JP2011039858A - Data processing device, data processing method, program analysis processing device, and program analysis processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To shorten a processing time of a reuse section by reuse of an execution result. <P>SOLUTION: A history memory 430 holds an input value of a function and its execution result for each section identification information of the function. An input value setting instruction address table 520 holds an address of an input value setting instruction executed before a function call instruction for each of section identification information of the function. An address determination unit 510, when an instruction address from a program counter 350 matches an instruction address in the input value setting instruction address table 520, outputs section identification information corresponding to the instruction address to an execution data holding unit 440. At the same time, the address determination unit 510 makes the execution data holding unit 440 hold an input value output from an execution unit 330. An execution history retrieval unit 410 retrieves an execution result in the history memory 430 based on the section identification information in the execution data holding unit 440 and the input value. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a data processing apparatus, and in particular, a data processing apparatus that reuses an execution result of an instruction section that is executed a plurality of times, a processing method thereof, a data conversion processing apparatus that converts a program corresponding to the data processing apparatus, and It relates to the processing method.

  2. Description of the Related Art Conventionally, research and development relating to high-speed computing processing technology has been actively performed in microprocessors such as a CPU (Central Processing Unit). As a technique for speeding up this arithmetic processing, a technique called value reuse technique has been devised. For example, a data processing apparatus in which this value reuse technique is applied to an instruction section of a loop has been proposed (for example, see Patent Document 1).

  In this value reuse technique, among the instruction sections that are part of the program, if the input value in the instruction section is the same, the input value in the instruction section that has the same execution result and the output value that is the execution result are Register in the reuse table in association. And when the same instruction interval is executed again, if the same input value is registered in the reuse table, it was executed in the past by outputting the output value corresponding to the input value from the reuse table. Reuse the execution result of the instruction section. As described above, an instruction interval in which an execution result of an instruction interval executed in the past among the instruction intervals executed a plurality of times can be reused is referred to as a reuse interval.

Japanese Patent No. 3855076 (FIG. 1)

  In the above-described conventional technology, when the process in the reuse section is executed again, if the input value of the reuse section is registered in the reuse table, the process in the reuse section can be omitted. Therefore, it is possible to reduce the execution time required for executing the reuse section. However, in this case, it is determined whether or not the input value of the reuse section is registered in the reuse table until the instruction that refers to the input value is executed after the execution of the call instruction of the reuse section. I can't. Thus, since the reuse table cannot be searched until the input value is used, the period that can be shortened by reusing the execution result is limited.

  The present invention has been made in view of such a situation, and an object thereof is to shorten the processing time of a reuse section by reusing an execution result.

  The present invention has been made to solve the above-mentioned problems, and a first aspect of the present invention is to execute a process based on an instruction sequence including a plurality of instruction sections and a call instruction for calling the instruction sections. An input value setting instruction address table that holds an input value setting instruction address that is an address of an input value setting instruction for setting an input value of the instruction section before the execution is executed for each section identification information of the instruction section; A history memory that associates an input value and an execution result in the instruction section for each section identification information and holds them as an execution history, and an instruction group from the input value setting instruction to the call instruction specified by the input value setting instruction address And the section identification information corresponding to the input value setting command address, and the input value output from the execution unit based on the input value setting command The execution history search unit that searches for the execution result in the execution history and the execution result is extracted by the execution history search unit when the call instruction specified by the input value setting instruction address is executed. In some cases, the data processing apparatus includes an execution result output unit that outputs the extracted execution result to the execution unit, and a processing method thereof. Thus, before the execution of the instruction section, the input value based on the input value setting instruction specified by the input value setting instruction address in the input value setting instruction address table and the section identification information associated with the input value setting instruction address When the execution result is extracted by the execution history search unit when the call instruction specified by the input value setting instruction address is executed, the execution result is extracted. This brings about the effect that the execution unit outputs.

  In the first aspect, the input value setting instruction address table is configured to set the input value setting instruction for setting an input value of a reuse section which is an instruction section executed a plurality of times among the plurality of instruction sections. The input value setting instruction address of each of the reuse sections is held for each section identification information, and the execution history search unit is configured to execute the execution unit based on the input value setting instruction in the instruction group in the reuse section. The execution result in the reuse section is searched using the input value output from the section and the section identification information corresponding to the input value setting instruction address, and the execution result output section uses the input value setting instruction address. When the calling instruction of the specified reuse section is executed, the execution history search unit extracts the execution result of the reuse section in the execution history. The execution result of the extracted may be output to the execution unit if it is. As a result, the input value acquired by the input value setting instruction specified by the input value setting instruction address and the input value setting instruction before execution of the calling instruction of the reuse section that is an instruction section that is executed a plurality of times When the execution result in the history memory is searched using the section identification information corresponding to the address, and the calling instruction of the reuse section specified by the input value setting instruction address is executed, the execution result is obtained by the execution history search unit. When extracted, the execution result is output to the execution unit.

  In the first aspect, the input value setting instruction address corresponding to the input value referred to in the instruction section called by the calling instruction among the input values set based on the input value setting instruction; You may make it further comprise the input value setting command address output part which outputs the said area identification information to the said input value setting command address table. As a result, the input value setting instruction address output unit sets the input value referenced by the instruction section of the calling instruction among the input values set by the input value setting instruction before the calling instruction. The input value setting command address and the section identification information are output. In this case, the input value setting instruction address output unit outputs the input value setting instruction address of the first input value setting instruction among the input value setting instructions corresponding to the plurality of input values referred to in the instruction section. And the start address of the command section, which is the section identification information, may be output. As a result, the input value setting instruction address of the earliest input value setting instruction and its instruction among the input value setting instructions for setting a plurality of input values referenced in the instruction section of the function by the input value setting instruction address output unit This produces the effect of outputting the start address of the section.

  In the first aspect, the input value setting command address table includes the input value setting command of the earliest input value setting command among the input value setting commands for setting a plurality of input values in the command section. An instruction address may be held for each section identification information. Thereby, the input value setting command address table holds the input value setting command address of the input value setting command executed first among the plurality of input value setting commands in the command interval for each section identification information. Bring.

  In the first aspect, the execution unit may determine the instruction section specified by the input value setting instruction address when the execution history search unit does not extract the execution result in the execution history from the history memory. The execution history search unit corresponds to the input value output from the execution unit based on the input value setting command, the execution result executed by the execution unit, and the input value setting command address. The section identification information may be held in the history memory. Thereby, when the execution result is not extracted from the history memory in the execution history search unit, the execution unit executes the process in the instruction section specified by the input value setting instruction address, and the execution history search unit sets the input value. The history value memory stores the input value acquired based on the instruction, the execution result of the process in the instruction section executed by the execution unit, and the section identification information corresponding to the input value setting instruction address in the input value setting instruction address table It brings the effect of letting.

  In the first aspect, the input value setting instruction address table includes the input value setting instruction address of the input value setting instruction of the function that is the instruction section for each head address of the function that is the section identification information. The history memory associates an input value and an execution result in the function for each head address of the function and holds the execution history as the execution history, and the execution history search unit stores the input value in the instruction group. The execution result is searched using the input value of the function output from the execution unit based on the setting instruction and the start address of the function corresponding to the input value setting instruction address. When the call instruction of the function specified by the input value setting instruction address is executed, the execution history search unit The execution result of the extracted may be output to the execution unit when the execution result is extracted. Thus, before the execution of the function call instruction, the input value set based on the input value setting instruction specified by the input value setting instruction address, the section identification information associated with the input value setting instruction address, and When the execution result is extracted by the execution history search unit when the call instruction specified by the input value setting instruction address is executed, the execution result of the function in the history memory is searched using The execution result is output to the execution unit.

  Further, the second aspect of the present invention provides a degree of reuse indicating the degree to which the input values for each execution of processing in an instruction section executed a plurality of times in the program match each other based on the usage state of the instruction section. An input value setting instruction for setting an input value in a reuse section extracted based on the reuse degree among the plurality of instruction sections, and a reuse degree generation unit that generates each instruction section A program analysis processing apparatus and a processing method therefor including a reuse section information generation unit that generates reuse section information in which an address and section identification information for identifying the reuse section are associated with each other. Thereby, based on the degree of reuse indicating the degree to which the execution results of the instruction sections executed a plurality of times match each other, the reuse section is extracted from the plurality of instruction sections, and the reuse section information generation unit There is an effect of generating reuse section information in which the input value setting instruction address of the input value setting instruction in the reuse section is associated with the section identification information of the reuse section.

  According to the present invention, it is possible to achieve an excellent effect that the processing time of the reuse section due to the reuse of the execution result can be shortened.

It is a block diagram which shows the example of 1 structure of the data processor in the 1st Embodiment of this invention. It is a block diagram which shows the example of 1 structure of the data processing part 300 and the execution result reuse process part 400 in the 1st Embodiment of this invention. It is a conceptual diagram which shows an example of the data structure of the history memory 430 in the 1st Embodiment of this invention. It is a conceptual diagram which shows the registration method of the area identification information and execution history in execution of the 1st function by the data processor 100 in the 1st Embodiment of this invention. It is a conceptual diagram which shows an example of the method regarding the execution result reuse process by the data processor 100 in the 1st Embodiment of this invention. It is a conceptual diagram which shows the example by which the processing time of a function is shortened by execution result reuse processing. It is a conceptual diagram which shows the registration method of the execution history in execution of the function after the 2nd by the data processor 100 in the 1st Embodiment of this invention. It is a flowchart which shows an example of the process sequence of the execution result reuse method by the data processor 100 in the 1st Embodiment of this invention. It is a block diagram which shows the function structural example of the program analysis processing apparatus in the 2nd Embodiment of this invention. It is a flowchart which shows an example of the process sequence of the program analysis processing method of the program analysis processing apparatus 600 in the 2nd Embodiment of this invention. It is a block diagram which shows the example of 1 structure of the data processor 100 in the 3rd Embodiment of this invention. It is a conceptual diagram which shows the example of a registration of the input value setting command address and area identification information with respect to the input value setting command address table 820 by the data processor 100 in the 3rd Embodiment of this invention. It is a flowchart which shows an example of the process sequence of the execution result reuse method by the data processor 100 in the 3rd Embodiment of this invention. It is a flowchart which shows the example of a process sequence of the execution history search process (step S960) by the data processor 100 in the 3rd Embodiment of this invention. It is a block diagram which shows the example of 1 structure of the integrated circuit in the case of providing the historical data memory | storage part outside the data processing apparatus 100 in the 4th Embodiment of this invention. It is a flowchart which shows the process sequence of the historical data transfer method by the data processor 100 in the 4th Embodiment of this invention.

Hereinafter, modes for carrying out the present invention (hereinafter referred to as embodiments) will be described. The description will be made in the following order.
1. First Embodiment (Data Processing Control: Example of Preregistration of Input Value Setting Instruction Address)
2. Second Embodiment (Program Analysis Processing: Extraction Example of Input Value Setting Instruction Address)
3. Third Embodiment (Data Processing Control: Input Value Setting Instruction Address Registration Example During Program Execution)
4). Fourth Embodiment (History Data Transfer Control: Example of Reading History Data from Outside the Data Processing Device to the History Memory for Each Program Execution)

<1. First Embodiment>
[Configuration example of data processing device]
FIG. 1 is a block diagram showing an example of the configuration of the data processing apparatus according to the first embodiment of the present invention. Here, a data processing device 100, a bus 120, and a main storage unit 130 constituting an integrated circuit are shown. This integrated circuit performs processing in the data processing apparatus 100 in accordance with a sequence of instructions from the main storage unit 130 read via the bus 120.

  The data processing apparatus 100 includes a primary cache 200, a data processing unit 300, an execution result reuse processing unit 400, and a search start instruction address management unit 500. The data processing device 100 is an example of a data processing device described in the claims.

  The primary cache 200 is a memory for reducing a delay time caused by processing when reading or writing an instruction and data from the main storage unit 130 via the bus 120. The primary cache 200 is realized by, for example, a DRAM (Dynamic Random Access Memory).

  The primary cache 200 includes an instruction cache 210 and a data cache 220. The instruction cache 210 temporarily holds past instructions read from the main storage unit 130. The instruction cache 210 outputs the held instruction to the data processing unit 300 via the command line 219 in accordance with a request from the data processing unit 300.

