Add files using upload-large-folder tool

benchmark_threading.py

@@ -0,0 +1,302 @@
+import os
+import time
+import argparse
+import subprocess
+import platform
+from typing import Optional, Tuple, Dict
+import threading
+import numpy as np
+from onnx import load, ModelProto
+import onnxruntime as ort
+
+os.environ["XLNX_ENABLE_CACHE"] = "0"
+os.environ["PATH"] += (
+    os.pathsep + f"{os.environ['CONDA_PREFIX']}\\Lib\\site-packages\\flexmlrt\\lib"
+)
+
+XRT_SMI_PATH = "C:\\Windows\\System32\\AMD\\xrt-smi.exe"
+
+ONNX_DTYPE_TO_NP = {
+    "tensor(float)": np.float32,
+    "tensor(float16)": np.float16,
+    "tensor(int64)": np.int64,
+    "tensor(int32)": np.int32,
+    "tensor(uint16)": np.uint16,
+    "tensor(int16)": np.int16,
+    "tensor(uint8)": np.uint8,
+    "tensor(int8)": np.int8,
+}
+
+
+def generate_rand_data_from_onnx(
+    model: ModelProto,
+    lowest_int_val: Optional[int],
+    highest_int_val: Optional[int],
+) -> Dict[str, np.ndarray]:
+    # Load the models
+
+    sess = ort.InferenceSession(
+        model.SerializePartialToString(), providers=["CPUExecutionProvider"]
+    )
+
+    inps = {}
+    # Iterate over the first models inputs and generate random data
+    for inp in sess.get_inputs():
+        inp_shapes = list(inp.shape)  # mutable
+        for inp_shape in inp_shapes:
+            assert isinstance(
+                inp_shape, int
+            ), f"Found dynamic axes: {inp_shape}. Please freeze."
+        np_type = ONNX_DTYPE_TO_NP[inp.type]
+        if np.issubdtype(np_type, np.integer):
+            iinfo = np.iinfo(np_type)
+            if lowest_int_val is None:
+                lowest_int_val = iinfo.min
+            if highest_int_val is None:
+                lowest_int_val = iinfo.max
+            inps[inp.name] = np.random.randint(
+                lowest_int_val, highest_int_val, size=tuple(inp_shapes), dtype=np_type
+            )
+        else:
+            inps[inp.name] = np.random.rand(*inp_shapes).astype(np_type)
+
+    return inps
+
+
+def configure_npu_power(p_mode: Optional[str] = None) -> Tuple[int, str, str]:
+    """
+    Configures the NPU power state using xrt-smi.exe.
+
+    Args:
+        p_mode (string, optional): The desired power mode (p-mode).
+            If None, displays current status.
+            Refer to xrt-smi documentation for valid p-modes.
+    Returns:
+        tuple: (return_code, stdout, stderr) from the subprocess call.
+               return_code is an integer, stdout and stderr are strings.
+    Raises:
+        OSError: If xrt-smi.exe is not found.
+    """
+
+    if platform.system() != "Windows":
+        return (-1, "xrt-smi.exe is only available on Windows.", "")
+
+    try:
+        if p_mode is not None:
+            command = [XRT_SMI_PATH, "configure", "--pmode", str(p_mode)]
+        else:
+            command = [
+                XRT_SMI_PATH,
+                "examine",
+                "--report",
+                "platform",
+            ]  # Just display status
+
+        process = subprocess.Popen(
+            command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True
+        )
+        stdout, stderr = process.communicate()
+        return_code = process.returncode
+
+        if return_code != 0:
+            print(f"Error executing xrt-smi.exe: {stderr}")
+
+        return return_code, stdout, stderr
+
+    except FileNotFoundError:
+        raise OSError("xrt-smi.exe not found.")
+    except Exception as e:  # pylint: disable=broad-except
+        print(f"An unexpected error occurred: {e}")
+        return -1, "", str(e)
+
+
+def main(
+    model_file: str,
+    vaip_config: str,
+    cache_path: str,
+    device: str,
+    pmode: str,
+    warmup_runs: int,
+    inferences: int,
+    lowest_int_value: Optional[int],
+    highest_int_value: Optional[int],
+    threads: int,
+):
+
+    assert os.path.exists(model_file)
+
+    assert threads >= 1
+
+    if device == "cpu":
+        ort_session = ort.InferenceSession(
+            model_file,
+            providers=["CPUExecutionProvider"],
+        )
+
+    elif device == "npu":
+        assert os.path.exists(vaip_config)
+        assert os.path.exists(cache_path)
+        cache_dir = os.path.dirname(os.path.abspath(cache_path))
+        cache_key = os.path.basename(cache_path)
+        print(f"Using cache directory {cache_dir} with key {cache_key}")
+
+        ret_code, stdout, stderr = configure_npu_power(pmode)
+        print(stdout)
+        if ret_code != 0:
+            print("Error configuring npu power mode.")
