[llvm] [AMDGPU] Check all incoming edges before deleting soft waits (PR #211684)

[Jay Foad via llvm-commits]

jayfoad wrote:

> To clarify, exposure to #2 is introduced after changing the algorithm to visit all predecessors. I would want to double check the details, but IIRC the issue is that we may insert vm_vsrc at the soft-wait, then update the brackets to note that we've cleared the events. Then when we revisit these soft waits for the other predecessor, we think the soft wait is sufficient given the new brackets state, and we optimize out the vm_vsrc. The main point I'm trying to convey is that the issue is introduced by the new iteration structure, and is not fixed by #212481

I tried rebasing this PR on #212481, and then undoing all your `UseImpliedWait`-related changes, and no tests failed. So I sill think #212481 is sufficient to fix issue #2.

https://github.com/llvm/llvm-project/pull/211684