Update on "[Jarvis][Nightly] address error jarvis-nightly-operators-test-aten-permute-copy-out"

https://docs.google.com/spreadsheets/d/12DsKcvPcGgxnZ8shgn6j8PmoOQUfy5GgUg974g1iO18/edit?gid=0#gid=0

Differential Revision: [D85364547](https://our.internmc.facebook.com/intern/diff/D85364547/)

[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
 
 
@@ -375,7 +375,9 @@ 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),
@@ -410,7 +412,9 @@ 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)),
@@ -522,7 +526,9 @@ 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