+            print(stderr)
+
+        sess_options = ort.SessionOptions()
+        ort_session = ort.InferenceSession(
+            model_file,
+            providers=["VitisAIExecutionProvider"],
+            sess_options=sess_options,
+            provider_options=[
+                {
+                    "config_file": vaip_config,
+                    "cacheDir": cache_dir,
+                    "cacheKey": cache_key,
+                }
+            ],
+        )
+
+    elif device == "igpu":
+        ort_session = ort.InferenceSession(
+            model_file,
+            providers=["DmlExecutionProvider"],
+            provider_options=[{"device_id": 2}],
+        )
+
+    onnx_inputs = generate_rand_data_from_onnx(
+        load(model_file),
+        lowest_int_val=lowest_int_value,
+        highest_int_val=highest_int_value,
+    )
+
+    # Warmup
+    for _ in range(warmup_runs):
+        ort_session.run(None, onnx_inputs)
+
+    def run_inference(runs, session, inputs):
+        for _ in range(runs):
+            session.run(None, inputs)
+
+    latencies = []
+    num_threads = threads
+    threads_list = []
+    inferences_per_thread = inferences // num_threads
+    remainder = inferences % num_threads
+    print(f"inferences per thread: {inferences_per_thread}, remainder: {remainder}")
+    start = time.perf_counter()
+    for i in range(num_threads):
+        num_runs = inferences_per_thread + (1 if i < remainder else 0)
+        thread = threading.Thread(
+            target=run_inference, args=(num_runs, ort_session, onnx_inputs)
+        )
+        threads_list.append(thread)
+        thread.start()
+
+    for thread in threads_list:
+        thread.join()
+
+    end = time.perf_counter()
+    latencies.append((end - start) / inferences)
+    print(f"Latencies: {latencies}")
+    print(f"Benchmark results averaged over {inferences} inferences targeting {device}")
+    print("Average latency (ms): ", round(np.mean(latencies) * 1e3, 3))
+    print("Average throughput (inf/s): ", round(1 / np.mean(latencies), 3))
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="",
+    )
+
+    parser.add_argument(
+        "--pmode",
+        type=str,
+        choices=["default", "powersaver", "balanced", "performance", "turbo"],
+        default="default",
+        help="Desired power mode.",
+    )
+
+    parser.add_argument(
+        "onnx_model",
+        type=str,
+        help="Provide the onnx model file.",
+    )
+
+    parser.add_argument(
+        "--vai-config",
+        type=str,
+        help="Path to the vaip configuration json file.",
+    )
+
+    parser.add_argument(
+        "--cache-path",
+        required=False,
+        type=str,
+        help="Path to the saved compilation directory.",
+    )
+
+    parser.add_argument(
+        "--device",
+        required=False,
+        type=str,
+        default="npu",
+        choices=["npu", "cpu", "igpu"],
+        help="Select the device to run the measurements on.",
+    )
+
+    parser.add_argument(
+        "--warmup-runs",
+        required=False,
+        default=10,
+        type=int,
+        help="The number of inferences to run before capturing performance.",
+    )
+
+    parser.add_argument(
+        "--inferences",
+        required=False,
+        default=100,
+        type=int,
+        help="The number of inferences to average performance over.",
+    )
+
+    parser.add_argument(
+        "--lowest-int-value",
+        required=False,
+        type=int,
+        help="Lowest value the rng will produce if the model has an integer input type.",
+    )
+
+    parser.add_argument(
+        "--highest-int-value",
+        required=False,
+        type=int,
+        help="Highest value the rng will produce if the model has an integer input type.",
+    )
+
+    parser.add_argument(
+        "--threads",
+        default=1,
+        required=False,
+        type=int,
+        help="The number of threads that are used to run the inferences.",
+    )
+
+    args = parser.parse_args()
+
+    main(
+        args.onnx_model,
+        args.vai_config,
+        args.cache_path,
+        args.device,
+        args.pmode,
+        args.warmup_runs,
+        args.inferences,
+        args.lowest_int_value,
+        args.highest_int_value,
+        args.threads,
+    )

segmentation_1_4_0_fp32_combined/aie_unsupported_original_ops.json

@@ -0,0 +1,13 @@
+[
+  "Cast_0",
+  "Transpose_10",
+  "Transpose_11",
+  "Transpose_12",
+  "Transpose_448",
+  "Transpose_449",
