Add a16w8 reduce_sum FVP coverage for Ethos-U85

Summary:
Adds an a16w8 (int16 IO + int8 weights) sweep for `aten.sum.dim_IntList` reducing the last dim with `keepdim=True`. The new tests `test_sum_dim_intlist_a16w8_{u55,u85}_INT` run on the standard Corstone-300 / Corstone-320 FVP harness and surface a numerics issue in the Ethos-U85 `ReduceSum` lowering at int16 IO precision (silent zero output). The Ethos-U55 path uses a different accumulator and is correct on the same OFM rescale.

## Context

Part of a stack that documents and fixes a numerics bug in the Vela 5.0 Ethos-U85 backend (`regor`). Plan + cross-references:

- **Plan:** {D103649006} ([Markup](https://internalfb.com/intern/markup/D103649006))
- **Step 1a (this diff):** ReduceSum-only a16w8 coverage in `test_sum.py` (LAND)
- **Step 1b-softmax:** {D103734699} -- `test_softmax.py` a16w8 MHA softmax sweep (LAND)
- **Step 1b-ops:** {D103760103} -- `test_softmax_ops.py` op-isolation harness (DNL)
- **Step 2a:** {D103760153} -- `regor` patch in third-party Vela 5.0 fork (LAND)
- **Step 2b:** {D103760514} -- DNL companion that drops `xfails=` from `test_sum.py` (lands in OSS only after upstream Vela syncs the fix)

## Test design

Tests use the standard `pipeline.run()` with the same a16w8 kwargs other arm a16w8 tests use (e.g. `test_native_layer_norm_16a8w_u85_INT` in `test_layer_norm.py`):

```
a16w8_quantization=True, symmetric_io_quantization=True, qtol=128, epsilon=2**-16
```

Numerical comparison is the standard `atol`/`rtol`-only check from `pipeline.run()` -- no SQNR helpers -- to stay consistent with the rest of `arm/test/ops/`.

The U85 cases are wrapped with `xfails=a16w8_sum_u85_xfails, strict=False`. `strict=False` keeps the test target green both on stock Vela 5.0 (cases XFAIL) *and* after Step 2a lands the Vela patch (cases XPASS, allowed under non-strict). Step 2b separately drops the `xfails=` argument once the upstream Vela fix syncs down.

The new U85 a16w8 test deliberately omits `common.XfailIfNoCorstone320` (which is present on the U55 sibling). Stacking that decorator with the per-id `xfails=` argument makes the per-id marks not fire (verified empirically) so the bug-firing cases would hard-fail instead of XFAIL. CI always has Corstone-320 installed; if it ever isn't, the test fails loudly with `FileNotFoundError`, which is the right signal for a missing-FVP misconfiguration. A code comment in the file documents this constraint.

## Scope note

This diff only **adds** new tests for the a16w8 path. It does not modify any existing tests in `test_sum.py` -- the pre-existing `Sum.test_parameters` (including the `dim_None` cases) is left as-is. Pre-existing `dim_None` test failures on `test_sum_u{55,85}_INT_1_0` are out of scope and unrelated to this diff.

Differential Revision: D103667823

Author: Ninja91

backends/arm/test/ops/test_sum.py

@@ -220,3 +220,68 @@ def test_sum_tosa_FP(test_data: Callable[[], input_t2]):
 def test_sum_tosa_INT(test_data: Callable[[], input_t2]):
     pipeline = TosaPipelineINT[input_t1](SumDefault(), test_data(), SumDefault.aten_op)
     pipeline.run()
+
+
+# a16w8 (int16 IO + int8 weights) coverage for sum.dim_IntList. Surfaces the
+# Ethos-U85 int16 ReduceSum silent-zero issue tracked upstream at
+# https://gitlab.arm.com/artificial-intelligence/ethos-u/ethos-u-vela/-/issues/23.
+
+
+class SumLastDim(torch.nn.Module):
+    """Reduce the last dim with keepdim=True."""
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return x.sum(dim=-1, keepdim=True)
+
+
+a16w8_sum_test_parameters = {
+    "rank1_16": lambda: (torch.rand(16),),
+    "rank3_8x1x16": lambda: (torch.rand(8, 1, 16),),
+    "rank3_4x4x16": lambda: (torch.rand(4, 4, 16),),
+}
+
+
+@common.parametrize("test_data", a16w8_sum_test_parameters)
+@common.XfailIfNoCorstone300
+def test_sum_dim_intlist_a16w8_u55_INT(test_data):
+    pipeline = EthosU55PipelineINT[input_t1](
+        SumLastDim(),
+        test_data(),
+        aten_op,
+        exir_ops=[],
+        a16w8_quantization=True,
+        symmetric_io_quantization=True,
+        qtol=128,
+        epsilon=2**-16,
+    )
+    pipeline.run()
+
+
+# Upstream Vela issue #23 (linked above). strict=False so the test target
+# stays green both on stock Vela 5.0 (cases XFAIL) and once the Vela fix is
+# in tree (cases XPASS). XfailIfNoCorstone320 is intentionally omitted --
+# stacking it with xfails= makes the per-id marks not fire.
+a16w8_sum_u85_xfails = {
+    case: "Ethos-U85 int16 ReduceSum returns zero (vela#23)"
+    for case in a16w8_sum_test_parameters
+}
+
+
+@common.parametrize(
+    "test_data",
+    a16w8_sum_test_parameters,
+    xfails=a16w8_sum_u85_xfails,
+    strict=False,
+)
+def test_sum_dim_intlist_a16w8_u85_INT(test_data):
+    pipeline = EthosU85PipelineINT[input_t1](
+        SumLastDim(),
+        test_data(),
+        aten_op,
+        exir_ops=[],
+        a16w8_quantization=True,
+        symmetric_io_quantization=True,
+        qtol=128,
+        epsilon=2**-16,
+    )
+    pipeline.run()

backends/arm/test/targets.bzl

@@ -30,6 +30,7 @@ def define_arm_tests():
         "ops/test_slice.py",
         "ops/test_sigmoid.py",
         "ops/test_sub.py",
+        "ops/test_sum.py",
         "ops/test_tanh.py",
         "ops/test_view.py",
         "ops/test_cos.py",