Cleanup XNN delegate post removal of upsample decomposition

Summary: Following the removal of the decompositions for upsample_bilinear2d in PyTorch, we don't need to pattern match and recompose upsample_bilinear2d. This PR cleans up the convert_to_upsample_bilinear2d pass and associated logic.

Differential Revision: D68374585

Author: GregoryComer

backends/xnnpack/_passes/__init__.py

@@ -14,9 +14,6 @@
 )
 from executorch.backends.xnnpack._passes.convert_to_linear import ConvertToLinearPass
 from executorch.backends.xnnpack._passes.convert_to_sdpa import ConvertToSDPAPass
-from executorch.backends.xnnpack._passes.convert_to_upsample_bilinear2d import (
-    ConvertToUpsampleBilinear2d,
-)
 from executorch.backends.xnnpack._passes.decompose_cat import DecomposeConcatenate
 from executorch.backends.xnnpack._passes.fuse_activation_pass import FuseActivationPass
 from executorch.backends.xnnpack._passes.fuse_batch_norm_with_conv import (
@@ -58,7 +55,6 @@ def __init__(
             self.passes = [
                 # TODO - remove this pass once we have a better support for dim_order ops lowering
                 DimOrderOpsRevertPass,
-                ConvertToUpsampleBilinear2d,
                 ConvertToLinearPass,
                 ConvertToSDPAPass,
                 ConstPropPass,

backends/xnnpack/_passes/convert_to_upsample_bilinear2d.py

@@ -133,17 +133,9 @@ def test_fp32_bilinear2d_dynamic_bilinear2d_not_partitioned(self):
                 3: torch.export.Dim("w", min=1, max=12),
             }
         }
-        artifact_str = str(
+        (
             Tester(self.StaticResizeBilinear2dModule(), example_inputs)
             .export(Export(dynamic_shapes))
             .to_edge_transform_and_lower()
-            .get_artifact()
-            .exported_program()
-        )
-        # NOTE The decomposition can be partially delegated. This will need to be replaced
-        # with the aten upsample op once decomp is removed.
-        self.assertTrue(
-            "executorch_exir_dialects_edge__ops_aten_index_Tensor" in artifact_str
-            or "executorch_exir_dialects_edge__ops_aten_upsample_bilinear2d_vec"
-            in artifact_str
+            .check("executorch_exir_dialects_edge__ops_aten_upsample_bilinear2d_vec")
         )