[AMDGPU] Use verify<domtree> instead of intra-pass asserts.

Verifying dominator tree is expensive using intra-pass
asserts. Asserts added during D147408 are
increasing the build time of libc significantly. This change
does the verification after the atomic optimizer pass
and should fix the regression reported in D153232.

Reviewed By: arsenm, #amdgpu

Differential Revision: https://reviews.llvm.org/D153261

llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp

@@ -770,9 +770,6 @@ void AMDGPUAtomicOptimizerImpl::optimizeAtomic(Instruction &I,
   Instruction *const SingleLaneTerminator =
       SplitBlockAndInsertIfThen(Cond, &I, false, nullptr, &DTU, nullptr);
 
-  // Control flow is changed here after splitting I's block
-  assert(DTU.getDomTree().verify(DominatorTree::VerificationLevel::Full));
-
   // At this point, we have split the I's block to allow one lane in wavefront
   // to update the precomputed reduced value. Also, completed the codegen for
   // new control flow i.e. iterative loop which perform reduction and scan using
@@ -799,7 +796,6 @@ void AMDGPUAtomicOptimizerImpl::optimizeAtomic(Instruction &I,
         {{DominatorTree::Insert, EntryBB, ComputeLoop},
          {DominatorTree::Insert, ComputeLoop, ComputeEnd},
          {DominatorTree::Delete, EntryBB, SingleLaneTerminator->getParent()}});
-    assert(DTU.getDomTree().verify(DominatorTree::VerificationLevel::Full));
 
     Predecessor = ComputeEnd;
   } else {

llvm/test/CodeGen/AMDGPU/global_atomics_iterative_scan.ll

@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN:  opt -S -mtriple=amdgcn-- -amdgpu-atomic-optimizer-strategy=Iterative -passes=amdgpu-atomic-optimizer %s | FileCheck -check-prefix=IR %s
+; RUN:  opt -S -mtriple=amdgcn-- -amdgpu-atomic-optimizer-strategy=Iterative -passes='amdgpu-atomic-optimizer,verify<domtree>' %s | FileCheck -check-prefix=IR %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) , ptr addrspace(1) %val) #0 {
 ; IR-LABEL: @uniform_value(