  When the instruction cache 210 holds the instruction requested from the data processing unit 300, the instruction cache 210 outputs the requested instruction to the data processing unit 300 among the plurality of held instructions. On the other hand, when the instruction requested from the data processing unit 300 is not held, the instruction cache 210 holds the instruction read from the main storage unit 130 by the data processing unit 300.

  The data cache 220 temporarily holds past data read from the main storage unit 130. The data cache 220 outputs the held data to the data processing unit 300 via the data line 229 in accordance with a request from the data processing unit 300.

  When the data requested by the data processing unit 300 is retained, the data cache 220 outputs the requested data to the data processing unit 300 among the plurality of retained data. On the other hand, when the data requested from the data processing unit 300 is not held, the data cache 220 holds the data read from the main storage unit 130 by the data processing unit 300. Further, when data for writing back to the main storage unit 130 is supplied from the data processing unit 300, the data cache 220 holds the data.

  The data processing unit 300 executes processing based on an instruction read from the main storage unit 130. For example, the data processing unit 300 reads an instruction from the main storage unit 130 via the instruction cache 210 and reads data stored in the main storage unit 130 via the data cache 220 according to the read instruction. . For example, the data processing unit 300 executes arithmetic processing based on the arithmetic instruction using the read data.

  In addition, for example, when executing processing in an instruction section of a function, the data processing unit 300 executes arithmetic processing of the function using an input value of an argument in the function from the data cache 220, and performs the calculation. The execution result that is the result of the processing is output to the data cache 220. At this time, the data processing unit 300 outputs the input value and the execution result in the function to the execution result reuse processing unit 400. The data processing unit 300 is realized by, for example, a processor core.

  When the input value of the instruction section executed in the past matches the input value of the instruction section executed again, the execution result reuse processing unit 400 displays the execution result of the instruction section executed in the past. The execution result reuse process to be reused is executed. Here, an instruction section in which an execution result of an instruction section executed in the past among the instruction sections executed a plurality of times can be reused is referred to as a reuse section. In other words, the reuse section refers to an instruction section that has the same execution result if the input values in the instruction section are the same among instruction sections that are executed a plurality of times.

  The execution result reuse processing unit 400 holds an input value and an execution result in a reuse section that is executed a plurality of times as an execution history. Further, the execution result reuse processing unit 400, when the input value of the reuse section to be executed again and the input value in the held execution history are the same, the execution result in the held execution history Is output to the data processing unit 300. At the same time, the execution result reuse processing unit 400 notifies the data processing unit 300 of an instruction to omit (skip) the processing in the reuse section.

  For example, when the input value of the argument of the function that is the reuse section is the same as the input value in the held execution history, the execution result reuse processing unit 400 uses the The execution result is output to the data processing unit 300. At the same time, the execution result reuse processing unit 400 notifies the data processing unit 300 of an instruction for skipping the processing in the function.

  The search start instruction address management unit 500 manages an instruction address serving as a reference for starting execution history search in the execution result reuse processing unit 400. The search start instruction address management unit 500 indicates a timing for starting comparison between the input value in the execution history held in the execution result reuse processing unit 400 and the input value set for the execution of the reuse section. The instruction address is managed for each reuse section as a reference. The search start instruction address management unit 500 instructs the execution result reuse processing unit 400 to start execution history search based on the managed instruction address.

  The bus 120 performs communication between the data processing apparatus 100 and the main storage unit 130. The bus 120 transfers a program stored in the main storage unit 130 to the data processing apparatus 100. In addition, the bus 120 transfers data output from the data processing apparatus 100 to the main storage unit 130.

  The main storage unit 130 stores a program for causing the data processing apparatus 100 to execute processing. Here, it is assumed that this program is a program generated based on the definition of ABI (Application Binary Interface). This program is generated based on, for example, SPARC (Scalable Processor Architecture) _ABI. In such a program, the data processing apparatus 100 can specify the location where the input value and the execution result in the function are stored, so that the reuse of the execution result can be realized.

[Configuration Example of Data Processing Unit 300 and Execution Result Reuse Processing Unit 400]
FIG. 2 is a block diagram illustrating a configuration example of the data processing unit 300 and the execution result reuse processing unit 400 according to the first embodiment of the present invention.

  The data processing unit 300 includes a fetch unit 310, an instruction decoder 320, an execution unit 330, and a register file 340. The execution unit 330 includes a load unit 331, an input selection unit 332, an arithmetic circuit 333, a store unit 334, and a program counter 350.

  The execution result reuse processing unit 400 includes an execution history search unit 410, an execution result output unit 420, and a history memory 430. Further, the search start command address management unit 500 includes an address determination unit 510 and an input value setting command address table 520.

  The fetch unit 310 reads an instruction held in the instruction cache 210 or an instruction stored in the main storage unit 130 via the instruction line 219. The fetch unit 310 reads an instruction from the instruction cache 210 in accordance with the instruction address output from the program counter 350.

  For example, the fetch unit 310 reads an input value setting instruction for setting an input value of an argument in the function before a call instruction for calling a function that is a reuse section. After the input value setting instruction is read, the fetch unit 310 reads the function call instruction.

  The fetch unit 310 supplies the read instruction to the instruction decoder 320. When the function omission signal for reusing the execution result in the history memory 430 is supplied from the execution history search unit 410, the fetch unit 310, for example, sends an instruction for setting the execution result to the instruction decoder. 320 is supplied.

  The instruction decoder 320 decodes (decodes) the instruction supplied from the fetch unit 310 and controls the execution unit 330, the register file 340, and the address determination unit 510 based on the decoded content.

  When the instruction value is supplied from the fetch unit 310, the instruction decoder 320 sends an input value setting signal to the address determination unit 510 so that the execution data holding unit 440 holds the input value of the argument of the function. Supply. In this case, the instruction decoder 320 determines whether or not the instruction supplied from the fetch unit 310 is an input value setting instruction for setting an input value of an argument in the function. The instruction decoder 320 determines whether or not the instruction from the fetch unit 310 is an input value setting instruction based on, for example, ABI regulations. Here, an example of determination based on the ABI rules of MIPS (Microprocessor without Interlocked Pipeline Stages) will be briefly described.

  According to the MIPS rules, for example, when all input values of arguments are integers and the number of arguments is 4 or less, the input values are stored in registers 4 to 7 in the register file 340. Further, when there are five or more arguments, the input values of the fifth or more arguments are stacked in the stack area in the main storage unit 130. Specifically, the input value of the fifth or more argument is input to the stack area of the main storage unit 130 corresponding to a value obtained by adding 16 or more to the stack point value stored in the register 29 of the register file 340. Stacked.

  Therefore, for example, when the transfer destination register indicated by the load word instruction (lw) is the registers 4 to 7, the instruction decoder 320 determines that the instruction is an input value setting instruction. Further, the instruction decoder 320 has the transfer destination register indicated by the store word instruction (sw) as the register 29 when the number of arguments is five or more and all the arguments are integers, and Since the offset value is “16” or more, it is determined as an input value setting command.

  In this way, the instruction decoder 320 determines whether or not the instruction is an input value setting instruction based on the data storage destination indicated by the instruction supplied from the fetch unit 310. If it is determined that the instruction is an input value setting instruction, the instruction decoder 320 sends an input value setting signal to the execution data holding unit 440 to hold the data output from the input selection unit 332 as an input value of an argument. This is supplied to the address determination unit 510.

  For example, when receiving an input value setting command for setting an input value of a function read from the main storage unit 130, the instruction decoder 320 stores the input value read from the load unit 331 in a register file. It controls to store in 340. At the same time, the instruction decoder 320 supplies an input value setting signal to the address determination unit 510.

  For example, when the instruction decoder 320 receives an input value setting instruction for setting the data stored in the register file 340 as an input value of a function, the instruction decoder 320 stores the data in one register in the register file 340. Transfer the input value to another register. At the same time, the instruction decoder 320 supplies an input value setting signal to the address determination unit 510.

  When the instruction decoder 320 receives a call instruction for calling a function after the input value setting instruction, the instruction decoder 320 supplies a function call signal indicating that a jump to the start address of the function is made to the address determination unit 510. That is, when the instruction decoder 320 receives a function call instruction, the instruction decoder 320 supplies a function call signal to the address determination unit 510 in order to notify the timing for executing the execution result reuse processing in the history memory 430. .

  In addition, the instruction decoder 320 refers to an input value for referring to an input value that is an argument of a function according to the storage location of the data indicated by the instruction from the fetch unit 310 based on, for example, MIPS. Determine whether the command. When the instruction decoder 320 receives an input value reference instruction, the instruction decoder 320 supplies an input value reference signal to the address determination unit 510. When the instruction decoder 320 receives a function return instruction, the instruction decoder 320 supplies a function return signal to the address determination unit 510.

  Further, the instruction decoder 320 determines whether or not the instruction is an execution result setting instruction for setting the execution result by the execution of the function based on the storage location indicated by the instruction from the fetch unit 310 based on the MIPS regulations. To do. When the instruction decoder 320 receives the execution result setting instruction, the instruction decoder 320 supplies an execution result setting signal to the address determination unit 510 in order to hold the execution data holding unit 440.

  When the instruction decoder 320 receives a function return instruction, the instruction decoder 320 supplies a function return signal to the address determination unit 510. The instruction decoder 320 sets the value of the program counter 350 based on the instruction supplied from the fetch unit 310.

  The execution unit 330 executes processing in accordance with control from the instruction decoder 320. The execution unit 330 executes processing based on an instruction sequence including a plurality of instruction sections. That is, the execution unit 330 executes a process based on an instruction sequence including a reuse section that is an instruction section that is executed a plurality of times. The execution unit 330 outputs the input value and execution result of the function, which is a reuse section, to the register file 340 or the main storage unit 130 and also supplies the execution data holding unit 440.

  The execution unit 330 sets, for example, the input value of the function in the register file 340 or the main storage unit 130 before the function call instruction by executing the input value setting instruction, and outputs it to the execution data holding unit 440. To do. For example, the execution unit 330 refers to the input value set by the input value setting command by executing the input value reference command, and outputs the referenced input value to the execution data holding unit 440. For example, the execution unit 330 outputs the numeric value of the argument, the type of the argument, and the storage location of the argument to the execution data holding unit 440 as input values. The execution unit 330 is an example of an execution unit described in the claims.

  The load unit 331 reads data from the main storage unit 130 or the data cache 220 in accordance with control from the instruction decoder 320 and supplies the read data to the input selection unit 332. For example, the load unit 331 reads an input value of an argument in a function from the main storage unit 130 or the data cache 220 according to control from the instruction decoder 320 and supplies the read input value to the input selection unit 332. .

  The input selection unit 332 selects one of the data output from the execution result output unit 420, the arithmetic circuit 333, the register file 340, and the execution result output unit 420 according to control from the instruction decoder 320. is there.

  The input selection unit 332 outputs the selected data to the register file 340 and the execution data holding unit 440. That is, the input selection unit 332 stores one of the outputs of the execution result output unit 420, the arithmetic circuit 333, the register file 340, and the execution result output unit 420 according to the control of the instruction decoder 320. Output to the unit 440.

  For example, when a load word instruction is supplied to the instruction decoder 320 as an input value setting instruction, the input selection unit 332 converts the data from the load unit 331 into the register file 340 and the execution data according to the control of the instruction decoder 320. The data is output to the holding unit 440.

  Further, for example, when a move command is supplied as an input value setting command, the input selection unit 332 transfers data in the register file 340 to the register file 340 and the execution data holding unit 440 under the control of the command decoder 320. Output.

  In addition, when an arithmetic instruction for executing arithmetic processing is supplied to the instruction decoder 320, the input selection unit 332 uses the arithmetic result output from the arithmetic circuit 333 as an execution result under the control of the instruction decoder 320. Output to the register file 340. Further, when the execution result is extracted by the execution history search unit 410, the input selection unit 332 outputs the execution result output from the execution result output unit 420 to the register file 340 according to the control from the instruction decoder 320. To do.

  The arithmetic circuit 333 executes arithmetic processing in accordance with control from the instruction decoder 320. For example, when an arithmetic instruction for executing arithmetic processing such as multiplication, division or sum of products is supplied to the instruction decoder 320, the arithmetic circuit 333 is stored in the register file 340 according to the control of the instruction decoder 320. The arithmetic processing is executed using the obtained data. In addition, the arithmetic circuit 333 stores the calculation result of the calculation processing as an execution result in the register file 340 via the input selection unit 332.

