[PATCH] D29971: [AMDGPU] Revert failed scheduling

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added a comment.

In https://reviews.llvm.org/D29971#677412, @vpykhtin wrote:

> Looks good, but should this be split into 2 changes?


These parts are not extremely independent, as I need to access pressure limits from strategy in the schedule method. I.e. I need them to be unchanged for a region.


Repository:
  rL LLVM

https://reviews.llvm.org/D29971