Treat a missing rounding mode in div_out_mode as true division (pytorch#24178)

Summary:

`div.Tensor_mode(a, b, rounding_mode=None)` is true division. The HiFi `div_out_mode` sent `None` to the non-optimized path, where `mode_is_trunc` was false and the code fell through to `floor_divide` (its comment assumed the mode "must be floor"). So `7 / 2` returned 3 and `-7 / 2` returned -4. The kernel now delegates to `div_out` when `mode` has no value, which is what the portable and Fusion G3 `div_out_mode` already do.

Authored with Claude Code.

Reviewed By: DrJessop

Differential Revision: D127746755

Pull Request resolved: pytorch#24178

Author: aliafzal

backends/cadence/hifi/operators/op_div.cpp

@@ -210,6 +210,10 @@ Tensor& div_out_mode(
     Tensor& out) {
   ET_DCHECK_MSG(!tensor_has_zero(b), "divisor tensor contains zero");
 
+  if (!mode.has_value()) {
+    return div_out(ctx, a, b, out);
+  }
+
   ET_KERNEL_CHECK(
       ctx,
       torch::executor::resize_to_broadcast_target_size(a, b, out) == Error::Ok,

backends/cadence/hifi/operators/tests/test_op_div.cpp

@@ -59,6 +59,31 @@ TEST_F(HiFiDivTest, DISABLED_Int32FloorDivideTest) {
   EXPECT_TENSOR_EQ(out, tf.full(sizes, kExpectedResult));
 }
 
+TEST_F(HiFiDivTest, FloatNoRoundingModeIsTrueDivision) {
+  TensorFactory<ScalarType::Float> tf;
+  const std::vector<int> sizes{2, 2};
+  Tensor out = tf.zeros(sizes);
+  const Tensor numerator = tf.make(sizes, {7.0, -7.0, 1.0, -1.0});
+  const Tensor denominator = tf.make(sizes, {2.0, 2.0, 4.0, 4.0});
+
+  div_out_mode(numerator, denominator, std::nullopt, out);
+
+  EXPECT_TENSOR_EQ(out, tf.make(sizes, {3.5, -3.5, 0.25, -0.25}));
+}
+
+TEST_F(HiFiDivTest, Int32NoRoundingModeIsTrueDivisionToFloat) {
+  TensorFactory<ScalarType::Int> tf_int;
+  TensorFactory<ScalarType::Float> tf_float;
+  const std::vector<int> sizes{2, 2};
+  Tensor out = tf_float.zeros(sizes);
+  const Tensor numerator = tf_int.make(sizes, {7, -7, 1, -1});
+  const Tensor denominator = tf_int.make(sizes, {2, 2, 4, 4});
+
+  div_out_mode(numerator, denominator, std::nullopt, out);
+
+  EXPECT_TENSOR_EQ(out, tf_float.make(sizes, {3.5, -3.5, 0.25, -0.25}));
+}
+
 } // namespace
 } // namespace native
 } // namespace HiFi