+  "Transpose_450",
+  "Transpose_451",
+  "Transpose_452",
+  "Transpose_453",
+  "Transpose_9"
+]

segmentation_1_4_0_fp32_combined/context.json

@@ -0,0 +1,1052 @@
+{
+ "metaDef": [
+  {
+   "id": "vaiml_par_0",
+   "inputs": [
+    "385",
+    "394",
+    "395",
+    "396",
+    "397"
+   ],
+   "outputs": [
+    "921",
+    "894",
+    "868",
+    "832",
+    "796",
+    "916"
+   ],
+   "nodes": [
+    "921",
+    "909",
+    "908",
+    "907",
+    "1081",
+    "904",
+    "1078",
+    "901",
+    "900",
+    "895",
+    "894",
+    "893",
+    "889",
+    "888",
+    "887",
+    "886",
+    "884",
+    "883",
+    "882",
+    "881",
+    "879",
+    "878",
+    "1075",
+    "875",
+    "874",
+    "869",
+    "868",
+    "867",
+    "863",
+    "862",
+    "861",
+    "860",
+    "858",
+    "857",
+    "856",
+    "855",
+    "853",
+    "852",
+    "1072",
+    "849",
+    "848",
+    "838",
+    "833",
+    "832",
+    "831",
+    "827",
+    "826",
+    "825",
+    "824",
+    "822",
+    "821",
+    "820",
+    "819",
+    "817",
+    "816",
+    "1069",
+    "813",
+    "812",
+    "802",
+    "797",
+    "796",
+    "795",
+    "791",
+    "790",
+    "789",
+    "788",
+    "786",
+    "785",
+    "784",
+    "783",
+    "781",
+    "777",
+    "776",
+    "775",
+    "774",
+    "770",
+    "769",
+    "767",
+    "764",
+    "1063",
+    "760",
+    "1060",
+    "757",
+    "756",
+    "754",
+    "751",
+    "749",
+    "748",
+    "747",
+    "746",
+    "745",
+    "744",
+    "742",
+    "739",
+    "1057",
+    "735",
+    "734",
+    "732",
+    "729",
+    "1054",
+    "725",
+    "1051",
+    "722",
+    "721",
+    "719",
+    "716",
+    "714",
+    "713",
+    "712",
+    "711",
+    "710",
+    "709",
+    "707",
+    "704",
+    "1048",
+    "700",
+    "699",
+    "697",
+    "694",
+    "1045",
+    "1042",
+    "688",
+    "687",
+    "685",
+    "682",
+    "680",
+    "679",
+    "678",
+    "677",
+    "676",
+    "675",
+    "673",
+    "670",
+    "1039",
+    "666",
+    "665",
+    "663",
+    "660",
+    "1036",
+    "656",
+    "1033",
+    "653",
+    "652",
+    "650",
+    "647",
+    "645",
+    "644",
+    "643",
+    "642",
+    "641",
+    "640",
+    "638",
+    "635",
+    "1030",
+    "631",
+    "630",
+    "628",
+    "625",
+    "1027",
+    "1024",
+    "619",
+    "618",
+    "616",
+    "613",
+    "611",
+    "610",
+    "609",
+    "608",
+    "607",
+    "606",
+    "604",
+    "601",
+    "1021",
+    "597",
+    "596",
+    "594",
+    "591",
+    "1018",
+    "587",
+    "1015",
+    "584",
+    "583",
+    "581",
+    "578",
+    "1012",
+    "574",
+    "573",
+    "571",
+    "568",
+    "1009",
+    "564",
+    "1006",
+    "561",
+    "560",
+    "558",
+    "555",
+    "1003",
+    "551",
+    "550",
+    "548",
+    "545",
+    "1000",
+    "541",
+    "997",
+    "538",
+    "537",
+    "535",
+    "532",
+    "994",
+    "528",
+    "527",
+    "525",
+    "522",
+    "991",
+    "988",
+    "516",
+    "515",
+    "513",
+    "510",
+    "985",
+    "506",
+    "505",
+    "503",
+    "500",
+    "982",
+    "496",
+    "979",
+    "493",
+    "492",
+    "490",
+    "487",
+    "485",
+    "484",
+    "483",
+    "482",
+    "481",
+    "976",
+    "478",
+    "973",
+    "475",
+    "970",
+    "472",
+    "471",
+    "469",
+    "466",
+    "464",
+    "463",
+    "462",
+    "461",
+    "460",
+    "967",
+    "457",
+    "964",
+    "961",
+    "452",
+    "451",
+    "449",
+    "446",
+    "444",
+    "443",
+    "442",
+    "441",
+    "440",
+    "958",
+    "437",
+    "955",
+    "434",
+    "952",
+    "431",
+    "949",
+    "428",
+    "946",
+    "943",
+    "423",
+    "940",
+    "420",
+    "937",
+    "417",
+    "934",
+    "414",
+    "931",
+    "411",
+    "410",
+    "408",
+    "405",
+    "928",
+    "401",
+    "399",
+    "393",
+    "392",
+    "387",
+    "773",
+    "1066",
+    "794",
+    "793",
+    "780",
+    "779",
+    "778",
+    "830",
+    "829",
+    "866",
+    "865",
+    "892",
+    "891",
+    "916",
+    "911"
+   ],
+   "constantInitializers": [
+    "1001",
+    "1002",
+    "1004",
+    "1005",
+    "1007",
+    "1008",
+    "1010",
+    "1011",
+    "1013",
+    "1014",
+    "1016",
+    "1017",
+    "1019",
+    "1020",
+    "1022",
+    "1023",
+    "1025",
+    "1026",
+    "1028",
+    "1029",
+    "1031",
+    "1032",
+    "1034",
+    "1035",
+    "1037",
+    "1038",
+    "1040",
+    "1041",
+    "1043",
