory that is accessed under the control of the CPU are connected, and the CPU is configured to process objects stored in the external memory. It has a means for importing a file into the main memory, and a means for sending information regarding the file and a calculation instruction to the arithmetic processing device, and the arithmetic processing device stores the file in the main memory in accordance with the information regarding the file and the operation instruction. Extract single or multiple fields with the specified key from the stored record of the target file,
means for converting the extracted field into data that can be processed by the calculation unit of the calculation processing unit; and a means for converting the extracted field into data that can be processed by the calculation unit of the calculation processing unit; A data processing device comprising: means for inverting; and means for executing an operation according to the operation instruction on the converted data or the inverted data.