Add 16A8W support and test for add operation (#13568)

Summary:

Add 16A8W quantization support and test for the add operation in ExecutorTorch ARM backend.

This follows the pattern established for linear operations, extending int16 support to add operations.

Changes:
- Add INT16 dtype validation support in op_add.py
- Add test_add_tensor_16a8w_tosa_INT test function
- Enable test_add.py in test targets configuration

The 16A8W configuration uses 16-bit activations with 8-bit weights, enabling higher precision for activations while maintaining weight efficiency.

Differential Revision: D80510463

Author: Ninja91

backends/arm/operators/op_add.py

@@ -50,7 +50,7 @@ def define_node(
         validate_valid_dtype(
             self.target,
             [*inputs, output],
-            [ts.DType.INT8, ts.DType.INT32],
+            [ts.DType.INT8, ts.DType.INT16, ts.DType.INT32],
             output.tosa_spec,
         )
 

backends/arm/test/ops/test_add.py

@@ -10,6 +10,10 @@
 import pytest
 import torch
 from executorch.backends.arm.quantizer import arm_quantizer
+from executorch.backends.arm.quantizer.arm_quantizer import (
+    get_symmetric_a16w8_quantization_config,
+    TOSAQuantizer,
+)
 from executorch.backends.arm.test import common, conftest
 from executorch.backends.arm.test.tester.test_pipeline import (
     EthosU55PipelineINT,
@@ -216,3 +220,46 @@ def test_add_tensor_vgf_INT(test_data: input_t1):
         tosa_version="TOSA-1.0+INT",
     )
     pipeline.run()
+
+
+def get_symmetric_a16w8_add_quantizer(u55_config=False, per_channel_quantization=False):
+    tosa_version = conftest.get_option("tosa_version")
+    tosa_profiles = {
+        "1.0": TosaSpecification.create_from_string("TOSA-1.0+INT+int16"),
+    }
+
+    quantizer = TOSAQuantizer(tosa_profiles[tosa_version])
+    quantizer.set_global(
+        get_symmetric_a16w8_quantization_config(is_per_channel=per_channel_quantization)
+    )
+
+    return Quantize(
+        quantizer,
+        get_symmetric_a16w8_quantization_config(
+            is_per_channel=per_channel_quantization
+        ),
+    )
+
+
+@common.parametrize("test_data", Add.test_data)
+def test_add_tensor_16a8w_tosa_INT(test_data: input_t1):
+    """Test add operation with 16A8W quantization (16-bit activations, 8-bit weights)"""
+    per_channel_quantization = False
+
+    pipeline = TosaPipelineINT[input_t1](
+        Add(),
+        test_data(),
+        aten_op,
+        exir_op=[],
+        per_channel_quantization=per_channel_quantization,
+        use_to_edge_transform_and_lower=True,
+        tosa_extensions=["int16"],
+    )
+
+    pipeline.change_args(
+        "quantize",
+        get_symmetric_a16w8_add_quantizer(
+            per_channel_quantization=per_channel_quantization
+        ),
+    )
+    pipeline.run()

backends/arm/test/targets.bzl

@@ -13,6 +13,7 @@ def define_arm_tests():
 
     # Operators
     test_files += [
+        "ops/test_add.py",
         "ops/test_avg_pool2d.py",
         "ops/test_linear.py", 
         "ops/test_slice.py",