+    "1044",
+    "1046",
+    "1047",
+    "1049",
+    "1050",
+    "1052",
+    "1053",
+    "1055",
+    "1056",
+    "1058",
+    "1059",
+    "1061",
+    "1062",
+    "1064",
+    "1065",
+    "1067",
+    "1068",
+    "1070",
+    "1071",
+    "1073",
+    "1074",
+    "1076",
+    "1077",
+    "1079",
+    "1080",
+    "1082",
+    "1083",
+    "1086",
+    "1090",
+    "386",
+    "388",
+    "389",
+    "398",
+    "400",
+    "752",
+    "755",
+    "763",
+    "801",
+    "809",
+    "837",
+    "845",
+    "847",
+    "873",
+    "890",
+    "899",
+    "929",
+    "930",
+    "932",
+    "933",
+    "935",
+    "936",
+    "938",
+    "939",
+    "941",
+    "942",
+    "944",
+    "945",
+    "947",
+    "948",
+    "950",
+    "951",
+    "953",
+    "954",
+    "956",
+    "957",
+    "959",
+    "960",
+    "962",
+    "963",
+    "965",
+    "966",
+    "968",
+    "969",
+    "971",
+    "972",
+    "974",
+    "975",
+    "977",
+    "978",
+    "980",
+    "981",
+    "983",
+    "984",
+    "986",
+    "987",
+    "989",
+    "990",
+    "992",
+    "993",
+    "995",
+    "996",
+    "998",
+    "999",
+    "aspp.aspp2.1.weight",
+    "backbone.features.11.block.2.fc1.bias",
+    "backbone.features.11.block.2.fc1.weight",
+    "backbone.features.11.block.2.fc2.bias",
+    "backbone.features.11.block.2.fc2.weight",
+    "backbone.features.12.block.2.fc1.bias",
+    "backbone.features.12.block.2.fc1.weight",
+    "backbone.features.12.block.2.fc2.bias",
+    "backbone.features.12.block.2.fc2.weight",
+    "backbone.features.13.block.2.fc1.bias",
+    "backbone.features.13.block.2.fc1.weight",
+    "backbone.features.13.block.2.fc2.bias",
+    "backbone.features.13.block.2.fc2.weight",
+    "backbone.features.14.block.2.fc1.bias",
+    "backbone.features.14.block.2.fc1.weight",
+    "backbone.features.14.block.2.fc2.bias",
+    "backbone.features.14.block.2.fc2.weight",
+    "backbone.features.15.block.2.fc1.bias",
+    "backbone.features.15.block.2.fc1.weight",
+    "backbone.features.15.block.2.fc2.bias",
+    "backbone.features.15.block.2.fc2.weight",
+    "backbone.features.4.block.2.fc1.bias",
+    "backbone.features.4.block.2.fc1.weight",
+    "backbone.features.4.block.2.fc2.bias",
+    "backbone.features.4.block.2.fc2.weight",
+    "backbone.features.5.block.2.fc1.bias",
+    "backbone.features.5.block.2.fc1.weight",
+    "backbone.features.5.block.2.fc2.bias",
+    "backbone.features.5.block.2.fc2.weight",
+    "backbone.features.6.block.2.fc1.bias",
+    "backbone.features.6.block.2.fc1.weight",
+    "backbone.features.6.block.2.fc2.bias",
+    "backbone.features.6.block.2.fc2.weight",
+    "decoder.decode1.gru.hh.0.bias",
+    "decoder.decode1.gru.hh.0.weight",
+    "decoder.decode1.gru.ih.0.bias",
+    "decoder.decode1.gru.ih.0.weight",
+    "decoder.decode2.gru.hh.0.bias",
+    "decoder.decode2.gru.hh.0.weight",
+    "decoder.decode2.gru.ih.0.bias",
+    "decoder.decode2.gru.ih.0.weight",
+    "decoder.decode3.gru.hh.0.bias",
+    "decoder.decode3.gru.hh.0.weight",
+    "decoder.decode3.gru.ih.0.bias",
+    "decoder.decode3.gru.ih.0.weight",
+    "decoder.decode4.gru.hh.0.bias",
+    "decoder.decode4.gru.hh.0.weight",
+    "decoder.decode4.gru.ih.0.bias",
+    "decoder.decode4.gru.ih.0.weight",
+    "project_mat.conv.bias",
+    "project_mat.conv.weight"
+   ],
+   "device": "VAIML",
+   "vaimlParam": {
+    "vaimlModelPath": "./segmentation_1_4_0_fp32_combined/vaiml_par_0",
+    "deviceName": "stx",
+    "outputShapes": [
+     {
+      "shapes": [
+       "1",
+       "1",
+       "180",
+       "320"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "16",
+       "90",
+       "160"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "20",
+       "45",
+       "80"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "40",
+       "23",
+       "40"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "64",
+       "12",
+       "20"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "3",
+       "180",
+       "320"
+      ]
+     }
+    ],
+    "inputShapes": [
+     {
+      "shapes": [
+       "1",
+       "180",
+       "320",
+       "4"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "16",
+       "90",
+       "160"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "20",
+       "45",
+       "80"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "40",
+       "23",
+       "40"
+      ]
+     },
+     {
+      "shapes": [
+       "1",
+       "64",
+       "12",
+       "20"
+      ]
