[AArch64][SDAG] Fix selection of extend of v1if16 SETCC (llvm#140274)

There is a DAG combine, that folds:

```
t1: v1i1 = setcc x:v1f16, y:v1f16, setogt:ch
	t2: v1i64 = zero_extend t1
```

->

```
t1: v1i16 = setcc x:v1f16, y:v1f16, setogt:ch
	t2: v1i64 = any_extend t1
```

This creates an issue on AArch64 when attempting to widen the result to
`v4i16`. The operand types (`v1f16`) are set to be scalarized, so the
"by hand" widening with `DAG.WidenVector` is used for them, however,
this only widens to the next power-of-2, so returns `v2f16`, which does
not match the result VF. The fix is to manually construct the widened
inputs using `INSERT_SUBVECTOR`.

Fixes llvm#136540

Author: MacDue

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

@@ -6634,8 +6634,12 @@ SDValue DAGTypeLegalizer::WidenVecRes_SETCC(SDNode *N) {
     InOp1 = GetWidenedVector(InOp1);
     InOp2 = GetWidenedVector(InOp2);
   } else {
-    InOp1 = DAG.WidenVector(InOp1, SDLoc(N));
-    InOp2 = DAG.WidenVector(InOp2, SDLoc(N));
+    SDValue Poison = DAG.getPOISON(WidenInVT);
+    SDValue ZeroIdx = DAG.getVectorIdxConstant(0, SDLoc(N));
+    InOp1 = DAG.getNode(ISD::INSERT_SUBVECTOR, SDLoc(N), WidenInVT, Poison,
+                        InOp1, ZeroIdx);
+    InOp2 = DAG.getNode(ISD::INSERT_SUBVECTOR, SDLoc(N), WidenInVT, Poison,
+                        InOp2, ZeroIdx);
   }
 
   // Assume that the input and output will be widen appropriately.  If not,

llvm/test/CodeGen/AArch64/arm64-neon-v1i1-setcc.ll

@@ -249,3 +249,19 @@ if.then:
 if.end:
   ret i32 1;
 }
+
+define <1 x i64> @test_zext_half(<1 x half> %v1) {
+; CHECK-LABEL: test_zext_half:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $h0 killed $h0 def $d0
+; CHECK-NEXT:    mov w8, #1 // =0x1
+; CHECK-NEXT:    fcvtl v0.4s, v0.4h
+; CHECK-NEXT:    fmov d1, x8
+; CHECK-NEXT:    fcmgt v0.4s, v0.4s, #0.0
+; CHECK-NEXT:    xtn v0.4h, v0.4s
+; CHECK-NEXT:    and v0.8b, v0.8b, v1.8b
+; CHECK-NEXT:    ret
+  %1 = fcmp ogt <1 x half> %v1, zeroinitializer
+  %2 = zext <1 x i1> %1 to <1 x i64>
+  ret <1 x i64> %2
+}