[PATCH] D157495: [WIP] Run SimplifyCFG from Atomic-Expand on CAS loop blocks.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

What happens if you remove the aarch64 tidy with this?



================
Comment at: llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll:3196
-  %id.x = call i32 @llvm.amdgcn.workitem.id.x()
-  %divValue = bitcast i32 %id.x to float
-  %result = atomicrmw fmin ptr addrspace(1) %ptr, float %divValue syncscope("agent") monotonic, align 4
----------------
Why were these tests deleted?


================
Comment at: llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-simplify-cfg-CAS-block.ll:6
+
+define amdgpu_kernel void @divergent_cfg(ptr addrspace(1) %out, float %in) #0 {
+; GFX90A-LABEL: @divergent_cfg(
----------------
Can you precommit the test?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157495/new/

https://reviews.llvm.org/D157495