[PATCH] D25998: AMDGPU/SI: Don't use non-0 waitcnt values when waiting on Flat instructions
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Wed Oct 26 12:23:49 PDT 2016
arsenm added inline comments.
================
Comment at: lib/Target/AMDGPU/SIInsertWaits.cpp:300-301
+ if (TII->isFLAT(*I))
+ IsFlatOutstanding = true;
+
----------------
Is this too strict? I know the manual says something like the only sensible value to use is 0 ,but from the reasoning before it it sounds like that's only if accessing a generic address. We could check the MMO and see if it is really global which is the common case
https://reviews.llvm.org/D25998
More information about the llvm-commits
mailing list