  The store unit 334 is for writing back the data stored in the register file 340 or the execution result output from the execution result output unit 420 to the main storage unit 130 according to the control from the instruction decoder 320. When a store word instruction for writing data back to the main storage unit 130 is supplied to the instruction decoder 320, the store unit 334 sends data to be written back to the data line 229 according to control from the instruction decoder 320. To the data cache 220.

  In addition, when the execution result is extracted from the history memory 430 by the execution history search unit 410, the store unit 334 displays the execution result output from the execution result output unit 420 via the data line 229. 130 and data cache 220 are written back.

  The register file 340 stores data output from the execution unit 330. The register file 340 is composed of a plurality of registers, for example, 32 registers of registers 0 to 31. The register file 340 stores the data output from the execution unit 330 in one register among a plurality of registers in accordance with control from the instruction decoder 320.

  The register file 340 also stores the execution result stored in one of the plurality of registers in the execution unit 330 or through the execution unit 330 according to control from the instruction decoder 320, for example. Output to.

  The program counter 350 is set with a count value under the control of the instruction decoder 320. The program counter 350, for example, increases the count value by one every time one instruction is executed under the control of the instruction decoder 320. The program counter 350 is set with the start address of the function stored in the register file 340 when a function call instruction is executed under the control of the instruction decoder 320. The program counter 350 outputs the count value to the address determination unit 510 as an instruction address indicating the memory address of the main storage unit 130.

  The address determination unit 510 causes the execution history search unit 410 and the execution data holding unit 440 to search the execution history in the history memory 430 based on the input value setting command address registered in the input value setting command address table 520. It is something to control. That is, the address determination unit 510 starts searching for an execution history when the instruction address output from the program counter 350 matches the input value setting instruction address held in the input value setting instruction address table 520. It is.

  The address determination unit 510 determines whether the instruction address output from the program counter 350 matches the input value setting instruction address registered in the input value setting instruction address table 520. If both instruction addresses match, the address determination unit 510 executes the input value output from the execution unit 330 based on the input value setting command specified by the input value setting command address. 440 is held.

  At the same time, the address determination unit 510 causes the execution data holding unit 440 to hold section identification information associated with the matched input value setting command address in the input value setting command address table 520. The section identification information here is identification information for identifying a plurality of reuse sections from each other. As the section identification information, for example, the start address of a function that is a reuse section may be used.

  Further, when both instruction addresses coincide with each other, when the input value setting signal is supplied from the instruction decoder 320 until the function call signal is supplied, the address determination unit 510 outputs from the execution unit 330. The execution data holding unit 440 holds the input value. That is, the address determination unit 510 outputs the output from the execution unit 330 as the input value of the argument in the function based on the input value setting signal supplied from the instruction decoder 320 until the function call signal is supplied. The holding unit 440 holds it.

  Further, when a function call signal is supplied from the instruction decoder 320, the address determination unit 510 instructs the execution history search unit 410 to reuse the execution result in the history memory 430. Further, the address determination unit 510 causes the execution data holding unit 440 to hold the output from the execution unit 330 as a function execution result based on the execution result setting signal supplied from the instruction decoder 320.

  In addition, the address determination unit 510 executes, based on the function return signal supplied from the instruction decoder 320, to newly register the section identification information, the input value, and the execution result in the execution data holding unit 440 in the history memory 430. A registration instruction is issued to the history search unit 410.

  The input value setting instruction address table 520 is an input that is an address of an input value setting instruction for setting an input value in a function for each section identification information for identifying a function that is a reuse section executed a plurality of times. It holds the value setting instruction address. The address here indicates a memory address in which the input value setting command is stored in the main storage unit 130.

  Here, in the input value setting instruction address table 520, for example, data relating to a reuse section extracted by analyzing a program stored in the main storage unit 130 by pre-execution of a compiler device or a program is held. Assuming that That is, the input value setting instruction address table 520 holds an input setting instruction address of a function whose execution result is highly reused and section identification information for identifying the function in association with each other.

  The input value setting command address table 520 is, for example, the input value setting command address of the input value setting command that first sets the input value among the input value setting commands for setting the input value in the function for each section identification information. Hold on. That is, the input value setting instruction address table 520 holds the earliest input value setting instruction address in the reuse section for each section identification information of the reuse section. In this way, the capacity of the input value setting command address table 520 can be reduced by holding only the earliest input value setting command.

  Further, the input value setting instruction address table 520 outputs the held data to the address determination unit 510. If the function that is a reuse section has a plurality of arguments in the input value setting instruction address table 520, a plurality of input value setting instruction addresses may be held for each section identification information. The input value setting instruction address table 520 is an example of the input value setting instruction address table described in the claims.

  Note that the input value setting command address table 520 may further hold the priority when deleting the execution history for each section identification information. In this case, the execution history search unit 410 registers the priority from the address determination unit 510 in the history memory 430. Then, when the capacity of the history memory 430 exceeds a certain condition, the execution history search unit 410 deletes the execution history in the history memory 430 based on the priority stored in the history memory 430.

  The execution data holding unit 440 holds the section identification information from the address determination unit 510, the input value in the function from the execution unit 330, and the execution result in accordance with the instruction from the address determination unit 510. The execution data holding unit 440 outputs the held section identification information, the input value in the function, and the execution result to the execution history search unit 410.

  The execution history search unit 410 searches the execution history in the history memory 430 based on the identification information output from the execution data holding unit 440 and the input value of the function. The execution history search unit 410 includes, in the history memory 430, the section identification information and the input stored in the execution data storage unit 440 among the input values in the reuse section stored for each section identification information and the execution history as the execution result. The execution result in the same execution history as the value is extracted.

  When the execution result is extracted from the history memory 430, the execution history search unit 410 outputs the execution result to the execution result output unit 420 when receiving an instruction for the reuse process from the address determination unit 510. At the same time, the execution history search unit 410 supplies information related to the storage location in the extracted execution result to the fetch unit 310 as a function omission signal for omitting the function processing.

  On the other hand, when the execution result is not extracted from the history memory 430, the execution history search unit 410 does not output the function omission signal to the fetch unit 310 when an instruction for the reuse process is received from the address determination unit 510. Then, after the execution result newly generated by the execution of the function in the execution unit 330 is held in the execution data holding unit 440, the execution history search unit 410 outputs the output from the execution data holding unit 440 to the history memory 430. sign up.

  That is, the execution history search unit 410 causes the history memory 430 to hold the section identification information, the input value, and the execution result held in the execution data holding unit 440 based on the registration instruction from the address determination unit 510.

  If the execution result is extracted from the history memory 430 by the execution history search unit 410, the execution result output unit 420 stores the execution result in the register file 340 or the store unit 334 via the input selection unit 332. Output. The execution result output unit 420 outputs the data in the execution result to the store unit 334 or the input selection unit 332 according to the storage location of the data in the execution result from the history memory 430. The execution result output unit 420 is an example of an execution result output unit described in the claims.

  The history memory 430 stores, as execution history, the input value and the execution result in the function identified by the section identification information for each section identification information. The history memory 430 is realized by, for example, a content addressable memory (CAM). In this example, the history memory 430 starts searching for an execution history associated with the section identification information when section identification information that is a search key for searching for an execution result is input from the execution history search unit 410. To do.

  The history memory 430 is associated with the input value in the history memory 430 when the input values sequentially supplied from the execution history search unit 410 and the input values held in the history memory 430 all match. The execution result is output to the execution history search unit 410. That is, the execution history search unit 410 extracts the execution result from the history memory 430 by detecting from the history memory 430 the same execution history as the section identification information and the input value input from the execution history search unit 410.

  The history memory 430 realized by this associative memory holds, for example, a pattern of input values in the execution history in a tree structure. The history memory 430 is an example of a history memory described in the claims.

  Thus, by providing the address determination unit 510 and the input value setting instruction address table 520, the earliest input value setting instruction in the reuse section can be specified. An execution history search at 430 can be performed. Next, an example of a data structure in the history memory 430 will be described below with reference to the drawings.

[Data structure example of history memory 430]
FIG. 3 is a conceptual diagram showing an example of the data structure of the history memory 430 in the first embodiment of the present invention. Here, a configuration is shown in which the history memory 430 holds a plurality of execution histories in one section identification information in a tree structure among execution histories held for each section identification information. In this example, it is assumed that a function has n arguments and returns an output as an execution result to m storage destinations. Here, the function address that is the start address of the function is used as section identification information.

  In this example, the function route 460 in the tree structure, the first argument nodes 461 and 462, the nth argument nodes 471 to 474, the first output nodes 481 to 484, and the mth output nodes 491 to 494 are displayed. Is shown.

  In the function route 460, a function address that is section identification information and a pointer that points to the first argument node 461 are shown.

  The first and nth argument nodes 461, 462, and 471 to 474 include input data indicating argument values as input values of arguments in the execution history held in the history memory 430, the types of the arguments, The type indicating the storage location of the argument is shown. The storage location here refers to the register number of the register file 340 or the memory address of the main storage unit 130.

  Furthermore, the first and nth argument nodes 461, 462, and 471 to 474 show a right pointer that points to the argument node in the next argument when the input values to be compared match each other. On the other hand, the first and nth argument nodes 461, 462, and 471 to 474 show a lower pointer that points to another argument node in the same argument when the input values to be compared do not match. The first and mth output nodes 481 to 484 and 491 to 494 are connected to the nth argument nodes 471 to 474, respectively.

  In the first and m-th output nodes 481 to 484 and 491 to 494, output data indicating execution result values as execution results in the execution history held in the history memory 430 and storage locations of the execution results are stored. The type to be shown and the type of the execution result are shown. Further, the first output nodes 481 to 484 show a right pointer indicating the output node in the next output. The first and m-th output nodes 481 to 484 and 491 to 494 constitute a linked list. The right pointers of the m-th output nodes 491 to 494 indicate a null indicating the end of the output node.

  In such a tree structure, when a function address that matches the function address indicated in the function route 460 is input from the execution history search unit 410, the first argument node 461 indicated by the pointer of the function route 460 is used. Input value comparison processing is executed. Here, the input value comparison process is to compare the input data, type, and type indicated by the first argument node 461 with the input value from the execution history search unit 410.

  At this time, for example, when the input value indicated by the first argument node 461 matches the input value from the execution history search unit 410, the input is indicated by the right pointer of the first argument node 461. Input value comparison processing is executed at the next argument node. On the other hand, when the input value indicated by the first argument node 461 and the input value from the execution history search unit 410 do not match, the first pointer indicated by the lower pointer of the first argument node 461 is used. In the argument node 462, input value comparison processing is executed.

  In this way, the argument node pointed to by the right or lower pointer is selected based on the comparison result of the comparison process at each argument node, and the input value comparison process is sequentially executed at the selected argument node. If the input value indicated by the nth argument node 471 and the input value from the execution history search unit 410 match each other, the first output node 481 is set by the right pointer of the nth argument node 471. Is pointed to. As a result, the execution results indicating the output data, type and type held in the first output node 481 are sequentially output to the execution history search unit 410 from the execution result held in the mth output node 491 to the execution result. Is done.

  In this way, by configuring the history memory 430 with a tree structure for each section identification information, it is not necessary to hold the input values of the same argument redundantly, so that the storage area of the history memory 430 can be saved. Further, by dividing the data structure for each section identification information, it is possible to suppress a decrease in search speed. Next, as a registration method for the history memory 430, an example of registration processing for the history memory 430 in the first execution of a function that is a reuse section will be described below with reference to the drawings.

[Registration example for the history memory 430 by the first execution of the reuse section]
FIG. 4 is a conceptual diagram showing a method of registering section identification information and execution history in the first function execution by the data processing apparatus 100 according to the first embodiment of the present invention. FIG. 4A is a diagram illustrating an example of the data format of the input value setting instruction address table 520. The input value setting instruction address table 520 shows the correspondence between the earliest input value setting instruction address 521 in the function and the function address 522 which is section identification information for identifying the function.

