[DAGCombine] Fix type mismatch in (shl X, cttz(Y)) -> (mul (Y & -Y), X) (#94008)

Proof: https://alive2.llvm.org/ce/z/J7GBMU

Same as #92753, the types of
LHS and RHS in shift nodes may differ.
+ When VT is smaller than ShiftVT, it is safe to use trunc.
+ When VT is larger than ShiftVT, it is safe to use zext iff
`is_zero_poison` is true (i.e., `opcode == ISD::CTTZ_ZERO_UNDEF`). See
also the counterexample `src_shl_cttz2 -> tgt_shl_cttz2` in the alive2
proofs.

Fixes issue
#85066 (comment).

Author: dtcxzyw

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -10120,13 +10120,16 @@ SDValue DAGCombiner::visitSHL(SDNode *N) {
 
   // fold (shl X, cttz(Y)) -> (mul (Y & -Y), X) if cttz is unsupported on the
   // target.
-  if ((N1.getOpcode() == ISD::CTTZ || N1.getOpcode() == ISD::CTTZ_ZERO_UNDEF) &&
-      N1.hasOneUse() && !TLI.isOperationLegalOrCustom(ISD::CTTZ, VT) &&
+  if (((N1.getOpcode() == ISD::CTTZ &&
+        VT.getScalarSizeInBits() >= ShiftVT.getScalarSizeInBits()) ||
+       N1.getOpcode() == ISD::CTTZ_ZERO_UNDEF) &&
+      N1.hasOneUse() && !TLI.isOperationLegalOrCustom(ISD::CTTZ, ShiftVT) &&
       TLI.isOperationLegalOrCustom(ISD::MUL, VT)) {
     SDValue Y = N1.getOperand(0);
     SDLoc DL(N);
-    SDValue NegY = DAG.getNegative(Y, DL, VT);
-    SDValue And = DAG.getNode(ISD::AND, DL, VT, Y, NegY);
+    SDValue NegY = DAG.getNegative(Y, DL, ShiftVT);
+    SDValue And =
+        DAG.getZExtOrTrunc(DAG.getNode(ISD::AND, DL, ShiftVT, Y, NegY), DL, VT);
     return DAG.getNode(ISD::MUL, DL, VT, And, N0);
   }
 

llvm/test/CodeGen/PowerPC/pr85066.ll

@@ -0,0 +1,45 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=powerpc64le < %s | FileCheck %s
+
+; Tests from pr85066
+define i64 @test_shl_zext_cttz(i16 %x) {
+; CHECK-LABEL: test_shl_zext_cttz:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    oris 3, 3, 1
+; CHECK-NEXT:    neg 4, 3
+; CHECK-NEXT:    and 3, 3, 4
+; CHECK-NEXT:    clrldi 3, 3, 32
+; CHECK-NEXT:    blr
+entry:
+  %cttz = tail call i16 @llvm.cttz.i16(i16 %x, i1 false)
+  %zext = zext i16 %cttz to i64
+  %res = shl i64 1, %zext
+  ret i64 %res
+}
+
+define i64 @test_shl_zext_cttz_zero_is_poison(i16 %x) {
+; CHECK-LABEL: test_shl_zext_cttz_zero_is_poison:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    neg 4, 3
+; CHECK-NEXT:    and 3, 3, 4
+; CHECK-NEXT:    clrldi 3, 3, 32
+; CHECK-NEXT:    blr
+entry:
+  %cttz = tail call i16 @llvm.cttz.i16(i16 %x, i1 true)
+  %zext = zext i16 %cttz to i64
+  %res = shl i64 1, %zext
+  ret i64 %res
+}
+
+define i16 @test_shl_trunc_cttz(i32 %x) {
+; CHECK-LABEL: test_shl_trunc_cttz:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    neg 4, 3
+; CHECK-NEXT:    and 3, 3, 4
+; CHECK-NEXT:    blr
+entry:
+  %cttz = tail call i32 @llvm.cttz.i32(i32 %x, i1 false)
+  %trunc = trunc i32 %cttz to i16
+  %res = shl i16 1, %trunc
+  ret i16 %res
+}