diff --git a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-simplify-cfg-CAS-block.ll b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-simplify-cfg-CAS-block.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-simplify-cfg-CAS-block.ll
@@ -0,0 +1,66 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -atomic-expand %s | FileCheck -check-prefix=GFX90A %s
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+
+define amdgpu_kernel void @divergent_cfg(ptr addrspace(1) %out, float %in) #0 {
+; GFX90A-LABEL: @divergent_cfg(
+; GFX90A-NEXT:  entry:
+; GFX90A-NEXT:    [[TID:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; GFX90A-NEXT:    [[D_CMP:%.*]] = icmp ult i32 [[TID]], 16
+; GFX90A-NEXT:    br i1 [[D_CMP]], label [[IF:%.*]], label [[ELSE:%.*]]
+; GFX90A:       if:
+; GFX90A-NEXT:    [[TMP0:%.*]] = load float, ptr addrspace(1) [[OUT:%.*]], align 4
+; GFX90A-NEXT:    br label [[ATOMICRMW_START:%.*]]
+; GFX90A:       atomicrmw.start:
+; GFX90A-NEXT:    [[LOADED:%.*]] = phi float [ [[TMP0]], [[IF]] ], [ [[TMP4:%.*]], [[ATOMICRMW_START]] ]
+; GFX90A-NEXT:    [[NEW:%.*]] = fadd float [[LOADED]], [[IN:%.*]]
+; GFX90A-NEXT:    [[TMP1:%.*]] = bitcast float [[NEW]] to i32
+; GFX90A-NEXT:    [[TMP2:%.*]] = bitcast float [[LOADED]] to i32
+; GFX90A-NEXT:    [[TMP3:%.*]] = cmpxchg ptr addrspace(1) [[OUT]], i32 [[TMP2]], i32 [[TMP1]] seq_cst seq_cst, align 4
+; GFX90A-NEXT:    [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP3]], 1
+; GFX90A-NEXT:    [[NEWLOADED:%.*]] = extractvalue { i32, i1 } [[TMP3]], 0
+; GFX90A-NEXT:    [[TMP4]] = bitcast i32 [[NEWLOADED]] to float
+; GFX90A-NEXT:    br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX90A:       atomicrmw.end:
+; GFX90A-NEXT:    br label [[ENDIF:%.*]]
+; GFX90A:       else:
+; GFX90A-NEXT:    [[TMP5:%.*]] = load float, ptr addrspace(1) [[OUT]], align 4
+; GFX90A-NEXT:    br label [[ATOMICRMW_START2:%.*]]
+; GFX90A:       atomicrmw.start2:
+; GFX90A-NEXT:    [[LOADED3:%.*]] = phi float [ [[TMP5]], [[ELSE]] ], [ [[TMP9:%.*]], [[ATOMICRMW_START2]] ]
+; GFX90A-NEXT:    [[NEW4:%.*]] = fadd float [[LOADED3]], [[IN]]
+; GFX90A-NEXT:    [[TMP6:%.*]] = bitcast float [[NEW4]] to i32
+; GFX90A-NEXT:    [[TMP7:%.*]] = bitcast float [[LOADED3]] to i32
+; GFX90A-NEXT:    [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[OUT]], i32 [[TMP7]], i32 [[TMP6]] seq_cst seq_cst, align 4
+; GFX90A-NEXT:    [[SUCCESS5:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
+; GFX90A-NEXT:    [[NEWLOADED6:%.*]] = extractvalue { i32, i1 } [[TMP8]], 0
+; GFX90A-NEXT:    [[TMP9]] = bitcast i32 [[NEWLOADED6]] to float
+; GFX90A-NEXT:    br i1 [[SUCCESS5]], label [[ATOMICRMW_END1:%.*]], label [[ATOMICRMW_START2]]
+; GFX90A:       atomicrmw.end1:
+; GFX90A-NEXT:    br label [[ENDIF]]
+; GFX90A:       endif:
+; GFX90A-NEXT:    [[COMBINE:%.*]] = phi float [ [[TMP4]], [[ATOMICRMW_END]] ], [ [[TMP9]], [[ATOMICRMW_END1]] ]
+; GFX90A-NEXT:    store float [[COMBINE]], ptr addrspace(1) [[OUT]], align 4
+; GFX90A-NEXT:    ret void
+;
+entry:
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %d_cmp = icmp ult i32 %tid, 16
+  br i1 %d_cmp, label %if, label %else
+
+if:
+  %res_if = atomicrmw fadd ptr  addrspace(1) %out, float %in seq_cst
+  br label %endif
+
+else:
+  %res_else = atomicrmw fadd ptr  addrspace(1) %out, float %in seq_cst
+  br label %endif
+
+endif:
+  %combine = phi float [%res_if, %if], [%res_else, %else]
+  store float %combine, ptr addrspace(1) %out
+  ret void
+}
+
+attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" "amdgpu-unsafe-fp-atomics"="true" }