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 `a16w8_gelu_test_parameters` dict with 3 test configurations covering rank-1, rank-2, and rank-3 tensors
- Add `test_gelu_a16w8_u55_INT` using `EthosU55PipelineINT` with `a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16`
- 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

@@ -176,3 +176,42 @@ def test_gelu_vgf_quant(test_data: input_t1):
         quantize=True,
     )
     pipeline.run()
+
+
+a16w8_gelu_test_parameters = {
+    "rank1_rand": lambda: torch.rand(10),
+    "rank2_rand": lambda: torch.rand(8, 8) - 0.5,
+    "rank3_randn": lambda: torch.randn(1, 4, 4) + 2,
+}
+
+
+@common.parametrize("test_data", a16w8_gelu_test_parameters)
+@common.XfailIfNoCorstone300
+def test_gelu_a16w8_u55_INT(test_data: input_t1):
+    pipeline = EthosU55PipelineINT[input_t1](
+        Gelu(),
+        (test_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", a16w8_gelu_test_parameters)
+@common.XfailIfNoCorstone320
+def test_gelu_a16w8_u85_INT(test_data: input_t1):
+    pipeline = EthosU85PipelineINT[input_t1](
+        Gelu(),
+        (test_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