  FIG. 4B shows a process in which a function having two arguments is called by a call instruction (call) in the upper routine and then returned to the upper routine by a return instruction (return) in a lower routine that is an instruction section of the function. It is a conceptual diagram which shows an example. Here, an input value A setting 321 and an input value B setting 322 in the upper routine, an input value A reference 323, an input value B reference 324, and an execution result C setting 325 in the lower routine are shown. Here, time passes from the left to the right.

  The input value A setting 321 and the input value B setting 322 indicate the timing at which the input value A and the input value B in the function that is a reuse section are set based on two input value setting commands. Here, the input value A is set based on the input value A setting command corresponding to the input value A setting command address. The input value B is set based on the input value B setting command corresponding to the input value B setting command address. In this way, the input value of the argument of the function is set by the input value setting instruction before the function call instruction (call), as described in FIG. 1, the program stored in the main storage unit 130. This is because is generated based on the ABI rules.

  The input value A reference 323 and the input value B reference 324 indicate the timing at which the input value of the function is referred to by executing the input value reference instruction in the processing of the function by the lower level routine. Here, the input value A and the input value B set by the input value A setting command and the input value B setting command are referred to based on the two input value reference commands, respectively. That is, in the function processing, the numerical value of the argument stored in the register in the register file 340 in which the input value A and the input value B are set is used by executing the input value reference instruction.

  The execution result C setting 325 indicates the timing at which the execution result C generated by the function processing is set in the main storage unit 130 or the register file 340. Here, the execution result C is set based on the execution result setting command.

  FIG. 4C is a conceptual diagram illustrating an example of a data format in the history memory 430. Here, the correspondence relationship between the function address 431 that is the section identification information of the function and the execution history search data 432 is shown. The execution history search data 432 is search data constituted by the tree structure shown in FIG. 3 and includes information associated with input values and execution results in the execution history.

  In such a case, in the input value A setting 321, it is assumed that the instruction address output from the program counter 350 by the address determination unit 510 matches the “input value A setting instruction address” in the input value setting instruction address table 520. Determined.

  As a result, the section identification information (function address 1) corresponding to the matched input value setting instruction address (input value A setting instruction address) is input to the history memory 430. That is, the section determination information (function address 1) is held in the execution data holding unit 440 by the address determination unit 510, and the held “function address 1” is input to the history memory 430 by the execution history search unit 410. .

  At this time, since the section identification information that matches the section identification information (function address 1) from the address determination unit 510 is not held in the history memory 430, the section identification information (function address 1) is registered in the history memory 430. Is done.

  Thereafter, the input value A and the input value B set by the input value setting command and the execution result C set by the execution result setting command are registered in the history memory 430 in association with the section identification information (function address 1). Is done. That is, the input value A and the input value B are held in the execution data holding unit 440 by the address determination unit 510 based on the input value setting signal from the instruction decoder 320 by execution of the input setting command. Thereafter, the execution result C is held in the execution data holding unit 440 based on the execution result setting signal from the instruction decoder 320 by execution of the execution result setting instruction.

  Then, based on the function return signal from the instruction decoder 320 based on the return instruction (return), the address determination unit 510 instructs the execution history search unit 410 to register the execution history. As a result, the execution history search unit 410 registers the data (input value A, input value B, and execution result C) in the execution data holding unit 440 in the history memory 430.

  Thus, by providing the input value setting instruction address table 520, only the execution history of the function corresponding to the input value setting instruction address held in the input value setting instruction address table 520 can be registered in the history memory 430. . As a result, by registering the input value setting instruction address of the reuse section in advance, only the execution history with a high possibility that the execution result is reused can be held in the history memory 430. For this reason, the capacity of the history memory 430 can be used effectively. Next, an example of reusing the execution result in the execution history held in the history memory 430 will be briefly described with reference to the following diagram.

[Execution result reuse processing example]
FIG. 5 is a conceptual diagram showing an example of a method related to the execution result reuse process by the data processing apparatus 100 according to the first embodiment of the present invention. Here, since FIGS. 5A and 5C correspond to FIGS. 4A and 4C, description thereof is omitted here.

  FIG. 5B shows a process in which a function having two arguments is called by a call instruction (call) in the upper routine and then returned to the upper routine by a return instruction (return) in the lower routine that is the instruction section of the function. It is a conceptual diagram which shows an example.

  Here, an input value A setting 321 and an input value B setting 322 in the upper routine, and an input value A reference 323, an input value B reference 324, and an execution result C setting 325 in the lower routine that is the function instruction section are shown. Yes. Since these are the same as those shown in FIG. 4, the same reference numerals are given and description thereof is omitted here. Here, time passes from the left to the right.

  In such a case, in the input value A setting 321, it is assumed that the instruction address output from the program counter 350 by the address determination unit 510 matches the “input value A setting instruction address” in the input value setting instruction address table 520. Determined. As a result, the section identification information (function address 1) corresponding to the matched input value setting instruction address (input value A setting instruction address) is input to the history memory 430. That is, the section determination information (function address 1) is held in the execution data holding unit 440 by the address determination unit 510, and the held function address 1 is input to the history memory 430 by the execution history search unit 410.

  At this time, since the same “function address 1” as the section identification information (function address 1) from the address determination unit 510 is already held in the history memory 430, the “execution history search data 1” associated therewith is stored. The execution result is searched by “”.

  In the input value A setting 321, the input value A set by the input value A setting command is input to the history memory 430. In the input value B setting 322, the input value B set by the input value B setting command is input to the history memory 430. That is, in accordance with an instruction from address determination unit 510, input value A and input value B are sequentially held in execution data holding unit 440 based on an input value setting signal from instruction decoder 320. Then, the execution history search unit 410 sequentially inputs the input value A and the input value B in the execution data holding unit 440 to the execution history search unit 410.

  As a result, the comparison between the input value A and the input value B from the execution history search unit 410 and the input value held in “execution history search data 1” corresponding to “function address 1” in the history memory 430 is sequentially performed. Is called. Here, since both input values (input values A and B) match, the section identification information (function address 1) and the execution result (execution result C) associated with the input value (input value A and input value B). Is supplied to the execution history search unit 410. That is, the section identification information (function address 1) input to the history memory 430 and the execution result (execution result C) associated with the input values (input value A and input value B) are output from the history memory 430.

  Thereafter, based on the function call signal from the instruction decoder 320 by the call instruction (call), the address determination unit 510 notifies the execution history search unit 410 of the execution result reuse instruction. Usage processing is executed. That is, when the execution result is extracted by the execution history search unit 410 when the execution result output unit 420 executes the call instruction specified by the input value setting instruction address, the extracted execution result is The data is output to the execution unit 330.

  Thus, by providing the input value setting instruction address table 520, the earliest input value A setting instruction to be executed first for the function at the function address 1 can be specified. Therefore, the input values (input value A and input value B) set based on the input value A setting instruction and the input value B setting instruction in the instruction group from the input value A setting instruction to the call instruction (call) are determined. Can be identified. Thereby, in the execution history search period Ts until the execution of the call instruction (call) specified by the input value A setting instruction address, the execution history corresponding to the section identification information (function address 1) in the history memory 430 is searched. be able to.

  Further, the execution result C associated with the input value A and the input value B from the execution history search unit 410 is extracted from the execution history search data 1 of the function address 1 in the execution history search period Ts, thereby executing the function. Time (shortening period T1) can be reduced. Here, the difference between the shortening period T1 in the first embodiment of the present invention and the shortening period by the conventional execution result reuse process will be briefly described with reference to the drawings.

[Example of shortening period shortened by execution result reuse processing]
FIG. 6 is a conceptual diagram illustrating an example in which the execution time of a function is shortened by the execution result reuse process. FIG. 6A is a conceptual diagram showing a shortened period due to reuse of execution results in a conventional data processing apparatus that does not have an input value setting instruction address table 520. FIG. 6B is a conceptual diagram showing a shortened period due to reuse of the execution result in the data processing apparatus 100 according to the first embodiment of the present invention. 6 (a) and 6 (b) are the same as those shown in FIG. 5 (b), and therefore the same reference numerals are given and description thereof is omitted here.

  In the case of the prior art shown in FIG. 6A, all of the two arguments are referred to by the execution of the input value reference instruction (input value A reference 323 and input value B reference 324) in the lower-level routine that is the instruction section of the function. Until then, the input values A and B that are arguments of the function cannot be specified. For this reason, even when the input values A and B of the function all coincide with the input values in the history memory 430, the execution period of the function is only the shortened period T2 from the input value B reference 324 to the return instruction (return). Can not be reduced.

  On the other hand, in the first embodiment of the present invention shown in FIG. 6B, the input value A is set by the input value A setting 321 specified based on the input value setting command address table 520 as described in FIG. And the input value B can be specified. That is, the input value of the argument in the function can be specified based on the input value setting command in the execution history search period Ts from the input value A setting command to the call command (call).

  As a result, the search of the execution result in the history memory 430 can be terminated in the execution history search period Ts. Therefore, when the execution result can be reused, all the periods required for executing the function (shortening period T1) ) Can be reduced. Therefore, in the first embodiment of the present invention, the execution result reuse process in the data processing apparatus 100 can reduce the shortening period T1 longer than the conventional shortening period T2. Next, when both section identification information in the execution history search unit 410 and the history memory 430 match, the input value from the execution history search unit 410 and the input value in the history memory 430 do not match. An example of registration will be described with reference to the following diagram.

[Execution history registration example for the history memory 430 by the second and subsequent executions of the reuse section]
FIG. 7 is a conceptual diagram showing an execution history registration method in the second and subsequent function executions by the data processing apparatus 100 according to the first embodiment of the present invention. Here, since FIGS. 7A to 7C correspond to FIGS. 4A to 4C, detailed description thereof is omitted here.

  FIG. 7B is a conceptual diagram illustrating a processing example of the function illustrated in FIG. Here, it is assumed that an input value that is an argument of a function is a variable and an input value that is not held in the history memory 430 is set. For example, the case where the value indicated by the input value A in the history memory 430 is “3” and the value indicated by the input value A set by executing the function here is “5” is applicable.

  In such a case, in the input value A setting 321, it is assumed that the instruction address output from the program counter 350 by the address determination unit 510 matches the “input value A setting instruction address” in the input value setting instruction address table 520. Determined.

  As a result, the section identification information (function address 1) corresponding to the matched input value setting instruction address (input value A setting instruction address) is input to the history memory 430. That is, the section determination information (function address 1) is held in the execution data holding unit 440 by the address determination unit 510, and the held “function address 1” is input to the history memory 430 by the execution history search unit 410. .

  At this time, since the section identification information that matches the section identification information (function address 1) from the address determination unit 510 is already held in the history memory 430, the execution by the “execution history search data 1” associated therewith is executed. A search for results is performed.

  In the input value A setting 321, the input value A set by the input value A setting command is input to the history memory 430. At this time, since the input value A from the execution history search unit 410 and the input value held in the “execution history search data 1” in the history memory 430 do not match, the input value A from the execution history search unit 410 is “ It is newly registered in the “execution history search data 1”.

  Further, in the input value B setting 322, the input value B set by the input value B setting command is registered in the history memory 430 by the execution history search unit 410. That is, “execution history search data 1” in which the input value A and the input value B are associated is generated.

  Thereafter, the processing of the function is executed in the lower-level routine, and the execution result C set by the execution result setting instruction is registered in the history memory 430 by the execution history search unit 410 in the execution result C setting 325. That is, “execution history search data 1” in which the input value A, the input value B, and the execution result C are associated is generated.

  As described above, when the input value set by the input value setting command does not match the input value in the history memory 430 in the second and subsequent processes for the same function, the function is executed, and the execution result and The input value is newly registered in the history memory 430. Although an example in which the input value specified by the input value setting instruction is registered has been described here, the input value specified by the execution of the input value reference instruction may be registered in the history memory 430.

[Operation Example of Data Processing Device 100]
Next, the operation of the data processing apparatus 100 according to the first embodiment of the present invention will be described with reference to the drawings.

  FIG. 8 is a flowchart showing an example of the processing procedure of the execution result reuse method by the data processing apparatus 100 according to the first embodiment of the present invention.

  First, the fetch unit 310 reads an instruction from the main storage unit 130 or the instruction cache 210 (step S911). At this time, the address determination unit 510 determines whether or not the instruction address output from the program counter 350 matches the input value setting instruction address registered in the input value setting instruction address table 520 (step S912). . If it does not match the input value setting instruction address, the process returns to step S911 and is repeated until it matches the input value setting instruction address.

