[GlobalISel] Check whether G_CTLZ is legal in matchUMulHToLShr

We need to check `G_CTLZ` because the combine uses `G_CTLZ` to get log base 2,
and it is not always legal for on a target.

Author: shiltian

llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp

@@ -5641,6 +5641,7 @@ bool CombinerHelper::matchUMulHToLShr(MachineInstr &MI) const {
   Register RHS = MI.getOperand(2).getReg();
   Register Dst = MI.getOperand(0).getReg();
   LLT Ty = MRI.getType(Dst);
+  LLT RHSTy = MRI.getType(RHS);
   LLT ShiftAmtTy = getTargetLowering().getPreferredShiftAmountTy(Ty);
   auto MatchPow2ExceptOne = [&](const Constant *C) {
     if (auto *CI = dyn_cast<ConstantInt>(C))
@@ -5649,7 +5650,10 @@ bool CombinerHelper::matchUMulHToLShr(MachineInstr &MI) const {
   };
   if (!matchUnaryPredicate(MRI, RHS, MatchPow2ExceptOne, false))
     return false;
-  return isLegalOrBeforeLegalizer({TargetOpcode::G_LSHR, {Ty, ShiftAmtTy}});
+  // We need to check both G_LSHR and G_CTLZ because the combine uses G_CTLZ to
+  // get log base 2, and it is not always legal for on a target.
+  return isLegalOrBeforeLegalizer({TargetOpcode::G_LSHR, {Ty, ShiftAmtTy}}) &&
+         isLegalOrBeforeLegalizer({TargetOpcode::G_CTLZ, {RHSTy, RHSTy}});
 }
 
 void CombinerHelper::applyUMulHToLShr(MachineInstr &MI) const {

llvm/test/CodeGen/AMDGPU/GlobalISel/no-ctlz-from-umul-to-lshr-in-postlegalizer.mir

@@ -0,0 +1,23 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -run-pass=amdgpu-postlegalizer-combiner %s -o - | FileCheck %s
+
+---
+name: test
+tracksRegLiveness: true
+legalized: true
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    ; CHECK-LABEL: name: test
+    ; CHECK: liveins: $vgpr0, $vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 4
+    ; CHECK-NEXT: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[COPY]], [[C]]
+    ; CHECK-NEXT: $vgpr0 = COPY [[UMULH]](s32)
+    ; CHECK-NEXT: SI_RETURN implicit $vgpr0
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = G_CONSTANT i32 4
+    %2:_(s32) = G_UMULH %0:_, %1:_
+    $vgpr0 = COPY %2:_(s32)
+    SI_RETURN implicit $vgpr0