Jay Foad 7ecf19697e [AMDGPU] Fix and extend vccz workarounds ...

We have workarounds for two different cases where vccz can get out of
sync with the value in vcc. This fixes them in two ways:

1. Fix the case where the def of vcc was in a previous basic block, by
pessimistically assuming that vccz might be incorrect at a basic block
boundary.

2. Fix the handling of pre-existing waitcnt instructions by calling
generateWaitcntInstBefore before examining ScoreBrackets to determine
whether there's an outstanding smem read operation.

Differential Revision: https://reviews.llvm.org/D91636

2020-11-18 15:26:06 +00:00

61 KiB

Raw Blame History

View Raw