NXP backend: Improve cifarnet speed by removing the initial pading. (pytorch#13279)

### Summary
NXP backend: Improve cifarnet speed by removing the initial pading.

### Test plan
Update to test_remove_io_quant_ops_pass__cifarnet() is part of the diff.

Author: jirioc

backends/nxp/tests/ir/edge_passes/test_remove_io_quant_ops_pass.py

@@ -58,12 +58,12 @@ def test_remove_io_quant_ops_pass__cifarnet():
     )
 
     nodes = list(exec_prog.exported_program().graph.nodes)
-    assert len(nodes) == 17
+    assert len(nodes) == 11
     assert (
         nodes[0].meta["val"].dtype == torch.int8
     ), "Input tensor doesn't have type INT8."
     assert (
-        nodes[16].meta["val"][0].dtype == torch.int8
+        nodes[10].meta["val"][0].dtype == torch.int8
     ), "Output tensor doesn't have type INT8."
 
     assert (

backends/nxp/tests/test_integration.py

@@ -1,4 +1,4 @@
-# Copyright 2024 NXP
+# Copyright 2024-2025 NXP
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -43,8 +43,8 @@ def test_cifarnet():
 
     delegation_info = get_delegation_info(exec_prog.exported_program().graph_module)
     assert delegation_info.num_delegated_subgraphs == 1
-    assert delegation_info.num_non_delegated_nodes == 17
-    assert delegation_info.num_delegated_nodes == 42
+    assert delegation_info.num_non_delegated_nodes == 11
+    assert delegation_info.num_delegated_nodes == 45
 
     nodes = list(exec_prog.exported_program().graph.nodes)
     assert nodes[2].name == "quantized_decomposed_quantize_per_tensor_default"

examples/nxp/experimental/cifar_net/cifar_net.pth

@@ -1,4 +1,4 @@
-# Copyright 2024 NXP
+# Copyright 2024-2025 NXP
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -57,7 +57,7 @@ class CifarNetModel(nn.Module):
     def __init__(self):
         super().__init__()
 
-        self.conv1 = nn.Conv2d(8, 32, 5)
+        self.conv1 = nn.Conv2d(3, 32, 5)
         self.conv2 = nn.Conv2d(32, 32, 5)
         self.conv3 = nn.Conv2d(32, 64, 5)
         self.pool1 = nn.MaxPool2d(2, 2)
@@ -66,10 +66,7 @@ def __init__(self):
         self.softmax = nn.Softmax(1)
 
     def forward(self, x):
-
-        # Neutron Backend does not yet have passses for automated padding if number of channels does not
-        # fit to Neutron constrains (#channels == #MAC units). So define the model explicitly tailored for Neutron-C-64.
-        x = F.pad(x, (2, 2, 2, 2, 0, 5))
+        x = F.pad(x, (2, 2, 2, 2))
         x = self.conv1(x)
         x = self.pool1(x)