[PATCH] D43594: [AMDGPU] Respect pragma unroll when loop contains convergent instructions

[Eli Friedman via Phabricator via llvm-commits]

efriedma added inline comments.


================
Comment at: include/llvm/Analysis/TargetTransformInfo.h:426
+    /// Allow unrolling convergent loop with remainder.
+    bool AllowRemainderForConvergentLoop;
   };
----------------
I don't like sticking this here.

>From your description, it sounds like it's a *correctness* property of the target, whether or not certain transforms which duplicate convergent operations are allowed.  In that case, it's not really about unrolling at all; it could apply to other transforms which clone code.  So at the very least, this should be a separate hook, with a clear explanation of exactly which transforms this allows.


https://reviews.llvm.org/D43594