+     }
+    ],
+    "vaimlUnarchivePath": "./segmentation_1_4_0_fp32_combined",
+    "subgraphName": "vaiml_par_0",
+    "priority": "normal",
+    "configJson": "vitisai_config.json",
+    "deviceBatchSize": 1,
+    "inputNames": [
+     "385",
+     "394",
+     "395",
+     "396",
+     "397"
+    ],
+    "outputNames": [
+     "921",
+     "894",
+     "868",
+     "832",
+     "796",
+     "916"
+    ]
+   }
+  }
+ ],
+ "config": {
+  "passes": [
+   {
+    "name": "init",
+    "plugin": "vaip-pass_init"
+   },
+   {
+    "name": "vaiml_partition",
+    "plugin": "vaip-pass_vaiml_partition",
+    "vaimlConfig": {
+     "device": "stx",
+     "enableF32ToBf16Conversion": true,
+     "keepOutputs": true
+    }
+   }
+  ],
+  "cacheDir": "/tmp/vaip/.cache",
+  "cacheKey": "4e8d9ee8719e050537726a1cd8f79305",
+  "version": {
+   "versionInfos": [
+    {
+     "packageName": "vaip",
+     "commit": "e4ca074a034e568a2fd44af176f112e64e845411",
+     "version": "vaip.1.0.0"
+    },
+    {
+     "packageName": "target_factory",
+     "commit": "60f0780e75861ed37681e00c5eeeaf132f887c45",
+     "version": "target-factory.3.5.0"
+    },
+    {
+     "packageName": "vart",
+     "commit": "01141f8d14af4be8a1229d3d5dd93f26ba608f58",
+     "version": "vart"
+    },
+    {
+     "packageName": "xcompiler",
+     "commit": "8ccbd710317a738251bbddcebb919fd0e8145250",
+     "version": "xcompiler.3.5.0"
+    },
+    {
+     "packageName": "onnxrutnime",
+     "commit": "5c1b7ccbff7e5141c1da7a9d963d660e5741c319",
+     "version": "onnxruntime.1.20.1"
+    },
+    {
+     "packageName": "xir",
+     "commit": "bef5d269fc06f065c5f8de5ba202d6f02edfad7f",
+     "version": "xir.3.5.0"
+    },
+    {
+     "packageName": "xrt",
+     "commit": "acc144998d650acbfda7e5919a1290de8f8c7735",
+     "version": "xrt.2.19.72"
+    },
+    {
+     "packageName": "graph_engine",
+     "commit": "d7385f8afa5f6eb7d5d4452749b0e07bce67b75b",
+     "version": "graph_engine"
+    }
+   ]
+  },
+  "onnxPath": "segmentation_1_4_0_fp32_combined.onnx",
+  "sessionOptions": {
+   "config_file": "vitisai_config.json"
+  },
+  "enableCacheFileIoInMem": false
+ },
+ "events": [
+  {
+   "name": "before_compile_onnx_model_internal",
+   "ph": "X",
+   "ts": "31561",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "30664"
+  },
+  {
+   "id": "before_compile_onnx_model_internal_mem_usage_1",
+   "ph": "v",
+   "ts": "31561",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "before_compile_onnx_model_internal_mem_usage_2",
+   "ph": "v",
+   "ts": "62226",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "check_cache_hit",
+   "ph": "X",
+   "ts": "62248",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "25"
+  },
+  {
+   "id": "check_cache_hit_mem_usage_1",
+   "ph": "v",
+   "ts": "62248",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "check_cache_hit_mem_usage_2",
+   "ph": "v",
+   "ts": "62273",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "0-init@vaip-pass_init",
+   "ph": "X",
+   "ts": "65069",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "11"
+  },
+  {
+   "id": "0-init@vaip-pass_init_mem_usage_1",
+   "ph": "v",
+   "ts": "65069",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "0-init@vaip-pass_init_mem_usage_2",
+   "ph": "v",
+   "ts": "65080",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "1-vaiml_partition@vaip-pass_vaiml_partition",
+   "ph": "X",
+   "ts": "65090",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "8266564167"
+  },
+  {
+   "id": "1-vaiml_partition@vaip-pass_vaiml_partition_mem_usage_1",
+   "ph": "v",
+   "ts": "65090",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "1-vaiml_partition@vaip-pass_vaiml_partition_mem_usage_2",
+   "ph": "v",
+   "ts": "8266629258",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "update_cache",
+   "ph": "X",
+   "ts": "62287",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "8266568873"
+  },
+  {
+   "id": "update_cache_mem_usage_1",
+   "ph": "v",
+   "ts": "62287",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "update_cache_mem_usage_2",
+   "ph": "v",
+   "ts": "8266631160",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "read_cache",
+   "ph": "X",
+   "ts": "8266632901",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "1033"
+  },
+  {
+   "id": "read_cache_mem_usage_1",
+   "ph": "v",
+   "ts": "8266632901",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "read_cache_mem_usage_2",
+   "ph": "v",
