Add a16w8 per-op test for gelu (#19598)

Summary:

Add int16 activation / int8 weight (a16w8) quantization tests for `aten.gelu` on Ethos-U55 and Ethos-U85.

## Changes
- Add `test_gelu_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16`, reusing existing `Gelu.test_data` parameters (12 test configurations covering both \`none\` and \`tanh\` approximation modes)
- Add `test_gelu_a16w8_u85_INT` using `EthosU85PipelineINT` with same kwargs
- Register `ops/test_gelu.py` in `fbcode/` and `xplat/` `targets.bzl`

bypass-pytorch-oss-checks

Differential Revision: D104532359

Author: christine-long-meta

backends/arm/test/ops/test_gelu.py

@@ -6,6 +6,7 @@
 from typing import Tuple
 
 import torch
+
 from executorch.backends.arm.test import common
 from executorch.backends.arm.test.tester.test_pipeline import (
     EthosU55PipelineINT,
@@ -176,3 +177,37 @@ def test_gelu_vgf_quant(test_data: input_t1):
         quantize=True,
     )
     pipeline.run()
+
+
+@common.parametrize("test_data", Gelu.test_data)
+@common.XfailIfNoCorstone300
+def test_gelu_a16w8_u55_INT(test_data: input_t1):
+    approximate, data = test_data()
+    pipeline = EthosU55PipelineINT[input_t1](
+        Gelu(approximate),
+        (data,),
+        Gelu.aten_op,
+        Gelu.exir_op,
+        a16w8_quantization=True,
+        symmetric_io_quantization=True,
+        qtol=128,
+        epsilon=2**-16,
+    )
+    pipeline.run()
+
+
+@common.parametrize("test_data", Gelu.test_data)
+@common.XfailIfNoCorstone320
+def test_gelu_a16w8_u85_INT(test_data: input_t1):
+    approximate, data = test_data()
+    pipeline = EthosU85PipelineINT[input_t1](
+        Gelu(approximate),
+        (data,),
+        Gelu.aten_op,
+        Gelu.exir_op,
+        a16w8_quantization=True,
+        symmetric_io_quantization=True,
+        qtol=128,
+        epsilon=2**-16,
+    )
+    pipeline.run()

backends/arm/test/targets.bzl

@@ -41,6 +41,7 @@ def define_arm_tests():
         "ops/test_mean_dim.py",
         "ops/test_var.py",
         "ops/test_conv1d.py",
+        "ops/test_gelu.py",
     ]
 
     # Quantization