diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 0d23323c4fb0..775b35d65214 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -2491,7 +2491,7 @@ bool SIInstrInfo::hasUnwantedEffectsWhenEXECEmpty(const MachineInstr &MI) const
   //       given the typical code patterns.
   if (Opcode == AMDGPU::S_SENDMSG || Opcode == AMDGPU::S_SENDMSGHALT ||
       Opcode == AMDGPU::EXP || Opcode == AMDGPU::EXP_DONE ||
-      Opcode == AMDGPU::DS_ORDERED_COUNT)
+      Opcode == AMDGPU::DS_ORDERED_COUNT || Opcode == AMDGPU::S_TRAP)
     return true;
 
   if (MI.isCall() || MI.isInlineAsm())
diff --git a/llvm/test/CodeGen/AMDGPU/skip-branch-trap.ll b/llvm/test/CodeGen/AMDGPU/skip-branch-trap.ll
new file mode 100644
index 000000000000..bce4023316fa
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/skip-branch-trap.ll
@@ -0,0 +1,58 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=HSA-TRAP %s
+
+; FIXME: merge with trap.ll
+
+; An s_cbranch_execnz is required to avoid trapping if all lanes are 0
+; GCN-LABEL: {{^}}trap_divergent_branch:
+; GCN: s_and_saveexec_b64
+; GCN: s_cbranch_execz [[ENDPGM:BB[0-9]+_[0-9]+]]
+; GCN: s_branch [[TRAP:BB[0-9]+_[0-9]+]]
+; GCN: [[ENDPGM]]:
+; GCN-NEXT: s_endpgm
+; GCN: [[TRAP]]:
+; GCN: s_trap 2
+; GCN-NEXT: s_endpgm
+define amdgpu_kernel void @trap_divergent_branch(i32 addrspace(1)* nocapture readonly %arg) {
+  %id = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %id
+  %divergent.val = load i32, i32 addrspace(1)* %gep
+  %cmp = icmp eq i32 %divergent.val, 0
+  br i1 %cmp, label %bb, label %end
+
+bb:
+  call void @llvm.trap()
+  br label %end
+
+end:
+  ret void
+}
+
+; GCN-LABEL: {{^}}debugtrap_divergent_branch:
+; GCN: s_and_saveexec_b64
+; GCN: s_cbranch_execz [[ENDPGM:BB[0-9]+_[0-9]+]]
+; GCN: BB{{[0-9]+}}_{{[0-9]+}}:
+; GCN: s_trap 3
+; GCN-NEXT: [[ENDPGM]]:
+; GCN-NEXT: s_endpgm
+define amdgpu_kernel void @debugtrap_divergent_branch(i32 addrspace(1)* nocapture readonly %arg) {
+  %id = call i32 @llvm.amdgcn.workitem.id.x()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %id
+  %divergent.val = load i32, i32 addrspace(1)* %gep
+  %cmp = icmp eq i32 %divergent.val, 0
+  br i1 %cmp, label %bb, label %end
+
+bb:
+  call void @llvm.debugtrap()
+  br label %end
+
+end:
+  ret void
+}
+
+declare void @llvm.trap() #0
+declare void @llvm.debugtrap() #1
+declare i32 @llvm.amdgcn.workitem.id.x() #2
+
+attributes #0 = { nounwind noreturn }
+attributes #1 = { nounwind }
+attributes #2 = { nounwind readnone speculatable }