[AMDGPU] SIRemoveShortExecBranches should not remove branches exiting loops

Summary:
Check that a s_cbranch_execz is not a loop exit before removing it.
As the pass is generating infinite loops.

Reviewers: cdevadas, arsenm, nhaehnle

Reviewed By: nhaehnle

Subscribers: kzhuravl, jvesely, wdng, yaxunl, tpr, t-tye, hiraditya, kerbowa, llvm-commits, dstuttard, foad

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D72997

llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp

@@ -88,10 +88,9 @@ bool SIRemoveShortExecBranches::mustRetainExeczBranch(
     for (MachineBasicBlock::const_iterator I = MBB.begin(), E = MBB.end();
          I != E; ++I) {
       // When a uniform loop is inside non-uniform control flow, the branch
-      // leaving the loop might be an S_CBRANCH_VCCNZ, which is never taken
-      // when EXEC = 0. We should skip the loop lest it becomes infinite.
-      if (I->getOpcode() == AMDGPU::S_CBRANCH_VCCNZ ||
-          I->getOpcode() == AMDGPU::S_CBRANCH_VCCZ)
+      // leaving the loop might never be taken when EXEC = 0.
+      // Hence we should retain cbranch out of the loop lest it become infinite.
+      if (I->isConditionalBranch())
         return true;
 
       if (TII->hasUnwantedEffectsWhenEXECEmpty(*I))

llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll

@@ -32,6 +32,7 @@ define amdgpu_ps void @main(i32, float) {
 ; CHECK-NEXT:    s_and_b64 s[8:9], s[8:9], exec
 ; CHECK-NEXT:    s_or_b64 s[4:5], s[4:5], s[8:9]
 ; CHECK-NEXT:    s_andn2_b64 exec, exec, s[2:3]
+; CHECK-NEXT:    s_cbranch_execz BB0_6
 ; CHECK-NEXT:  BB0_3: ; %loop
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    s_or_b64 s[6:7], s[6:7], exec
@@ -49,7 +50,7 @@ define amdgpu_ps void @main(i32, float) {
 ; CHECK-NEXT:    s_add_i32 s0, s0, 1
 ; CHECK-NEXT:    s_xor_b64 s[6:7], exec, -1
 ; CHECK-NEXT:    s_branch BB0_1
-; CHECK-NEXT:  ; %bb.6: ; %Flow2
+; CHECK-NEXT:  BB0_6: ; %Flow2
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[2:3]
 ; CHECK-NEXT:    v_mov_b32_e32 v1, 0
 ; CHECK-NEXT:    s_and_saveexec_b64 s[0:1], s[4:5]

llvm/test/CodeGen/AMDGPU/valu-i1.ll

@@ -13,6 +13,7 @@ declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
 ; SI-NEXT: s_mov_b64 {{s\[[0-9]+:[0-9]+\]}}, 0
 ; SI-NEXT: s_and_saveexec_b64 [[SAVE1:s\[[0-9]+:[0-9]+\]]], vcc
 ; SI-NEXT: s_xor_b64 [[SAVE2:s\[[0-9]+:[0-9]+\]]], exec, [[SAVE1]]
+; SI-NEXT: s_cbranch_execz [[FLOW_BB:BB[0-9]+_[0-9]+]]
 
 ; SI-NEXT: ; %bb.{{[0-9]+}}: ; %LeafBlock3
 ; SI:      s_mov_b64 s[{{[0-9]:[0-9]}}], -1
@@ -20,7 +21,7 @@ declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
 ; SI-NEXT: s_cbranch_execnz
 
 ; v_mov should be after exec modification
-; SI: ; %bb.{{[0-9]+}}:
+; SI: [[FLOW_BB]]:
 ; SI-NEXT: s_or_saveexec_b64 [[SAVE3:s\[[0-9]+:[0-9]+\]]], [[SAVE2]]
 ; SI-NEXT: s_xor_b64 exec, exec, [[SAVE3]]
 ;