  On the other hand, if the input value setting instruction address matches, the address determination unit 510 obtains the section identification information associated with the matching input value setting instruction address from the input value setting instruction address table 520. Then, the acquired section identification information is held in the execution data holding unit 440 by the address determination unit 510 (step S913).

  Subsequently, the execution history search unit 410 inputs the section identification information held in the execution data holding unit 440 as a search key of the history memory 430 (step S914). As a result, a search for a plurality of execution histories corresponding to the section identification information in the history memory 430 is started.

  Next, the instruction decoder 320 determines whether or not the instruction read from the fetch unit 310 is an input value setting instruction (step S915). If it is determined that the instruction is an input value setting command, the input value set by the input value setting command based on the input value setting signal from the command decoder 320 is executed by the instruction of the address determination unit 510. It is held by the holding unit 440.

  Thereafter, the execution history search unit 410 inputs the input value held in the execution data holding unit 440 into the history memory 430 (step S921). Note that the determination in step S915 for the first time is always determined as an input value setting command here, so that the determination may be omitted and the process may proceed to step S921.

  Subsequently, for the execution history in the history memory 430 corresponding to the section identification information from the execution history search unit 410, the history memory 430 causes the input value from the execution history search unit 410 to match the input value in the execution history. Is determined (step S922). And when both input values do not correspond, it progresses to the process of step S924.

  On the other hand, if the two input values match, the pointer is advanced to the argument node in the next argument in the history memory 430 to compare the input value of the next argument in the execution history (step S923). That is, if there is an argument node that matches the input value from the execution history search unit 410, the next argument node is indicated by the right pointer of the argument node. Next, the fetch unit 310 reads an instruction from the main storage unit 130 or the instruction cache 210 (step S924), and the process returns to step S915.

  On the other hand, if it is determined in step S915 that the instruction is not an input value setting instruction, it is determined whether the instruction read by the fetch unit 310 is a function call instruction (step S916). If it is not a call instruction, the process proceeds to step S924.

  In this way, a series of processes in steps S915, S916 and S921 to S924 are repeatedly executed until the input values of all the arguments in the function are set. That is, the input value set based on the input value setting command of the function from the input value setting command to the call command specified by the input value setting command address table 520 is held in the execution data holding unit 440 and held. The input value is input to the history memory 430.

  As described above, the section identification information corresponding to the input value setting instruction address that matches the instruction address output from the program counter 350 is held in the execution data holding unit 440. Then, based on the input value setting command in the instruction group from the input value setting command to the call command specified by the input value setting command address, the input value output from the execution unit is held in the execution data holding unit 440. Is done. As a result, the execution history search unit 410 searches for an execution result associated with the execution history in the history memory 430 using the section identification information and the input value in the execution data holding unit 440. Note that steps S911 to S916 and S921 to S924 are an example of an execution history search procedure described in the claims.

  On the other hand, if it is determined in step S916 that the instruction is a function call instruction, whether the section identification information and the input value from the execution data holding unit 440 all match the input value associated with the section identification information in the history memory 430. It is determined whether or not (step S917).

  If all the section identification information and input values from the execution history search unit 410 match, an execution result reuse process is executed (step S925). That is, the execution result in the history memory 430 corresponding to the section identification information and the input value from the execution history search unit 410 is output from the execution result output unit 420. Then, the data is written back to the main storage unit 130 or the register file 340, and the function processing is skipped. Note that S925 is an example of an execution result output procedure described in the claims.

  On the other hand, if the section identification information from the execution history search unit 410 and the input values do not all match, the function called by the call instruction is executed, and the execution result is held in the execution data holding unit 440 (step). S918). Then, the execution history search unit 410 registers the execution result held in the execution data holding unit 440 and the section identification information and the input value held by the processes in steps S913 and S921 in the history memory 430 (step S919). ).

  As described above, in the first embodiment of the present invention, the input value setting command address table 520 causes the execution data holding unit 440 to store the section identification information of the reuse section and the function call instruction that is the reuse section. The input value can be held. Thus, before the function is called, the execution history search unit 410 can search the execution history in the history memory 430 based on the section identification information and the input value held in the execution data holding unit 440.

  For this reason, when an execution result associated with the execution history in the history memory 430 that matches the section identification information and the input value from the execution history search unit 410 is extracted, the execution of the function called by the call instruction is omitted. be able to. As a result, the processing time of the function due to the reuse of the execution result can be greatly reduced.

<2. Second Embodiment>
[Configuration example of program analysis processing device]
FIG. 9 is a block diagram illustrating a functional configuration example of the program analysis processing apparatus according to the second embodiment of the present invention. The program analysis processing device 600 includes a source program storage unit 610, a compile processing unit 620, an object program storage unit 660, and a reuse section information storage unit 670. The program analysis processing device 600 is an example of a program analysis processing device described in the claims.

  The source program storage unit 610 stores a source program to be compiled. This source program is a source program including a reuse section in which the execution result is used again. The source program storage unit 610 supplies the stored source program to the compilation processing unit 620.

  The compile processing unit 620 generates an object program that is a machine language program and reuse section information by compiling the source program from the source program storage unit 610. The reuse section information here refers to, for each reuse section, the input value setting instruction address of the first input value setting instruction in the reuse section and the section identification information for identifying the reuse section. Information. This reuse section information is stored in the input value setting instruction address table 520 in the search start instruction address management unit 500 shown in FIG.

  The compile processing unit 620 stores the generated object program in the object program storage unit 660 and the generated reuse section information in the reuse section information storage unit 670. The compilation processing unit 620 includes a program analysis unit 630, a program optimization processing unit 640, and a code generation unit 650.

  The program analysis unit 630 executes analysis processing such as morphological analysis and syntax analysis based on the source program read from the source program storage unit 610. The program analysis unit 630 generates a program with an intermediate representation expressed as an intermediate code in a format suitable for analysis or optimization, and executes an analysis process on the generated program with the intermediate representation.

  The program analysis unit 630 includes a reuse candidate section extraction unit 631 and a reuse candidate section analysis unit 632. The reuse candidate section extraction unit 631 extracts, from the program, a reuse candidate section that is a candidate for a reuse section in which an execution result is reused from among a plurality of command sections included in the program. The reuse candidate section extraction unit 631 extracts a function instruction section as a reuse candidate section.

  The reuse candidate section extraction unit 631 excludes functions whose execution results cannot be reused from the reuse candidate sections. This reuse candidate section extraction unit 631 excludes functions that have different execution results even if all the input values in the instruction section are the same, for example, functions that include a branch instruction in the instruction section from the reuse candidate section targets. To do. In this reuse candidate section extraction unit 631, for example, the second function is executed immediately after the execution of the first function. Therefore, the second input value setting instruction is executed before the call instruction of the first function. The first and second functions as described above are excluded from the reuse candidate section. In addition, the reuse candidate section extraction unit 631 supplies section identification information for identifying the extracted reuse candidate section to the reuse candidate section analysis unit 632 together with the program.

  The reuse candidate section analysis unit 632 analyzes the usage mode of the reuse candidate section extracted by the reuse candidate section extraction unit 631. For example, the reuse candidate section analysis unit 632 analyzes the number and types of arguments in a function and the number of times one function is executed for each function as a usage mode.

  For example, the reuse candidate section analysis unit 632 outputs a range that can be taken by an argument in the function as an analysis result of the usage mode. The reuse candidate section analysis unit 632 supplies the analysis result to the program optimization processing unit 640 together with the section identification information and program of the reuse candidate section.

  Based on the program supplied from the reuse candidate section analysis unit 632, the program optimization processing unit 640 performs program optimization such as optimization for improving the execution speed of the program and optimization for reducing the code size. The process is executed. The program optimization processing unit 640 includes a reuse degree generation unit 641, a reuse section extraction unit 642, and a reuse section information generation unit 643.

  Based on the analysis result supplied from the reuse candidate section analysis unit 632, the reuse degree generation unit 641 generates a reuse degree indicating the degree to which the execution result of the reuse candidate section is reused. In other words, the reuse level generation unit 641 generates a reuse level for each instruction interval based on the usage of the instruction interval, indicating the degree to which the input values for each execution of processing in the instruction interval executed a plurality of times match each other. To do.

  For example, the reuse degree generation unit 641 generates a reuse degree according to the number of executions of one reuse candidate section. In this case, for example, the reuse level generation unit 641 sets the reuse level larger as the number of executions is larger. In addition, the reuse degree generation unit 641 generates a reuse degree for the reuse candidate section, for example, according to a range that can be taken by the input value of the reuse candidate section. In this case, the degree of reuse is calculated, for example, by multiplying a reciprocal of the number of possible ranges by a constant. Thus, the larger the reuse degree of the reuse candidate section, the higher the probability that the reuse result of the reuse candidate section will be reused.

  In addition, the reuse degree generation unit 641 supplies the reuse degree related to the generated reuse candidate section to the reuse section extraction unit 642 together with the program and the section identification information of the reuse candidate section. The reuse level generation unit 641 is an example of a reuse level generation unit described in the claims.

  The reuse section extraction unit 642 re-uses the reuse section based on the reuse degree related to each reuse candidate section from the reuse degree generation section 641 among the plurality of reuse candidate sections extracted by the reuse candidate section analysis unit 632. This is to extract the usage section. For example, the reuse section extraction unit 642 extracts a reuse candidate section that is equal to or greater than a certain threshold (reuse threshold) regarding the degree of reuse as a reuse section.

  In addition, the reuse interval extraction unit 642 supplies the extracted interval identification information regarding the reuse interval to the reuse interval information generation unit 643 together with the program. Note that the reuse section extraction unit 642 may generate, for example, the priority when deleting the execution history for each section identification information in the history memory 430 illustrated in FIG. 2 based on the degree of reuse. In this case, the reuse section extraction unit 642 generates the priority so that the higher the reuse degree, the lower the priority.

  The reuse section information generation unit 643 associates the section identification information of the reuse section extracted by the reuse section extraction unit 642 and the earliest input value setting command address in the reuse section as reuse section information. Is to be generated. The reuse section information generation unit 643 is the memory address of the earliest input value setting instruction that is executed first on the time axis among the input value setting instructions in the reuse section extracted by the reuse section extraction unit 642. The input value setting instruction address is extracted for each reuse section.

  Further, the reuse section information generation unit 643 generates reuse section identification information in which the extracted input value setting command address and section identification information extracted are associated with each reuse section. Further, the reuse interval information generation unit 643 stores the generated reuse interval identification information in the reuse interval information storage unit 670. Here, the example in which the earliest input value setting command address is associated with each piece of section identification information has been described as the reuse section information. However, all input value setting instruction addresses are associated with each piece of section identification information. May be generated.

  In addition, the reuse interval information generation unit 643, for example, with respect to the program supplied from the reuse interval extraction unit 642, commands from the earliest input value setting command in the reuse interval to the call instruction of the reuse interval Rearrange the instruction codes so that the number of groups is as small as possible. Thereby, the search period of the execution history in the history memory 430 shown in FIG. 2 can be shortened, so that the power consumption by the history memory 430 in the data processing apparatus 100 can be reduced.

  In addition, the reuse section information generation unit 643 supplies the code generation unit 650 with a program in which the instruction code is rearranged. The reuse section information generation unit 643 is an example of a reuse section information generation unit described in the claims.

  Note that the reuse section information generation unit 643 uses the priority when deleting the execution history of the history memory 430, the section identification information, and the earliest input based on the reuse degree from the reuse degree generation unit 641. The reuse section information may be generated in association with the value setting instruction address.

  As a result, when the capacity of the history memory 430 exceeds a certain condition, the execution history search unit 410 can delete the execution history of the history memory 430 according to the priority. For this reason, it is possible to preferentially hold an execution history with a high degree of reuse in the history memory 430.

  The code generation unit 650 generates an object program that is a code of a machine language program based on the program supplied from the reuse section information generation unit 643. The code generation unit 650 stores the generated object program in the object program storage unit 660.

  The object program storage unit 660 stores the object program output from the code generation unit 650. The object program stored in the object program storage unit 660 is stored in the main storage unit 130 shown in FIG.

