[MIGraphX EP Support] Update migx scripts (#21806)

### Description
<!-- Describe your changes. -->
No code changes to the EP only changes to the scripts whihc invoke
MIGraphX EP

- One case be explicit to set MIGraphX EP when running gpt2 testing
- The other to ensure we turn off optimizations like tensorRT and allow
MIGraphX to handle graph optimizations


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
MIGraphX has moved away from using rocBLAS and without this, some cases
used in CI shall fail as optmizations will attempt to use rocBLAS
kernels instead of MIGraphx EP directly.

onnxruntime/python/tools/transformers/benchmark.py

@@ -135,6 +135,15 @@ def run_onnxruntime(
             )
             return results
 
+    if provider == "migraphx":
+        optimizer_info = OptimizerInfo.NOOPT
+        warm_up_repeat = 5
+        if "MIGraphXExecutionProvider" not in onnxruntime.get_available_providers():
+            logger.error(
+                "Please install onnxruntime-rocm package, and use a machine with GPU for testing gpu performance."
+            )
+            return results
+
     if optimizer_info == OptimizerInfo.NOOPT:
         logger.warning(
             f"OptimizerInfo is set to {optimizer_info}, graph optimizations specified in FusionOptions are not applied."

onnxruntime/python/tools/transformers/models/gpt2/convert_to_onnx.py

@@ -370,8 +370,12 @@ def main(argv=None, experiment_name: str = "", run_id: str = "0", csv_filename:
     logger.info(f"Output path: {output_path}")
     model_size_in_MB = int(get_onnx_model_size(output_path, args.use_external_data_format) / 1024 / 1024)  # noqa: N806
 
+    provider = args.provider
+    if args.provider == "migraphx":
+        provider = "MIGraphXExecutionProvider"
+
     session = create_onnxruntime_session(
-        output_path, args.use_gpu, args.provider, enable_all_optimization=True, verbose=args.verbose
+        output_path, args.use_gpu, provider, enable_all_optimization=True, verbose=args.verbose
     )
     if args.model_class == "GPT2LMHeadModel" and session is not None:
         parity_result = gpt2helper.test_parity(