[llvm] AMDGPU/GlobalISel: Fix inst-selection of ballot (PR #109986)

[Matt Arsenault via llvm-commits]

================
@@ -1429,34 +1429,129 @@ bool AMDGPUInstructionSelector::selectBallot(MachineInstr &I) const {
   std::optional<ValueAndVReg> Arg =
       getIConstantVRegValWithLookThrough(I.getOperand(2).getReg(), *MRI);
 
-  const auto BuildCopy = [&](Register SrcReg) {
-    if (Size == STI.getWavefrontSize()) {
-      BuildMI(*BB, &I, DL, TII.get(AMDGPU::COPY), DstReg)
-          .addReg(SrcReg);
-      return;
+  const auto getCmpInput = [&]() -> MachineInstr * {
+    MachineInstr *SrcMI = getDefIgnoringCopies(I.getOperand(2).getReg(), *MRI);
+    // Try to fold sgpr compare.
+    if (SrcMI->getOpcode() == AMDGPU::G_TRUNC)
+      SrcMI = MRI->getVRegDef(SrcMI->getOperand(1).getReg());
+
+    if (SrcMI->getOpcode() == AMDGPU::G_ICMP ||
+        SrcMI->getOpcode() == AMDGPU::G_FCMP)
+      return SrcMI;
+    return nullptr;
+  };
+
+  const auto FoldCmp = [&](Register Dst, MachineInstr *CmpMI) -> bool {
+    // Fold ballot of a compare. Active lanes when the ballot is executed need
----------------
arsenm wrote:

Can you check that the block parents are the same? It's only broken in the mid block exec mask change, which we should move away from having 

https://github.com/llvm/llvm-project/pull/109986