  The reuse section information storage unit 670 stores the reuse section information output from the reuse section information generation unit 643. The reuse section information stored in the reuse section information storage unit 670 is transferred to the input value setting command address table 520 shown in FIG.

  As described above, by providing the reuse level generation unit 641, the reuse level is generated based on the usage mode of the command interval that is executed a plurality of times. Therefore, the execution result is reused among the plurality of command intervals. It is possible to extract an instruction section having a high probability of being used as a reuse section. Further, by providing the reuse section information generation unit 643, it is possible to generate reuse section information in which the input value setting command address and section identification information in the reuse section are associated with each extracted reuse section. .

[Operation Example of Program Analysis Processing Device 600]
Next, the operation of the program analysis processing apparatus 600 according to the second embodiment of the present invention will be described with reference to the drawings.

  FIG. 10 is a flowchart showing an example of the processing procedure of the program analysis processing method of the program analysis processing device 600 according to the second embodiment of the present invention.

  First, the reuse candidate section extraction unit 631 reads the source program from the source program storage unit 610 (step S931). Then, the reuse candidate section extraction unit 631 extracts a function that becomes a reuse candidate section from among the instruction sections that are a plurality of functions included in the program (step S932).

  Subsequently, the reuse candidate section analysis unit 632 analyzes the usage mode related to the reuse candidate section extracted by the reuse candidate section extraction unit 631 (step S933). Thereafter, the reuse degree is generated for each reuse candidate section by the reuse degree generation unit 641 based on the usage mode of the reuse candidate section analyzed by the reuse candidate section analysis unit 632 (step S934). . Note that step S934 is an example of a reuse degree generation procedure described in the claims.

  Then, the reuse section extraction unit 642 extracts a reuse section based on the reuse degree for each reuse candidate section (step S935). Next, the reuse section information generation unit 643 generates reuse section information in which the earliest input value setting instruction address in the reuse section and the section identification information of the reuse section are associated with each reuse section. (Step S936). Then, the reuse interval information generation unit 643 stores the generated reuse interval information in the reuse interval information storage unit 670. Note that step S936 is an example of a reuse section information generation procedure described in the claims.

  Thereafter, the code generation unit 650 generates an object program based on the program supplied from the reuse section information generation unit 643, and the generated object program is stored in the object program storage unit 660 (step S937). .

  As described above, in the second embodiment of the present invention, it is possible to generate reuse section information in which an input value setting instruction address in a function that is a reuse section having a high reuse degree and its section identification information are associated with each other. it can. Thereby, since the execution history for the function whose execution result is highly likely to be reused is held in the history memory 430 shown in FIG. 2, the reduction in execution time by the execution result reuse processing can be improved. .

  In the first and second embodiments of the present invention, the example in which the reuse section information generated by the program analysis processing device 600 is registered in the input value setting instruction address table 520 in the data processing device 100 has been described. However, it is not limited to this. For example, in the data processing apparatus 100, the reuse section information may be registered in the input value setting command address table 520 while executing a program stored in the main storage unit 130. Accordingly, a data processing apparatus 100 improved so as to register the input value setting instruction address and the section identification information in the input value setting instruction address table 520 during the execution of the program will be described below as a third embodiment.

<3. Third Embodiment>
[Configuration Example of Data Processing Device 100]
FIG. 11 is a block diagram showing a configuration example of the data processing apparatus 100 according to the third embodiment of the present invention. Here, of the data processing apparatus 100 shown in FIG. 1, a data processing unit 300, an execution result reuse processing unit 700, and a search start instruction address management unit 800 are shown. Here, since the data processing unit 300 is the same as that in FIG. 2, the same reference numerals as those in FIG.

  The execution result reuse processing unit 700 includes an execution history search unit 710, an execution result output unit 720, a history memory 730, and an execution data holding unit 740. The execution history search unit 710, the execution result output unit 720, the history memory 730, and the execution data holding unit 740 are added to the execution history search unit 410, the execution result output unit 420, the history memory 430, and the execution data holding unit 440 shown in FIG. Correspond. The configuration of the execution result output unit 720 and the history memory 730 is the same as that of the execution result output unit 420 and the history memory 430 shown in FIG.

  The search start command address management unit 800 includes an address determination unit 810, an input value setting command address table 820, an input value setting command address output unit 830, a set input value holding unit 840, and a search start command determining unit 850. Prepare. Address determination unit 810 and input value setting instruction address table 820 correspond to address determination unit 510 and input value setting instruction address table 520 shown in FIG.

  Here, the description will focus on the function of registering the input value setting command address and the section identification information in the input value setting command address table 820. Further, the method for searching the execution result in the history memory 730 based on the input value setting command address registered in the input value setting command address table 820 is realized by the same configuration as in FIG. Description is omitted.

  The execution data holding unit 740 holds data used for the execution result reuse process in accordance with an instruction from the address determination unit 810, and uses the held data as an execution history search unit 710, a set input value holding unit 840, and a search start. This is output to the instruction determination unit 850. The execution data holding unit 740 holds the output from the execution unit 330 as a set input value in accordance with an instruction based on the input value setting signal from the address determination unit 810.

  The execution data holding unit 740 holds the order in which the set input values are held on the time axis together with the set input values as the set order in which the input values are set by the input value setting command. For example, the execution data holding unit 740 holds the first set input value as the first set input value in accordance with an instruction based on the input value setting signal from the address determination unit 810, for example.

  Further, the execution data holding unit 740 outputs the held setting input values and the setting order thereof to the setting input value holding unit 840 according to an instruction based on the function call signal from the address determination unit 810. For example, the execution data holding unit 740 outputs the storage location included in the set input value and the setting order thereof to the set input value holding unit 840. The storage location here refers to the register number of the register file 340 or the memory address of the main storage unit 130.

  At this time, when there are a plurality of setting input values indicating the same storage location, the execution data holding unit 740 includes the setting input values of the largest number (maximum) setting order among the plurality of setting input values and Only the setting order is output to the setting input value holding unit 840. That is, when there are a plurality of setting input values indicating the same storage location, the execution data holding unit 740 outputs the last set input value and the setting order among the plurality of setting input values. . Alternatively, the execution data holding unit 740 already holds the setting order of the new setting input value when the setting input value indicating the same storage location is newly held in the setting input value holding unit 840. Overlays (overwrites) the setting input value in the setting order holding area.

  In this way, the input that is not referred to as the input value of the function by causing the setting input value holding unit 840 to hold only the setting input value in the maximum setting order among the plurality of setting input values indicating the same storage location. Value setting instructions can be excluded from registration targets. This is because the instruction decoder 320 determines whether or not the instruction is an input value setting instruction depending on the storage location of the data indicated in the instruction. It is also referred to by other processes. For this reason, it can be determined that the setting input values indicating the same storage location other than the setting input value set immediately before the function call instruction are not the setting of the function input value.

  Further, the execution data holding unit 740 holds, for example, an output from the execution unit 330 as function section identification information in accordance with an instruction based on the function call signal from the address determination unit 810. The execution data holding unit 740 holds, for example, an instruction address from the program counter 350 as function section identification information in accordance with an instruction based on the function call signal from the address determination unit 810.

  The execution data holding unit 740 holds the output from the execution unit 330 as a reference input value in accordance with an instruction based on the input value reference signal from the address determination unit 810. Further, the execution data holding unit 740 holds the output from the execution unit 330 as the execution result of the function in accordance with the instruction based on the execution result setting signal from the address determination unit 810.

  The execution data holding unit 740 outputs the held section identification information and reference input value to the search start instruction determination unit 850 in accordance with an instruction based on the function return signal from the address determination unit 810. For example, the execution data holding unit 740 outputs the storage location indicated by the reference input value to the search start instruction determination unit 850 in accordance with an instruction based on the function return signal from the address determination unit 810.

  The execution data holding unit 740 outputs the held section identification information, reference input value, and execution result to the execution history search unit 710 in accordance with an instruction based on the function return signal from the address determination unit 810.

  Further, the execution data holding unit 740 outputs the held data to the execution history search unit 710 in accordance with an instruction based on the function return signal from the address determination unit 810, and then stores the data held in the execution data holding unit 740. to erase.

  The address determination unit 810 causes the input value setting instruction address output unit 830 to hold an input value setting instruction address of a function that is a plurality of instruction sections included in the program. The address determination unit 810 causes the input value setting instruction address output unit 830 to hold the instruction address output from the program counter 350 based on the input value setting signal supplied from the instruction decoder 320 as an input value instruction address. At the same time, the address determination unit 810 causes the execution data holding unit 740 to hold the input value output from the execution unit 330 based on the input value setting signal from the instruction decoder 320 as a set input value.

  For example, the address determination unit 810 causes the execution data holding unit 740 to hold, as section identification information, the start address that is the instruction section of the function based on the function call signal supplied from the instruction decoder 320. For example, based on the function call signal from the instruction decoder 320, the address determination unit 810 causes the execution data holding unit 740 to hold the instruction address from the program counter 350 as section identification information. Alternatively, the address determination unit 810 causes the execution data holding unit 440 to hold the start address of the function output from the execution unit 330 as section identification information based on a function call signal from the instruction decoder 320, for example.

  Further, the address determination unit 810 causes the execution data holding unit 740 to hold the input value output from the execution unit 330 based on the input value reference signal supplied from the instruction decoder 320 as a reference input value. The address determination unit 810 also causes the execution data holding unit 740 to hold the execution result output from the execution unit 330 based on the execution result setting signal supplied from the instruction decoder 320.

  The input value setting instruction address table 820 holds, for each section identification information for identifying a function that is an instruction section, an input value setting instruction address that is an address of an input value setting instruction for setting an input value in the function. To do. This input value setting command address table 820 is, for example, the address of the earliest input value setting command for setting the input value first among the input value setting commands for setting the input value in the function. Is stored for each section identification information.

  Further, the input value setting instruction address table 820 outputs the held data to the address determination unit 810. If the function has a plurality of arguments, the input value setting instruction address table 820 stores a plurality of input value setting instruction addresses corresponding to the plurality of arguments for each section identification information of the function. Also good. The input value setting command address table 820 is an example of the input value setting command address table described in the claims.

  The input value setting command address output unit 830 associates the input value setting command address supplied from the address determination unit 810 with the section identification information supplied from the search start command determination unit 850 in the input value setting command address table 820. Output. The input value setting command address output unit 830 holds the input value setting command address supplied from the address determination unit 810.

  The input value setting command address output unit 830 holds the setting order, which is the order in which the input value setting command address is held on the time axis, together with the input value setting command address. The execution data holding unit 740 holds, for example, the first input value setting command address supplied from the address determination unit 810 as the first input value setting command address.

  The input value setting instruction address output unit 830 also sets the input value setting instruction address in the setting order determined by the search start instruction determining unit 850 and the search start instruction determining unit 850 among the held input value setting instruction addresses. Are output in association with the section identification information from. That is, the input value setting instruction address output unit 830 associates the input value setting instruction address in the function with the start address of the function that is the section identification information of the function, and registers it in the input value setting instruction address table 820 for each function. To do.

  The input value setting command address output unit 830 registers the held data in accordance with an instruction based on the function return signal from the address determination unit 810, and then stores the data held in the input value setting command address output unit 830. to erase.

  The setting input value holding unit 840 holds the setting input value output from the execution data holding unit 740 and the setting order in association with each other. The set input value holding unit 840 outputs the held set input values and the setting order to the search start instruction determining unit 850.

  The search start instruction determination unit 850 determines the earliest input value setting instruction in the function as a search start instruction based on the storage location included in the reference input value referenced by the execution of the input value reference instruction in the execution of the function. Is to do. The search start instruction determination unit 850 includes a storage location included in the set input value based on the input value setting instruction before the function call instruction, and a storage location included in the reference input value based on the input value reference instruction after the call instruction. Based on the above, the setting order of the earliest input value setting command is specified.

  The search start instruction determination unit 850, for example, among the set input values in the set input value holding unit 840, based on the storage location of the reference input value from the execution data holding unit 740, the setting referred to in the command section of the function The setting order of input values is extracted. Then, the search start instruction determination unit 850 specifies the smallest setting order among the setting orders of the extracted setting input values.

  That is, the search start instruction determination unit 850 first sets the input value in the storage location of the input value referred to in the instruction section of the function among the instructions determined by the instruction decoder 320 as the input value setting instruction. The setting command is specified as the earliest input value setting command.

