Optimizing branch re-wiring in a software instruction cache
A method includes a computer device receiving a branch instruction; the computer device managing two tables, where a first table relates to application blocks and a second table relates to available address slots; and the computer device calculating a target of the branch instruction using a branch-to-link register, the computer device optimizes re-wiring in a cache using the calculation and the managed two tables.
1. A computer-implemented method comprising:
receiving, by a processor of a computer device, a branch instruction of an application block of instructions;
managing, by the processor, two tables, wherein
a first table comprises branch target descriptor information for a plurality of application blocks, wherein the descriptor information comprises an offset of a branch target, and
a second table comprises slot-id address information of the branch target, wherein an address of the branch target in a cache to a branch-to-link register is written; and
calculating, by the processor, a target of the branch instruction by using the branch-to-link register, wherein calculating the target of the branch instruction comprises:
determining a cache status of the application block using the first table;
in response to the cache status indicating that the application block is located in the cache, writing the address of the target of the branch to the branch-to-link register using the slot-id address information of the target of the branch accessed from the second table comprising; and
in response to the cache status indicating that the application block is not located in the cache, writing an address of a miss handler to the branch-to-link register; and
jumping to the target of the branch instruction using the brank-to-link register.