[DAGCombiner][AArch64] Make combineCarryDiamond avoid creating UADDO_CARRY with carry in larger than setcc result type. (#89121)

In the attach test case we were creating a UADDO_CARRY with i1 carry out
and i41 carry in. i41 exceeds is larger than the setcc result type for
AArch64 which is i32. i41 needs to be promoted to i64 since it is larger
than i32. The type legalizer tried to use promoteTargetBoolean, but that
can only promote from a type smaller than setcc result type.

The easiest fix here is to force the carryin type to match the carryout
type at the type of creation. This should ensure the node won't exceeed
setcc result type as long as the output type doesn't.

I think we should explore requiring the types to match for this node.

Fixes #88966

Author: topperc

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -3520,6 +3520,8 @@ static SDValue combineCarryDiamond(SelectionDAG &DAG, const TargetLowering &TLI,
     return SDValue();
 
   SDLoc DL(N);
+  CarryIn = DAG.getBoolExtOrTrunc(CarryIn, DL, Carry1->getValueType(1),
+                                  Carry1->getValueType(0));
   SDValue Merged =
       DAG.getNode(NewOp, DL, Carry1->getVTList(), Carry0.getOperand(0),
                   Carry0.getOperand(1), CarryIn);

llvm/test/CodeGen/AArch64/pr88966.ll

@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: llc < %s -mtriple=aarch64 | FileCheck %s
+
+define i32 @f(ptr %arg, i41 %arg1, ptr %arg2) {
+; CHECK-LABEL: f:
+; CHECK:       // %bb.0: // %bb
+; CHECK-NEXT:    and w9, w1, #0x1
+; CHECK-NEXT:    mov w10, #1 // =0x1
+; CHECK-NEXT:    mov x8, x0
+; CHECK-NEXT:    cmp w9, #1
+; CHECK-NEXT:    mov w0, wzr
+; CHECK-NEXT:    adc x9, xzr, x10
+; CHECK-NEXT:    str x9, [x2]
+; CHECK-NEXT:    str xzr, [x8]
+; CHECK-NEXT:    ret
+bb:
+  %new0 = and i41 %arg1, 1
+  %last = trunc i41 %new0 to i1
+  %i = add i64 0, 1
+  %i3 = zext i1 %last to i64
+  %i4 = add i64 %i, %i3
+  %i5 = icmp ult i64 %i, 0
+  %i6 = icmp ult i64 %i4, %i
+  %i7 = and i1 %i5, %i6
+  %i8 = zext i1 %i7 to i64
+  store i64 %i4, ptr %arg2, align 8
+  store i64 %i8, ptr %arg, align 8
+  ret i32 0
+}