+   "ts": "8266633935",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "after_compile_onnx_model_internal",
+   "ph": "X",
+   "ts": "8266633946",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "26451"
+  },
+  {
+   "id": "after_compile_onnx_model_internal_mem_usage_1",
+   "ph": "v",
+   "ts": "8266633946",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "after_compile_onnx_model_internal_mem_usage_2",
+   "ph": "v",
+   "ts": "8266660397",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "compile_onnx_model_internal",
+   "ph": "X",
+   "ts": "31560",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "8266628844"
+  },
+  {
+   "id": "compile_onnx_model_internal_mem_usage_1",
+   "ph": "v",
+   "ts": "31560",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "compile_onnx_model_internal_mem_usage_2",
+   "ph": "v",
+   "ts": "8266660404",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "name": "compile_onnx_model_3",
+   "ph": "X",
+   "ts": "31447",
+   "pid": "214",
+   "tid": "214",
+   "args": {
+    "memUsage": {}
+   },
+   "dur": "8266629035"
+  },
+  {
+   "id": "compile_onnx_model_3_mem_usage_1",
+   "ph": "v",
+   "ts": "31447",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  },
+  {
+   "id": "compile_onnx_model_3_mem_usage_2",
+   "ph": "v",
+   "ts": "8266660483",
+   "pid": "214",
+   "args": {
+    "dumps": {
+     "process_totals": {
+      "peak_memory": "0",
+      "current_memory": "0"
+     }
+    }
+   }
+  }
+ ],
+ "cpuUsage": [
+  {
+   "avgCpuUtil": 75.2757797,
+   "memPeakWorkingSetSize": 1998.73828
+  }
+ ],
+ "cacheFiles": [
+  "context.json"
+ ]
+}

segmentation_1_4_0_fp32_combined/final-vaiml-pass-summary.txt

@@ -0,0 +1,23 @@
+--------- Final Summary of VAIML Pass ----------
+VAIP commit: e4ca074a034e568a2fd44af176f112e64e845411
+Model: segmentation_1_4_0_fp32_combined.onnx
+Model signature: 6bbb891ab96ca9362e0e61024cd02778
+Device: stx
+Model data type: float32
+Device data type: bfloat16
+Number of operators in the model: 317
+GOPs of the model: 3.73517
+Number of operators supported by VAIML: 306 (96.530%)
+GOPs supported by VAIML: 3.735 (100.000%)
+Number of subgraphs supported by VAIML: 1
+Number of operators offloaded by VAIML: 306 (96.530%)
+GOPs offloaded by VAIML: 3.735 (100.000%)
+Number of subgraphs offloaded by VAIML: 1
+Number of subgraphs with compilation errors (fall back to CPU): 0
+Number of subgraphs below 2% GOPs threshold (fall back to CPU): 0
+Stats for offloaded subgraphs
+Subgraph vaiml_par_0 stats: 
+    Operators: 306 (96.530%)
+    GOPs : 3.735 (100.000%)  OPs: 3,735,173,696
+
+

segmentation_1_4_0_fp32_combined/gops.csv

@@ -0,0 +1,318 @@
+Node,OPs,Note
+Add_105,115200
+Add_115,96000
+Add_124,96000
+Add_132,38400
+Add_135,88320
+Add_144,88320
+Add_152,38400
+Add_155,88320
+Add_164,88320
+Add_172,38400
+Add_175,230400
+Add_184,230400
+Add_19,460800
+Add_196,960
+Add_206,322560
+Add_215,322560
+Add_227,1344
+Add_235,53760
+Add_238,322560
+Add_247,322560
+Add_259,1344
+Add_269,460800
+Add_278,460800
+Add_29,460800
+Add_290,1920
+Add_298,76800
+Add_301,460800
+Add_310,460800
+Add_322,1920
+Add_330,76800
+Add_333,460800
+Add_362,30720
+Add_388,73600
+Add_40,172800
+Add_414,144000
+Add_434,460800
+Add_445,345600
+Add_50,144
+Add_67,240
+Add_75,73600
+Add_85,240
+Add_93,73600
+Add_96,441600
+AveragePool_346,0
+AveragePool_347,0
+AveragePool_348,0
+Cast_0,0
+Clip_108,230400
+Clip_118,192000
+Clip_127,192000
+Clip_138,176640
+Clip_147,176640
+Clip_158,176640
+Clip_167,176640
+Clip_178,460800
+Clip_187,460800
+Clip_199,1920
+Clip_209,645120
+Clip_218,645120
+Clip_22,921600
+Clip_230,2688
+Clip_241,645120
+Clip_250,645120
+Clip_262,2688
+Clip_272,921600
+Clip_281,921600
+Clip_293,3840
+Clip_304,921600
+Clip_313,921600
+Clip_325,3840
+Clip_336,921600
+Clip_446,691200
+Clip_447,230400
+Clip_53,288
+Clip_70,480
+Clip_88,480
+Clip_99,883200
+Concat_350,30720
+Concat_355,30720
+Concat_363,30720
+Concat_372,235520
+Concat_376,73600
+Concat_381,73600
+Concat_389,73600
+Concat_398,576000
+Concat_402,144000
+Concat_407,144000
+Concat_415,144000
+Concat_418,1152000
+Concat_422,460800
+Concat_427,460800
+Concat_435,460800
+Concat_438,3686400
+Conv_103,1152000
+Conv_112,9254400
+Conv_113,7776000
+Conv_122,960000
+Conv_131,7718400
+Conv_133,7153920
+Conv_142,883200
+Conv_151,7104000
+Conv_153,7153920
+Conv_162,883200
+Conv_17,12902400
+Conv_171,7104000
+Conv_173,18662400
+Conv_182,2304000
+Conv_192,115440
+Conv_194,116160
+Conv_203,25858560
+Conv_204,36449280
+Conv_213,3225600
+Conv_223,226128
+Conv_225,227136
