[LLVMdev] Autotuning parameters/heuristics within LLVM

[Robert Stevenson]

Hi,

I am planning to begin a project to explore the space of tuning LLVM
internals in an effort to increase performance. I am wondering if
anyone can point to me any parameterizations, heuristics, or
priorities functions within LLVM that can be tuned/adjusted. So far,
I'm considering BranchProbabilityInfo and InlineCost. Does anyone have
any other suggestions?

Thanks,
Robert