TH78418B - Comparing and replacing entries in the DAT table. - Google Patents

Abstract

DC60 (19/11/57) The first and second operands are compared. If they are equal, the contents of register R1+1 are stored at the location of the second operand, and the CPU, or all CPUs specified in the configuration, are freed of all TLB entries of the specified type created by using the replaced entry in storage and all lower-level TLB entries created by using the higher-level TLB entries that were cleared. Valid DAT entries are replaced with new entries, and the translation buffer (TLB) is cleared of at least one copy of the entry on all CPUs in the configuration. If the first and second operands are not equal, the second operand is loaded at the location of the first operand. The comparison result is indicated by the code. Conditions, methods, system products, and program products are provided.

Claims (8)

------01/02/2562------(OCR) Page 1 of 2 pages. Claims 1. A method for handling a dynamic address table (DAT) where the method consists of the following steps: The processor determines from the execution code of the instruction to be executed that it is a comparison instruction and replaces the entry in the DAT, where the instruction consists of fields R1 and R2; and the processor executes the instruction, where the operation consists of: adding the index value of an odd register to the value of an even register depending on the type field to create the address of the second operand, where the odd and even registers are the even and odd register pairs specified by the instruction's R2 field; accessing the original second operand from the memory location specified by the created address; comparing the first operand with the original second operand accessed. where the first operand is located in the even register (R, even) of the even and odd register pairs specified by the R field of the statement; and depending on the second operand, it is performed; storing the contents of the odd register (R1, odd) of the even and odd register pairs specified by the R1 field of the statement in the location of the second operand as the new second operand; and selecting to override all entries in the translation buffer (TLB) corresponding to entries created from the DAT using translation table entries depending on the translation table entries specified by the value of the second operand. 2. The method described in Claim 1 consists of storing the original second operand in register R, an even number depending on whether the first operand is not equal to the original second operand. 3. The method described in Claim 1, where the selected translation entry corresponds to the entry of the same level that is paired with the original second operand. 4. The method described in Claim 1 also consists of: setting the first condition code depending on whether the first operand is equal to the second operand; and setting the second condition code depending on whether the first operand is not equal to the second operand. 5. The method described in Claim 1, where the TLB entry to be removed is limited to the entry created to translate the address in the address space specified by Instruction 6. The method described in Claim 1, which also includes: selective removal of only the TLB of the processor executing the multi-processor instruction of the configuration based on the instruction's hidden field which has the first value; and selective removal of the TLB of the multi-processor instruction of the configuration based on the instruction's hidden field which has the second value. ------------ ------27/12/2017------(OCR) Page 1 of 2 Claim 1. The method for handling the Dynamic Address Table (DAT) involves the following steps: The processor determines from the execution code of the instruction to be executed that the instruction is a comparison instruction and replaces the entry in the DAT table, where the instruction contains the fields R and R2; and the processor executes the instruction, where the operations include: adding the index value of an odd register to the value of an even register depending on the field type to create the address of the second operand, where the odd and even registers are the even and odd registers specified by the R2 field of the instruction; acquiring the original second operand from the memory location specified by the created address; and comparing the first operand to the original second operand that was retrieved, where the first operand is in the even register (R, even) of the even and odd register pair specified by the R field of the instruction. And, depending on the second operand which is the same as the original second operand, the following will be done: storing the contents of the odd register (R1 odd) of the even and odd register pairs specified by the R1 field of the statement at the second operand's position in the form of the new second operand; and selectively override all entries in the translation buffer (TLB) corresponding to entries created from the DAT using translation table entries depending on the translation table entries specified by the value of the original second operand. 2. The method described in claim 1, which involves storing the original second operand in an even register R depending on the first operand which is not equal to the original second operand, is shown on page 2 of 2. 3. The method described in Claim 1, where the selected overridden entry corresponds to the lower-level entry paired with the original second operand. 4. The methods under claim 1 also include: setting the conditional code of the first operand based on the comparison value where the first operand is equal to the second operand; and setting the conditional code of the second operand based on the comparison value where the first operand is not equal to the second operand. 5. The method specified in Claim 1, where the nullified TLB entry is restricted to entries created to translate addresses in the address area specified by the order. 6. The methods specified in Claim 1 also include: selective override of only the TLB of the processor executing the multi-processor instruction of the configuration based on the instruction mask field having a value; and selective override of the TLB of multiple processors of the configuration based on the instruction mask field having a value. 7. The system comprises a mechanism that is adjusted to perform the steps of the established procedure according to the method. Which of the preceding methods is applicable? 8. A computer program consists of instructions to execute the steps of a method based on the preceding claims of any of the following methods. The computer executes on a computer system. ------------ 1. A method for handling a dynamic address table (DAT), where the method consists of the following steps: The processor determines from the execution code of the instruction to be executed whether the instruction is a comparison and replacement instruction, where the instruction consists of fields R1 and R2; and the processor executes the instruction, where the operation consists of: adding the index value of an odd register to the value of an even register depending on the type field to create the address of the second operand, where the odd and even registers are the even and odd register pairs specified by the instruction's field R2; and retrieving the original operand from the memory location specified by the created address. Comparing the first operand to the original second operand that receives it, where the first operand resides in the even register (even R1) of the even and odd register pairs specified by the R1 field of the instruction; storing the contents of the even R1 register at the location of the second operand as the new second operand, depending on whether the first operand is equal to the original second operand.