  In addition, the search start command determination unit 850 notifies the input value setting command address output unit 830 of the specified smallest setting order. At the same time, the search start command determination unit 850 outputs the section identification information output from the execution data holding unit 740 to the input value setting command address output unit 830.

  Further, when the storage location of the reference input value is output from the execution data holding unit 740, the search start command determining unit 850 sends the input value setting command for the input value setting command address table 820 to the input value setting command address output unit 830. Suppress address registration. Thereby, registration of useless input value setting instruction addresses in the input value setting instruction address table 820 can be reduced.

  The execution history search unit 710 registers the section identification information, the reference input value, and the execution result from the execution data holding unit 740 in the history memory 730 in accordance with a registration instruction based on the function return signal from the address determination unit 810. The other functions of the execution history search unit 710 are the same as those of the execution history search unit 410 shown in FIG.

  As described above, by providing the input value setting command address output unit 830, the input value setting command address and the section identification information are stored in the input value setting command address table 820 while the program from the main storage unit 130 is being executed. Can be registered. That is, by providing the input value setting command address output unit 830, the input value setting command address held by the input value setting command and the section identification information of the command section specified by the input value setting command are input value setting. It can be output to the instruction address table 820.

  Further, the input value setting instruction address output unit 830 corresponds to the input value referred to in the instruction section called by the calling instruction among the input values set by the search start instruction determining unit 850 by the input value setting instruction. An input value setting instruction address can be output. That is, the input value setting command address output unit 830 includes the input value setting command address and the section identification information of the first input value setting command among the input value setting commands corresponding to the plurality of input values referred to in the command section. The start address of a certain instruction section can be output. Next, an example of registering an input value setting command address and section identification information in the input value setting command address table 820 will be described below with reference to the drawings.

[Example of registration in input value setting instruction address table 820]
FIG. 12 is a conceptual diagram showing an example of registering an input value setting command address and section identification information in the input value setting command address table 820 by the data processing apparatus 100 according to the third embodiment of the present invention. FIG. 12A is a diagram showing an example of the data format of the input value setting instruction address table 820. The input value setting instruction address table 820 shows the correspondence between the earliest input value setting instruction address 821 in the instruction section that is a function and the function address 822 that is section identification information for identifying the function. Yes.

  FIG. 12B is a diagram showing a correspondence relationship between the input value setting instruction address and the set input value held every time the input value setting instruction is executed. FIG. 12B shows a setting order 811, an input value setting command address 831, and a setting input value 841.

  The setting order 811 indicates the order in which the input value setting instructions are executed. The input value setting instruction address 831 indicates an instruction address from the program counter 350 held in the input value setting instruction address output unit 830 based on the input value setting instruction. The set input value 841 indicates an input value held in the set input value holding unit 840 based on the input value setting command. The input value may be only information indicating the storage location of the input value. This is because if the storage location of the input value is known, it can be determined whether or not the input value in the function has been referenced.

  FIG. 12C shows a sequence in which a function having two arguments is called by a call instruction (call) in the upper routine and then returned to the upper routine by a return instruction (return) in the lower routine that is the instruction section of the function. It is a conceptual diagram which shows the example of a process.

  Here, a function call instruction (call) 311 and a return instruction (return) 312 are shown. Further, an input value A setting 321 and an input value B setting 322 in the upper routine, an input value A reference 323, an input value B reference 324, and an execution result C setting 325 in the lower routine are shown. Since these are the same as those shown in FIG. 4B, description thereof is omitted here.

  FIG. 12D is a conceptual diagram illustrating an example of a data format in the history memory 730. Here, the correspondence relationship between the function address 731 which is function section identification information and the execution history search data 732 is shown. The execution history search data 732 is search data configured by the tree structure shown in FIG. 3 and includes information associated with input values and execution results in the execution history.

  In such a case, in the input value A setting 321, the instruction address (input value A setting instruction address) output from the program counter 350 is input to the input value setting instruction address output unit 830 according to an instruction from the address determination unit 810. Retained. At this time, the first set input value (input value A) held in the execution data holding unit 740 is output to the set input value holding unit 840 according to an instruction from the address determination unit 810.

  In the input value B setting 322, the instruction address (input value B setting instruction address) output from the program counter 350 is held in the input value setting instruction address output unit 830 according to an instruction from the address determination unit 810. At this time, the second set input value (input value B) held in the execution data holding unit 740 is output to the set input value holding unit 840 according to an instruction from the address determination unit 810.

  In the call instruction (call) 311, the section identification information (function address 1) is held in the execution data holding unit 740 according to an instruction from the address determination unit 810. In the input value A reference 323, the input value B reference 324, and the execution result C setting 325, the first reference input value (input value A) and the second reference input value (input value B) are instructed by the address determination unit 810. The execution result (execution result C) is held in the execution data holding unit 740.

  In the return instruction (return) 312, section identification information (function address 1) in the execution data holding unit 740, first and second reference input values (input value A and input value B) according to an instruction from the address determination unit 810. Is output to the search start instruction determination unit 850. As a result, the search start command determination unit 850 causes the first and second set input values (inputs) in the set input value holding unit 840 corresponding to the first and second reference input values (input value A and input value B). The value A and the input value B) are extracted.

  That is, based on the storage location of the reference input value in the execution data holding unit 740, the input value referred to by the execution of the function among the set input values in the set input value holding unit 840 is specified. This is because even an instruction determined to be an input value setting instruction by the instruction decoder 320 may not be an instruction for setting an input value for a function. For example, an instruction to store data in the register 4 is determined as an input value setting instruction by the instruction decoder 320, but may be used by other processing outside the instruction section of the function.

  Then, search start command determination unit 850 selects the smallest setting order (1) among the setting orders (1 and 2) of the extracted setting input values. That is, the search start command determination unit 850 selects the setting order (1) corresponding to the set input value set based on the earliest input value setting command in the function.

  Accordingly, the setting order (1) and the section identification information (function address 1) are supplied from the search start instruction determination unit 850 to the input value setting instruction address output unit 830. Then, the input value setting command address output unit 830 associates the “input value A setting command address” corresponding to the setting order (1) from the search start command determination unit 850 and “function address 1” with the input value. It is output to the setting command address table 820.

  Further, according to an instruction from the address determination unit 810, the section identification information (function address 1), the reference input value (input value A and input value B) and the execution result (execution result C) in the execution data holding unit 740 are executed. The data is output to the search unit 710. Then, the execution history search unit 710 registers the output data in the history memory 730.

[Operation Example of Data Processing Device 100]
Next, the operation of the data processing apparatus 100 according to the third embodiment of the present invention will be described with reference to the drawings.

  FIG. 13 is a flowchart illustrating an example of a processing procedure of an execution result reuse method by the data processing apparatus 100 according to the third embodiment of the present invention.

  First, the fetch unit 310 reads an instruction from the main storage unit 130 or the instruction cache 210 (step S941). Subsequently, the address determination unit 810 determines whether or not the instruction address output from the program counter 350 matches the input value setting instruction address in the input value setting instruction address table 820 (step S942).

  If the instruction address from the program counter 350 matches the input value setting instruction address, an execution history search process (step S960) is executed. On the other hand, if it does not match the input value setting instruction address, the instruction decoder 320 determines whether or not it is an input value setting instruction (step S943).

  If it is determined that the instruction is an input value setting instruction, an instruction address from the program counter 350 is held in the input value setting instruction address output unit 830 as an input value setting instruction address by an instruction from the address determination unit 810. (Step S954). Subsequently, in response to an instruction from the address determination unit 810, the output from the execution unit 330 is held as a set input value in the execution data holding unit 740, and the held set input value is held in the set input value holding unit 840. (Step S955).

  On the other hand, if it is determined that the instruction is not an input value setting instruction, the instruction decoder 320 determines whether it is a function call instruction (step S944). If it is determined that the instruction is not a function call instruction, the process returns to step S941.

  In this way, every time the input value setting instruction is read until the function call instruction is read, the instruction from the program counter 350 is sent to the input value setting instruction address output unit 830 and the set input value and its setting. The order is held in the set input value holding unit 840. In this case, when a setting input value having the same storage location of the setting input value is already held in the setting input value holding unit 840, it is overlaid on the holding area of the setting input value already held and its setting order. Thus, the new setting input value and its setting order are held.

  On the other hand, if it is determined that the instruction is not a function call instruction, the address determination unit 810 holds the start address of the function in the execution data holding unit 740 as section identification information (step S945). Next, in the instruction section of the function, the fetch unit 310 reads an instruction from the main storage unit 130 or the instruction cache 210 (step S946). Subsequently, the instruction decoder 320 determines whether or not the read instruction is an input value reference instruction (step S947).

  If it is determined that the instruction is an input value reference command, the output from the execution unit 330 is stored in the execution data storage unit 740 as a reference input value together with the order in accordance with an instruction from the address determination unit 810 (step S956). ), The process returns to step S946. On the other hand, if it is determined that the instruction is not an input value reference instruction, the instruction decoder 320 determines whether or not the read instruction is an execution result setting instruction (step S948).

  If it is determined that the instruction is an execution result setting instruction, an output from the execution unit 330 is held in the execution data holding unit 740 as an execution result in accordance with an instruction from the address determination unit 810 (step S957). The process returns to step S946. On the other hand, if it is determined that the instruction is not an execution result setting instruction, the instruction decoder 320 determines whether or not the read instruction is a function return instruction (step S949).

  If it is determined that the instruction is not a function return instruction, the process returns to step S946, and the reference input value and the execution result are held in the execution data holding unit 740 until the function call instruction is read.

  On the other hand, if it is determined that the instruction is a function call instruction, the reference input value held in the execution data holding unit 740 among the set input values held in the set input value holding unit 840 by the search start instruction determining unit 850. Based on the above, the setting order of the earliest setting input value in the function is specified. Of the input value setting instruction addresses in the input value setting instruction address output unit 830, the input value setting instruction address corresponding to the setting order specified by the search start instruction determining unit 850 is the earliest input value setting instruction address. Extracted.

  As a result, the input value setting command address output unit 830 associates the earliest input value setting command address with the section identification information from the execution data holding unit 740 and registers it in the input value setting command address table 820 ( Step S951). Further, according to a registration instruction from the address determination unit 810, the section identification information, the reference input value, and the execution result in the execution data holding unit 740 are registered in the history memory 730 by the execution history search unit 710 (step S952).

  Then, after the registration in the history memory 730 and the input value setting command address table 820 is completed, the data in the execution data holding unit 740, the set input value holding unit 840, and the input value setting command address output unit 830 is erased (step) S953). Then, the processing of the execution result reuse method is terminated.

[Example of execution history search processing in data processing apparatus 100]
FIG. 14 is a flowchart illustrating an example of a processing procedure of an execution history search process (step S960) by the data processing apparatus 100 according to the third embodiment of the present invention.

  First, the address determination unit 810 outputs the section identification information corresponding to the input value setting command address that matches the command address from the program counter 350 from the input value setting command address table 820 to the execution data holding unit 740 (step S110). S963). Subsequently, the section identification information held in the execution data holding unit 740 is input to the history memory 730 as a search key of the history memory 730 by the execution history search unit 710 (step S964). As a result, a search for a plurality of execution histories corresponding to the section identification information in the history memory 730 is started.

  Next, the instruction decoder 320 determines whether or not the instruction read from the fetch unit 310 is an input value setting instruction (step S965). If it is determined that the instruction is an input value setting instruction, the input value set by the input value setting instruction is changed by the address determination unit 810 based on the input value setting signal from the instruction decoder 320. 740.

  Thereafter, the execution history search unit 710 inputs the input value held in the execution data holding unit 740 into the history memory 730 (step S971). Note that the determination in step S965 for the first time is always determined to be an input value setting command here, so that the determination may be omitted and the process may proceed to step S971.

  Subsequently, for the execution history in the history memory 730 corresponding to the section identification information from the execution history search unit 710, the input value from the execution history search unit 710 matches the input value in the execution history by the history memory 730. Is determined (step S972). And when both input values do not correspond, it progresses to the process of step S974.

