Update on "jarvis-nightly-operators-test-aten-clamp-out"

Differential Revision: [D85364552](https://our.internmc.facebook.com/intern/diff/D85364552/)

[ghstack-poisoned]

Author: Zonglin Peng

backends/cadence/utils/facto_util.py

@@ -31,26 +31,26 @@ def _positive_valid_dim_list(tensor: torch.Tensor, length: int) -> set[tuple[int
     """
     Generate valid permutations using only positive dimension indices.
     This is required for Cadence/Xtensa kernels that don't support negative indexing.
-    
+
     Args:
         tensor: Input tensor to generate permutations for
         length: Number of dimensions in the permutation (must equal tensor.dim())
-    
+
     Returns:
         Set of valid permutation tuples containing only positive indices [0, rank-1]
     """
     if length > tensor.dim():
         return set()
-    
+
     n = tensor.dim()
     pool = list(range(n))
-    
+
     # Generate multiple valid permutations (only positive indices)
     permutations: set[tuple[int, ...]] = set()
     for _ in range(3):  # Generate 3 different permutations for diversity
         perm = tuple(rm.get_random().sample(pool, length))
         permutations.add(perm)
-    
+
     return permutations
 
 
@@ -202,7 +202,9 @@ def random_size_constraint(deps: object, r: int, d: int) -> int:
                     cp.Value.Le(lambda deps, dtype, struct: 2**4),
                     cp.Rank.Ge(lambda deps: 1),
                     cp.Size.Ge(lambda deps, r, d: 1),
-                    cp.Size.In(lambda deps, r, d: fn.broadcast_with(deps[0].shape, r, d)),
+                    cp.Size.In(
+                        lambda deps, r, d: fn.broadcast_with(deps[0].shape, r, d)
+                    ),
                     max_size_constraint,
                 ]
             else:  # input tensor(b)
@@ -213,7 +215,11 @@ def random_size_constraint(deps: object, r: int, d: int) -> int:
                     cp.Value.Le(lambda deps, dtype, struct: 2**4),
                     cp.Rank.Ge(lambda deps: 1),
                     cp.Size.Ge(lambda deps, r, d: 1),
-                    cp.Size.In(lambda deps, r, d: fn.broadcast_with(fn.broadcasted_shape(deps[0].shape, deps[1].shape), r, d)),
+                    cp.Size.In(
+                        lambda deps, r, d: fn.broadcast_with(
+                            fn.broadcasted_shape(deps[0].shape, deps[1].shape), r, d
+                        )
+                    ),
                     max_size_constraint,
                 ]
         case "embedding.default":
@@ -365,7 +371,9 @@ def random_size_constraint(deps: object, r: int, d: int) -> int:
             if index == 1:  # Only apply zero-prevention to divisor
                 tensor_constraints.extend(
                     [
-                        cp.Value.Ne(lambda deps, dtype, struct: 0),  # Prevent division by zero
+                        cp.Value.Ne(
+                            lambda deps, dtype, struct: 0
+                        ),  # Prevent division by zero
                         cp.Value.Le(lambda deps, dtype, struct: 2**3),
                         cp.Size.Le(lambda deps, r, d: 2**3),
                         cp.Rank.Le(lambda deps: 2**2),
@@ -400,7 +408,9 @@ def random_size_constraint(deps: object, r: int, d: int) -> int:
                     cp.Dtype.In(lambda deps: [torch.int64, torch.int32, torch.float32]),
                     cp.Value.Ge(lambda deps, dtype, struct: -(2**4)),
                     cp.Value.Le(lambda deps, dtype, struct: 2**4),
-                    cp.Value.Ne(lambda deps, dtype, struct: 0),  # Prevent division by zero
+                    cp.Value.Ne(
+                        lambda deps, dtype, struct: 0
+                    ),  # Prevent division by zero
                     cp.Rank.Ge(lambda deps: 1),
                     cp.Rank.Eq(lambda deps: deps[0].dim()),
                     cp.Size.Eq(lambda deps, r, d: fn.safe_size(deps[0], d)),
@@ -485,7 +495,9 @@ def facto_testcase_gen(  # noqa: C901
                         [
                             cp.Optional.Eq(lambda deps: False),  # Never None
                             cp.Value.Ge(lambda deps, dtype: -(2**4)),
-                            cp.Value.Le(lambda deps, dtype: 2**4 - 2),  # Leave room for max (at least 2 units)
+                            cp.Value.Le(
+                                lambda deps, dtype: 2**4 - 2
+                            ),  # Leave room for max (at least 2 units)
                         ]
                     )
                 elif in_spec.name == "max":
@@ -494,7 +506,9 @@ def facto_testcase_gen(  # noqa: C901
                     spec.inspec[index].constraints.extend(
                         [
                             cp.Optional.Eq(lambda deps: False),  # Never None
-                            cp.Value.Ge(lambda deps, dtype: deps[1] + 2),  # max >= min + 2 (sufficient gap)
+                            cp.Value.Ge(
+                                lambda deps, dtype: deps[1] + 2
+                            ),  # max >= min + 2 (sufficient gap)
                             cp.Value.Le(lambda deps, dtype: 2**4),
                         ]
                     )
@@ -540,7 +554,9 @@ def facto_testcase_gen(  # noqa: C901
                 spec.inspec[index].constraints.extend(
                     [
                         cp.Length.Ge(lambda deps: 1),
-                        cp.Length.Eq(lambda deps: deps[0].dim()),  # Must be a complete permutation
+                        cp.Length.Eq(
+                            lambda deps: deps[0].dim()
+                        ),  # Must be a complete permutation
                         cp.Optional.Eq(lambda deps: False),
                         # Generate valid permutations using only positive indices
                         # Cadence/Xtensa hardware kernels do not support negative dimension indices