Early instruction text based operand store compare reject avoidance
View Patent ↗A method and system for early instruction text based operand store compare avoidance in a processor are provided. The system includes a processor pipeline for processing instruction text in an instruction stream, where the instruction text includes operand address information. The system also includes delay logic to monitor the instruction stream. The delay logic performs a method that includes detecting a load instruction following a store instruction in the instruction stream, comparing the operand address information of the store instruction with the load instruction. The method also includes delaying the load instruction in the processor pipeline in response to detecting a common field value between the operand address information of the store instruction and the load instruction.
1. A method for early instruction text based operand store compare avoidance in a processor pipeline, the method comprising:
creating addresses for a load store unit to access memory;
sending instruction text to an instruction grouping, wherein the instruction grouping establishes dependencies between an operand in the instruction text of a load instruction following a store instruction in the processor pipeline;
determining a delay period for delaying the load instruction; and
delaying, based on the determined delay period, the load instruction in the processor pipeline prior to reaching the load store unit.
2. The method of claim 1 wherein the load instruction is delayed in the processor pipeline prior to reaching the load store unit.
3. The method of claim 1 wherein the operand is identified as a field referencing a location in the memory.
4. The method of claim 3 wherein an address of the location is not fully resolved when dependencies are established.
5. The method of claim 4 wherein the load store unit is capable of rejecting the load instruction upon detecting an operand store compare attempting to load data from the location prior to storing the data to the location.
6. The method of claim 5 wherein the load instruction is delayed in the processor pipeline such that a number of delay cycles are inserted between the load instruction and the store instruction to prevent the load store unit from rejecting the load instruction.
7. A system for early instruction text based operand store compare avoidance in a processor pipeline, the system comprising:
a processor having a pipeline;
an instruction decoder; and
a load store unit configured to access memory, the processor configured to have an instruction grouping communicatively coupled to said the instruction decoder, the system configured to perform:
creating addresses for the load store unit to access memory;
receiving instruction text at the instruction grouping from the instruction decoder, wherein the instruction grouping establishes dependencies between an operand in the instruction text of a load instruction following a store instruction in the processor pipeline;
determining a delay period for delaying the load instruction; and
delaying, based on the determined delay period, the load instruction in the processor pipeline prior to reaching the load store unit.
8. The system of claim 7 wherein the load instruction is delayed in the processor pipeline prior to reaching the load store unit.
9. The system of claim 7 wherein the operand is identified as a field referencing a location in the memory.
10. The system of claim 9 wherein an address of the location is not fully resolved when dependencies are established.
11. The system of claim 10 wherein the load store unit is capable of rejecting the load instruction upon detecting an operand store compare attempting to load data from the location prior to storing the data to the location.
12. The system of claim 11 wherein the load instruction is delayed in the processor pipeline such that a number of delay cycles are inserted between the load instruction and the store instruction to prevent the load store unit from rejecting the load instruction.