+Conv_234,36180480
+Conv_236,36449280
+Conv_245,8386560
+Conv_255,226128
+Conv_257,227136
+Conv_26,4608000
+Conv_266,51686400
+Conv_267,74188800
+Conv_276,11980800
+Conv_28,7833600
+Conv_286,461280
+Conv_288,462720
+Conv_297,73804800
+Conv_299,74188800
+Conv_30,31334400
+Conv_308,11980800
+Conv_318,461280
+Conv_32,4608000
+Conv_320,462720
+Conv_329,73804800
+Conv_331,74188800
+Conv_34,11232000
+Conv_340,59043840
+Conv_343,246016
+Conv_35,12960000
+Conv_351,70840320
+Conv_356,35420160
+Conv_37,5184000
+Conv_373,226688000
+Conv_377,106131200
+Conv_382,53065600
+Conv_39,12614400
+Conv_399,277632000
+Conv_403,103968000
+Conv_408,51984000
+Conv_41,12960000
+Conv_419,490291200
+Conv_423,266342400
+Conv_428,133171200
+Conv_43,3444480
+Conv_439,582451200
+Conv_441,267264000
+Conv_443,7833600
+Conv_46,3504
+Conv_48,3600
+Conv_57,5372800
+Conv_58,9052800
+Conv_60,5740800
+Conv_63,7744
+Conv_65,7920
+Conv_74,8905600
+Conv_76,9052800
+Conv_78,5740800
+Conv_81,7744
+Conv_83,7920
+Conv_92,8905600
+Conv_94,18105600
+Div_101,1766400
+Div_110,460800
+Div_120,384000
+Div_129,384000
+Div_140,353280
+Div_149,353280
+Div_16,1382400
+Div_160,353280
+Div_169,353280
+Div_180,921600
+Div_189,921600
+Div_2,1843200
+Div_201,3840
+Div_211,1290240
+Div_220,1290240
+Div_232,5376
+Div_24,1843200
+Div_243,1290240
+Div_252,1290240
+Div_264,5376
+Div_274,1843200
+Div_283,1843200
+Div_295,7680
+Div_306,1843200
+Div_315,1843200
+Div_327,7680
+Div_338,1843200
+Div_55,576
+Div_72,960
+Div_90,960
+GlobalAveragePool_191,234240
+GlobalAveragePool_222,327936
+GlobalAveragePool_254,327936
+GlobalAveragePool_285,468480
+GlobalAveragePool_317,468480
+GlobalAveragePool_342,468480
+GlobalAveragePool_45,133056
+GlobalAveragePool_62,221760
+GlobalAveragePool_80,221760
+Mul_102,441600
+Mul_111,115200
+Mul_121,96000
+Mul_130,96000
+Mul_141,88320
+Mul_150,88320
+Mul_161,88320
+Mul_170,88320
+Mul_181,230400
+Mul_190,230400
+Mul_202,230400
+Mul_212,322560
+Mul_221,322560
+Mul_233,322560
+Mul_244,322560
+Mul_25,460800
+Mul_253,322560
+Mul_265,322560
+Mul_275,460800
+Mul_284,460800
+Mul_296,460800
+Mul_307,460800
+Mul_316,460800
+Mul_328,460800
+Mul_339,460800
+Mul_345,61440
+Mul_354,30720
+Mul_360,30720
+Mul_361,30720
+Mul_380,73600
+Mul_386,73600
+Mul_387,73600
+Mul_406,144000
+Mul_412,144000
+Mul_413,144000
+Mul_426,460800
+Mul_432,460800
+Mul_433,460800
+Mul_56,132480
+Mul_73,220800
+Mul_91,220800
+Relu_193,240
+Relu_224,336
+Relu_256,336
+Relu_27,460800
+Relu_287,480
+Relu_31,1843200
+Relu_319,480
+Relu_33,460800
+Relu_341,61440
+Relu_36,518400
+Relu_374,147200
+Relu_38,518400
+Relu_400,288000
+Relu_42,518400
+Relu_420,921600
+Relu_44,132480
+Relu_440,1843200
+Relu_442,1843200
+Relu_47,48
+Relu_59,220800
+Relu_61,220800
+Relu_64,64
+Relu_77,220800
+Relu_79,220800
+Relu_82,64
+Resize_365,245760
+Resize_391,588800
+Resize_417,1152000
+Resize_437,3686400
+Sigmoid_344,0
+Sigmoid_352,0
+Sigmoid_378,0
+Sigmoid_404,0
+Sigmoid_424,0
+Slice_371,235520
+Slice_397,576000
+Slice_7,345600
+Split_349,0
+Split_353,0
+Split_375,0
+Split_379,0
+Split_401,0
+Split_405,0
+Split_421,0
+Split_425,0
+Split_444,0
+Sub_14,345600
+Sub_359,30720
+Sub_385,73600
+Sub_411,144000
+Sub_431,460800
+Tanh_357,2334720
+Tanh_383,5593600
+Tanh_409,10944000
+Tanh_429,35020800
+Transpose_10,0
+Transpose_11,0
+Transpose_12,0
+Transpose_448,0
+Transpose_449,0
+Transpose_450,0
+Transpose_451,0
+Transpose_452,0
+Transpose_453,0
+Transpose_8,0
+Transpose_9,0

segmentation_1_4_0_fp32_combined/graph_partition_trace.csv

@@ -0,0 +1,318 @@
+Node, Type, Subgraph/CustomOp, Status
+Add_105,,vaiml_par_0,Supported
+Add_115,,vaiml_par_0,Supported
+Add_124,,vaiml_par_0,Supported
+Add_132,,vaiml_par_0,Supported
+Add_135,,vaiml_par_0,Supported
+Add_144,,vaiml_par_0,Supported
+Add_152,,vaiml_par_0,Supported
+Add_155,,vaiml_par_0,Supported
+Add_164,,vaiml_par_0,Supported
+Add_172,,vaiml_par_0,Supported
+Add_175,,vaiml_par_0,Supported
+Add_184,,vaiml_par_0,Supported
+Add_19,,vaiml_par_0,Supported
+Add_196,,vaiml_par_0,Supported
+Add_206,,vaiml_par_0,Supported
+Add_215,,vaiml_par_0,Supported
+Add_227,,vaiml_par_0,Supported
+Add_235,,vaiml_par_0,Supported
+Add_238,,vaiml_par_0,Supported
+Add_247,,vaiml_par_0,Supported
+Add_259,,vaiml_par_0,Supported
+Add_269,,vaiml_par_0,Supported
+Add_278,,vaiml_par_0,Supported
+Add_29,,vaiml_par_0,Supported
+Add_290,,vaiml_par_0,Supported
+Add_298,,vaiml_par_0,Supported
+Add_301,,vaiml_par_0,Supported
+Add_310,,vaiml_par_0,Supported
+Add_322,,vaiml_par_0,Supported
+Add_330,,vaiml_par_0,Supported
