[llvm] [AMDGPU] SIInsertHardClause: add configurable clause length limit (PR #142343)

[Jay Foad via llvm-commits]

jayfoad wrote:

> > Why?
> 
> In certain applications I am seeing large clauses to have a negative impact on performance. For these cases using small clauses (e.g. 4 operations) boosts performance 1-2%. (Disabling clausing entirely does not yield this benefit.) I assume these cases have improved cache efficiency from interleaving lock-stepped waves rather than issuing long sequences of uninterrupted memory requests from each wave in turn.
> 
> I am gather data to see if a lower (than hardware maximum) limit might be beneficial overall.

Fair enough. Should mention in the commit description that it's for performance tuning.

https://github.com/llvm/llvm-project/pull/142343