[llvm] [PowerPC] Optimize allocation of Conditional Register (PR #69299)

[Kai Luo via llvm-commits]

bzEq wrote:

> Can you outline the reason for the performance improvement?

This is found in our internal workload where the loop is short and inside the loop body, two cmp instructions, very near in the body, are writing the same CR register. If we modify the allocation of CR registers manually, we got significant improvement in IPC and runtime, though this PR doesn't affect SPEC2017 too much.

>  I wonder if perhaps it would be better to implement a flag to tell the register allocator to use a circular allocation order for a particular register class

This is a good idea that worth a try. I'll investigate it.

https://github.com/llvm/llvm-project/pull/69299