  On the other hand, if the two input values match, the history memory 730 advances the pointer to the argument node in the next argument in order to compare the input value of the next argument in the execution history (step S973). That is, if there is an argument node that matches the input value from the execution history search unit 710, the next argument node is indicated by the right pointer of the argument node. Next, the fetch unit 310 reads an instruction from the main storage unit 130 or the instruction cache 210 (step S974), and the process returns to step S915.

  On the other hand, if it is determined in step S965 that the instruction is not an input value setting instruction, it is determined whether the instruction read by the fetch unit 310 is a function call instruction (step S966). If it is not a function call instruction, the process proceeds to step S974.

  In this way, a series of processes in steps S965, S966, and S971 to S974 are repeatedly executed until all input values in the function are set. In other words, the input value set based on the input value setting command of the function from the input value setting command to the call command specified by the input value setting command address table 820 is held in the execution data holding unit 740 and held. The input value is input to the history memory 730.

  As described above, the section identification information corresponding to the input value setting instruction address that matches the instruction address output from the program counter 350 is held in the execution data holding unit 740. Then, the input value output from the execution unit based on the input value setting command in the instruction group from the input value setting command to the call command specified by the input value setting command address is held in the execution data holding unit 740. Is done.

  As a result, the execution history search unit 710 searches for an execution result associated with the execution history in the history memory 730 using the section identification information and the input value in the execution data holding unit 740. Note that steps S963 to S966 and S971 to S974 are an example of an execution history search procedure described in the claims.

  On the other hand, if it is determined in step S966 that the instruction is a function call instruction, whether the section identification information and the input value in the execution data holding unit 740 all match the input value associated with the section identification information in the history memory 730. It is determined whether or not (step S967).

  If all the section identification information and input values from the execution history search unit 710 match, an execution result reuse process is executed (step S975). That is, the execution result in the history memory 730 corresponding to the section identification information and the input value from the execution history search unit 710 is output from the execution result output unit 720. Then, the data is written back to the main storage unit 130 or the register file 340, and the function processing is skipped. Note that S975 is an example of an execution result output procedure described in the claims.

  On the other hand, when the section identification information from the execution history search unit 710 and the input values do not all match, the function called by the call instruction is executed and the execution result is held in the execution data holding unit 740 (step S968). Then, the execution history search unit 710 registers the execution result held in the execution data holding unit 740 and the section identification information and the input value held by the processes of steps S963 and S971 in the history memory 730 (step S919).

  As described above, in the third embodiment of the present invention, the search start instruction address management unit 800 registers the first input value setting instruction address in the function in the input value setting instruction address table 820 during the execution of the program. can do.

  As described above, according to the embodiment of the present invention, the execution history in the history memory 430 or 730 can be searched before executing the calling instruction in the instruction section. Time can be shortened. Further, by providing the input value setting instruction address tables 520 and 720, the execution history in the history memory 430 or 730 can be searched before the function call instruction is executed without embedding a dedicated instruction in the program itself.

  In the embodiment of the present invention, the history memory 430 or 730 may be realized by a nonvolatile memory such as an SRAM (Static Random Access Memory) or a ROM (Read Only Memory). As a result, even when the data processing apparatus 100 is turned off, the execution history held in the history memory 430 or 730 is not lost. It can be used effectively. For this reason, it is possible to suppress a decrease in execution time reduction effect due to the execution result reuse process immediately after the data processing apparatus 100 is activated.

  In addition, after the program is executed, the history data held in the history memory 430 or 730 may be transferred to a storage unit provided outside the data processing apparatus 100. Here, the case where the memory | storage part which memorize | stores historical data is provided in the exterior of the data processor 100 is demonstrated easily with reference to the next figure as 4th Embodiment.

<4. Fourth Embodiment>
[Example in which a history data storage unit is provided outside the data processing apparatus 100]
FIG. 15 is a block diagram showing a configuration example of an integrated circuit when a history data storage unit is provided outside the data processing apparatus 100 according to the fourth embodiment of the present invention. Here, in addition to the configuration of the integrated circuit shown in FIG. 1, a history data storage unit 140 is shown. Since the configuration other than the history data storage unit 140 is the same as that shown in FIG. 1, the description thereof is omitted here.

  The history data storage unit 140 stores history data in the history memory 430 or 730 transferred from the data processing device 100 after the program stored in the main storage unit 130 is executed. The history data storage unit 140 is realized by, for example, a nonvolatile memory.

  As described above, by providing the history data storage unit 140 realized by the non-volatile memory outside the data processing apparatus 100 and transferring the history data of the history memory 430 or 730, the loss of the history data due to power-off is avoided. can do. Next, a history data transfer method will be briefly described with reference to the following diagram.

  FIG. 16 is a flowchart illustrating a processing procedure of the history data transfer method by the data processing device 100 according to the fourth embodiment of the present invention.

  First, an application is activated (step S991), and the data processing unit 300 determines whether there is history data in the history data storage unit 140 (step S992).

  If the history data is stored in the history data storage unit 140, the stored history data is transferred to the history memory 430 or 730 by the data processing unit 300 (step S993). On the other hand, if no history data is stored, the process proceeds to step S994.

  Then, the data processing unit 300 executes an application that is a program stored in the main storage unit 130 (step S994). After execution of this application, the data processing unit 300 reconstructs new history data to be stored in the history data storage unit 140 based on both the history data in the history data storage unit 140 and the history memory 430 or 730 ( Step S995). Then, the reconstructed history data is stored in the history data storage unit 140.

  As described above, by transferring the past history data stored in the history data storage unit 140 to the history memory 430 or 730 before the execution of the program, the effect of shortening the execution time by the reuse processing immediately after the program is started can be obtained. Can be improved.

  In the embodiment of the present invention, an example of reusing the execution result for the instruction section of one function has been described. However, for a function having a multiple structure that calls a function more than once in the instruction section of a function. Can also be applied.

  The embodiment of the present invention shows an example for embodying the present invention. As clearly shown in the embodiment of the present invention, the matters in the embodiment of the present invention and the claims Each invention-specific matter in the scope has a corresponding relationship. Similarly, the matters specifying the invention in the claims and the matters in the embodiment of the present invention having the same names as the claims have a corresponding relationship. However, the present invention is not limited to the embodiments, and can be embodied by making various modifications to the embodiments without departing from the gist of the present invention.

  The processing procedure described in the embodiment of the present invention may be regarded as a method having a series of these procedures, and a program for causing a computer to execute the series of procedures or a recording medium storing the program May be taken as As this recording medium, for example, a CD (Compact Disc), an MD (MiniDisc), a DVD (Digital Versatile Disk), a memory card, a Blu-ray Disc (registered trademark), or the like can be used.

DESCRIPTION OF SYMBOLS 100 Data processor 120 Bus 130 Main memory part 200 Primary cache 210 Instruction cache 220 Data cache 300 Data processing part 310 Fetch part 320 Instruction decoder 330 Execution part 331 Load unit 332 Input selection part 333 Arithmetic circuit 334 Store unit 340 Register file 350 Program Counter 400, 700 Execution result reuse processing unit 410, 710 Execution history search unit 420, 720 Execution result output unit 430, 730 History memory 440, 740 Execution data holding unit 500, 800 Search start instruction address management unit 510, 810 Address determination Unit 520, 820 Input value setting instruction address table 600 Program analysis processing device 610 Source program storage unit 620 Compilation processing unit 630 Gram analysis unit 631 Reuse candidate section extraction unit 632 Reuse candidate section analysis unit 640 Program optimization processing unit 641 Reuse degree generation unit 642 Reuse section extraction unit 643 Reuse section information generation unit 650 Code generation unit 660 Object program storage Unit 670 Reuse section information storage unit 840 Setting input value holding unit 850 Search start command determining unit

Claims (10)

A process based on an instruction sequence including a plurality of instruction sections;
An input value setting instruction address that is an address of an input value setting instruction for setting an input value of the instruction section is held for each section identification information of the instruction section before a call instruction for calling the instruction section is executed. Input value setting instruction address table to be
A history memory that associates an input value and an execution result in the command section for each section identification information and holds it as an execution history;
The input value and the input value setting instruction address output from the execution unit based on the input value setting instruction in the instruction group from the input value setting instruction to the call instruction specified by the input value setting instruction address An execution history search unit that searches for the execution result in the execution history using the section identification information corresponding to
When the execution result is extracted by the execution history search unit when the call instruction specified by the input value setting instruction address is executed, the execution result that outputs the extracted execution result to the execution unit A data processing apparatus comprising an output unit. The input value setting instruction address table includes the input value setting instruction address of the input value setting instruction for setting an input value of a reuse section that is an instruction section executed a plurality of times among the plurality of instruction sections. Hold for each section identification information of the reuse section,
The execution history search unit includes: the input value output from the execution unit based on the input value setting command in the instruction group in the reuse interval; and the interval identification information corresponding to the input value setting command address. The execution result in the reuse section is searched using
The execution result output unit extracts the execution result of the reuse section in the execution history by the execution history search unit when the call instruction of the reuse section specified by the input value setting instruction address is executed. The data processing apparatus according to claim 1, wherein, when it is performed, the extracted execution result is output to the execution unit.   Of the input values set based on the input value setting command, the input value setting command address corresponding to the input value referred to in the command section called by the call command and the section identification information are input values. The data processing apparatus according to claim 1, further comprising an input value setting instruction address output unit for outputting to the setting instruction address table.   The input value setting command address output unit is configured to identify the input value setting command address of the first input value setting command and the interval among the input value setting commands corresponding to the plurality of input values referred to in the command interval. 4. The data processing apparatus according to claim 3, wherein the head address of the instruction section, which is information, is output.   The input value setting instruction address table includes, for each section identification information, the input value setting instruction address of the first input value setting instruction among the input value setting instructions for setting a plurality of input values in the instruction section. The data processing device according to claim 1, wherein the data processing device is held. The execution unit executes processing in the command section specified by the input value setting command address when the execution result in the execution history is not extracted from the history memory by the execution history search unit,
The execution history search unit includes an input value output from the execution unit based on the input value setting command, an execution result executed by the execution unit, and the section identification information corresponding to the input value setting command address. The data processing apparatus according to claim 1, wherein the data processing apparatus is held in the history memory. The input value setting instruction address table holds the input value setting instruction address of the input value setting instruction of the function that is the instruction section for each head address of the function that is the section identification information,
The history memory associates an input value and an execution result in the function for each head address of the function and holds the execution history as the execution history,
The execution history search unit includes the input value of the function output from the execution unit based on the input value setting command of the instruction group and a start address of the function corresponding to the input value setting command address. The execution result is searched using
The execution result output unit extracts the execution result when the execution history search unit extracts the execution result of the function when the call instruction of the function specified by the input value setting instruction address is executed. The data processing apparatus according to claim 1, wherein the executed result is output to the execution unit. A reuse level generation unit that generates a reuse level for each instruction interval based on a usage mode of the instruction interval, indicating a degree of matching between input values for each execution of processing in an instruction interval that is executed a plurality of times in the program When,
An input value setting instruction address of an input value setting instruction for setting an input value in a reuse section extracted based on the degree of reuse among the plurality of instruction sections, and a section identification for identifying the reuse section A program analysis processing apparatus comprising: a reuse section information generation unit that generates reuse section information associated with information. An execution unit for executing processing based on an instruction sequence including a plurality of instruction sections, and an input value setting instruction input value for setting an input value of the instruction section before execution of a call instruction for calling the instruction section An input value setting instruction address table that holds a set instruction address for each section identification information of the instruction section, and a history memory that holds an input value and an execution result in the instruction section for each section identification information and stores them as an execution history. A data processing method in a data processing apparatus comprising:
The input value and the input value setting instruction address output from the execution unit based on the input value setting instruction in the instruction group from the input value setting instruction to the call instruction specified by the input value setting instruction address An execution history search procedure for searching for the execution result in the execution history using the section identification information corresponding to
When the execution result is extracted by the execution history search procedure when the call instruction specified by the input value setting instruction address is executed, the execution result is output to the execution unit. A data processing method comprising: an output procedure. A reuse degree generation procedure for generating a reuse degree for each instruction section based on a usage mode of the instruction section;
An input value setting instruction address of an input value setting instruction for setting an input value in a reuse section extracted based on the degree of reuse among the plurality of instruction sections, and a section identification for identifying the reuse section A program analysis processing method comprising: a reuse section information generation procedure for generating reuse section information associated with information.

Images