[clang] [CIR] Upstream ArraySubscriptExpr for fixed size array (PR #134536)

[Andy Kaylor via cfe-commits]

================
@@ -232,6 +233,161 @@ LValue CIRGenFunction::emitUnaryOpLValue(const UnaryOperator *e) {
   llvm_unreachable("Unknown unary operator kind!");
 }
 
+/// If the specified expr is a simple decay from an array to pointer,
+/// return the array subexpression.
+/// FIXME: this could be abstracted into a common AST helper.
+static const Expr *isSimpleArrayDecayOperand(const Expr *e) {
+  // If this isn't just an array->pointer decay, bail out.
+  const auto *castExpr = dyn_cast<CastExpr>(e);
+  if (!castExpr || castExpr->getCastKind() != CK_ArrayToPointerDecay)
+    return nullptr;
+
+  // If this is a decay from variable width array, bail out.
+  const Expr *subExpr = castExpr->getSubExpr();
+  if (subExpr->getType()->isVariableArrayType())
+    return nullptr;
+
+  return subExpr;
+}
+
+static mlir::IntegerAttr getConstantIndexOrNull(mlir::Value idx) {
+  // TODO(cir): should we consider using MLIRs IndexType instead of IntegerAttr?
+  if (auto constantOp = dyn_cast<cir::ConstantOp>(idx.getDefiningOp()))
+    return mlir::dyn_cast<mlir::IntegerAttr>(constantOp.getValue());
+  return {};
+}
+
+static CharUnits getArrayElementAlign(CharUnits arrayAlign, mlir::Value idx,
+                                      CharUnits eltSize) {
+  // If we have a constant index, we can use the exact offset of the
+  // element we're accessing.
+  const mlir::IntegerAttr constantIdx = getConstantIndexOrNull(idx);
+  if (constantIdx) {
+    const CharUnits offset = constantIdx.getValue().getZExtValue() * eltSize;
+    return arrayAlign.alignmentAtOffset(offset);
+  }
+  // Otherwise, use the worst-case alignment for any element.
+  return arrayAlign.alignmentOfArrayElement(eltSize);
+}
+
+static QualType getFixedSizeElementType(const ASTContext &astContext,
+                                        const VariableArrayType *vla) {
+  QualType eltType;
+  do {
+    eltType = vla->getElementType();
+  } while ((vla = astContext.getAsVariableArrayType(eltType)));
+  return eltType;
+}
+
+static mlir::Value
+emitArraySubscriptPtr(CIRGenFunction &cgf, mlir::Location beginLoc,
+                      mlir::Location endLoc, mlir::Value ptr, mlir::Type eltTy,
+                      ArrayRef<mlir::Value> indices, bool inbounds,
+                      bool signedIndices, bool shouldDecay,
+                      const llvm::Twine &name = "arrayidx") {
+  if (indices.size() > 1) {
+    cgf.cgm.errorNYI("emitArraySubscriptPtr: handle multiple indices");
+    return {};
+  }
+
+  const mlir::Value idx = indices.back();
+  CIRGenModule &cgm = cgf.getCIRGenModule();
+  // TODO(cir): LLVM codegen emits in bound gep check here, is there anything
+  // that would enhance tracking this later in CIR?
+  if (inbounds)
+    assert(!cir::MissingFeatures::emitCheckedInBoundsGEP() && "NYI");
+  return cgm.getBuilder().getArrayElement(beginLoc, endLoc, ptr, eltTy, idx,
+                                          shouldDecay);
+}
+
+static Address emitArraySubscriptPtr(
+    CIRGenFunction &cgf, mlir::Location beginLoc, mlir::Location endLoc,
+    Address addr, ArrayRef<mlir::Value> indices, QualType eltType,
+    bool inbounds, bool signedIndices, mlir::Location loc, bool shouldDecay,
+    QualType *arrayType = nullptr, const Expr *base = nullptr,
----------------
andykaylor wrote:

These default parameters are all unused. Remove them until they are needed.

https://github.com/llvm/llvm-project/pull/134536