[llvm] AMDGPU: Drop and upgrade llvm.amdgcn.atomic.csub/cond.sub to atomicrmw (PR #105553)

[via llvm-commits]

================
@@ -0,0 +1,197 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 < %s | FileCheck %s -check-prefix=GFX12-GISEL
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 < %s | FileCheck %s -check-prefix=GFX12-SDAG
+
----------------
anjenner wrote:

Done in https://github.com/llvm/llvm-project/pull/141068 and combined with what was atomics_cond_sub.ll.

https://github.com/llvm/llvm-project/pull/105553