Test the IOQuantization pass does not have Q/DQ nodes

Change-Id: Ie3b466af5671f575d2b09e7775ce0b9a11920f2a

Author: gggekov

backends/arm/README.md

@@ -124,13 +124,13 @@ pytest -c /dev/null -v -n auto backends/arm/test --arm_run_corstoneFVP
 
 ## Passes
 
-With the default passes in the Arm Ethos-U backend, assuming the model lowers fully to the 
-Ethos-U, the exported program is composed of a Quantize node, Ethos-U custom delegate 
+With the default passes in the Arm Ethos-U backend, assuming the model lowers fully to the
+Ethos-U, the exported program is composed of a Quantize node, Ethos-U custom delegate
 and a Dequantize node. In some circumstances, you may want to feed quantized input to the Neural
-Network straight away, e.g. if you have a camera sensor outputting (u)int8 data and keep all the 
-arithmetic of the application in the int8 domain. For these cases, you can apply the 
+Network straight away, e.g. if you have a camera sensor outputting (u)int8 data and keep all the
+arithmetic of the application in the int8 domain. For these cases, you can apply the
 `exir/passes/quantize_io_pass.py`. See the unit test in `executorch/backends/arm/
-test/passes/test_ioquantization_pass.py`for an example how to feed quantized inputs and 
+test/passes/test_ioquantization_pass.py`for an example how to feed quantized inputs and
 obtain quantized outputs.
 
 

backends/arm/test/passes/test_ioquantization_pass.py

@@ -40,7 +40,27 @@ def test_ioquantisation_pass(self):
             .quantize()
             .export()
             .to_edge()
+            .check_count(
+                {
+                    "executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default": 3
+                }
+            )
+            .check_count(
+                {
+                    "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default": 3
+                }
+            )
             .partition()
+            .check_count(
+                {
+                    "executorch_exir_dialects_edge__ops_quantized_decomposed_quantize_per_tensor_default": 2
+                }
+            )
+            .check_count(
+                {
+                    "executorch_exir_dialects_edge__ops_quantized_decomposed_dequantize_per_tensor_default": 1
+                }
+            )
         )
         edge = tester.get_artifact()
         edge.transform(