+Add_333,,vaiml_par_0,Supported
+Add_362,,vaiml_par_0,Supported
+Add_388,,vaiml_par_0,Supported
+Add_40,,vaiml_par_0,Supported
+Add_414,,vaiml_par_0,Supported
+Add_434,,vaiml_par_0,Supported
+Add_445,,vaiml_par_0,Supported
+Add_50,,vaiml_par_0,Supported
+Add_67,,vaiml_par_0,Supported
+Add_75,,vaiml_par_0,Supported
+Add_85,,vaiml_par_0,Supported
+Add_93,,vaiml_par_0,Supported
+Add_96,,vaiml_par_0,Supported
+AveragePool_346,,vaiml_par_0,Supported
+AveragePool_347,,vaiml_par_0,Supported
+AveragePool_348,,vaiml_par_0,Supported
+Cast_0,,,Not supported. Check aie_unsupported_original_ops.json
+Clip_108,,vaiml_par_0,Supported
+Clip_118,,vaiml_par_0,Supported
+Clip_127,,vaiml_par_0,Supported
+Clip_138,,vaiml_par_0,Supported
+Clip_147,,vaiml_par_0,Supported
+Clip_158,,vaiml_par_0,Supported
+Clip_167,,vaiml_par_0,Supported
+Clip_178,,vaiml_par_0,Supported
+Clip_187,,vaiml_par_0,Supported
+Clip_199,,vaiml_par_0,Supported
+Clip_209,,vaiml_par_0,Supported
+Clip_218,,vaiml_par_0,Supported
+Clip_22,,vaiml_par_0,Supported
+Clip_230,,vaiml_par_0,Supported
+Clip_241,,vaiml_par_0,Supported
+Clip_250,,vaiml_par_0,Supported
+Clip_262,,vaiml_par_0,Supported
+Clip_272,,vaiml_par_0,Supported
+Clip_281,,vaiml_par_0,Supported
+Clip_293,,vaiml_par_0,Supported
+Clip_304,,vaiml_par_0,Supported
+Clip_313,,vaiml_par_0,Supported
+Clip_325,,vaiml_par_0,Supported
+Clip_336,,vaiml_par_0,Supported
+Clip_446,,vaiml_par_0,Supported
+Clip_447,,vaiml_par_0,Supported
+Clip_53,,vaiml_par_0,Supported
+Clip_70,,vaiml_par_0,Supported
+Clip_88,,vaiml_par_0,Supported
+Clip_99,,vaiml_par_0,Supported
+Concat_350,,vaiml_par_0,Supported
+Concat_355,,vaiml_par_0,Supported
+Concat_363,,vaiml_par_0,Supported
+Concat_372,,vaiml_par_0,Supported
+Concat_376,,vaiml_par_0,Supported
+Concat_381,,vaiml_par_0,Supported
+Concat_389,,vaiml_par_0,Supported
+Concat_398,,vaiml_par_0,Supported
+Concat_402,,vaiml_par_0,Supported
+Concat_407,,vaiml_par_0,Supported
+Concat_415,,vaiml_par_0,Supported
+Concat_418,,vaiml_par_0,Supported
+Concat_422,,vaiml_par_0,Supported
+Concat_427,,vaiml_par_0,Supported
+Concat_435,,vaiml_par_0,Supported
+Concat_438,,vaiml_par_0,Supported
+Conv_103,,vaiml_par_0,Supported
+Conv_112,,vaiml_par_0,Supported
+Conv_113,,vaiml_par_0,Supported
+Conv_122,,vaiml_par_0,Supported
+Conv_131,,vaiml_par_0,Supported
+Conv_133,,vaiml_par_0,Supported
+Conv_142,,vaiml_par_0,Supported
+Conv_151,,vaiml_par_0,Supported
+Conv_153,,vaiml_par_0,Supported
+Conv_162,,vaiml_par_0,Supported
+Conv_17,,vaiml_par_0,Supported
+Conv_171,,vaiml_par_0,Supported
+Conv_173,,vaiml_par_0,Supported
+Conv_182,,vaiml_par_0,Supported
+Conv_192,,vaiml_par_0,Supported
+Conv_194,,vaiml_par_0,Supported
+Conv_203,,vaiml_par_0,Supported
+Conv_204,,vaiml_par_0,Supported
+Conv_213,,vaiml_par_0,Supported
+Conv_223,,vaiml_par_0,Supported
+Conv_225,,vaiml_par_0,Supported
+Conv_234,,vaiml_par_0,Supported
+Conv_236,,vaiml_par_0,Supported
+Conv_245,,vaiml_par_0,Supported
+Conv_255,,vaiml_par_0,Supported
+Conv_257,,vaiml_par_0,Supported
+Conv_26,,vaiml_par_0,Supported
+Conv_266,,vaiml_par_0,Supported
+Conv_267,,vaiml_par_0,Supported
+Conv_276,,vaiml_par_0,Supported
+Conv_28,,vaiml_par_0,Supported
+Conv_286,,vaiml_par_0,Supported
+Conv_288,,vaiml_par_0,Supported
+Conv_297,,vaiml_par_0,Supported
+Conv_299,,vaiml_par_0,Supported
+Conv_30,,vaiml_par_0,Supported
+Conv_308,,vaiml_par_0,Supported
+Conv_318,,vaiml_par_0,Supported
+Conv_32,,vaiml_par_0,Supported
+Conv_320,,vaiml_par_0,Supported
+Conv_329,,vaiml_par_0,Supported
+Conv_331,,vaiml_par_0,Supported
+Conv_34,,vaiml_par_0,Supported
+Conv_340,,vaiml_par_0,Supported
+Conv_343,,vaiml_par_0,Supported
+Conv_35,,vaiml_par_0,Supported
+Conv_351,,vaiml_par_0,Supported
+Conv_356,,vaiml_par_0,Supported
+Conv_37,,vaiml_par_0,Supported
+Conv_373,,vaiml_par_0,Supported
+Conv_377,,vaiml_par_0,Supported
+Conv_382,,vaiml_par_0,Supported
+Conv_39,,vaiml_par_0,Supported
+Conv_399,,vaiml_par_0,Supported
+Conv_403,,vaiml_par_0,Supported
+Conv_408,,vaiml_par_0,Supported
+Conv_41,,vaiml_par_0,Supported
+Conv_419,,vaiml_par_0,Supported
+Conv_423,,vaiml_par_0,Supported
+Conv_428,,vaiml_par_0,Supported
+Conv_43,,vaiml_par_0,Supported
+Conv_439,,vaiml_par_0,Supported
+Conv_441,,vaiml_par_0,Supported
+Conv_443,,vaiml_par_0,Supported
+Conv_46,,vaiml_par_0,Supported
+Conv_48,,vaiml_par_0,Supported
+Conv_57,,vaiml_par_0,Supported
+Conv_58,,vaiml_par_0,Supported
+Conv_60,,vaiml_par_0,Supported
+Conv_63,,vaiml_par_0,Supported
+Conv_65,,vaiml_par_0,Supported
+Conv_74,,vaiml_par_0,Supported
+Conv_76,,vaiml_par_0,Supported
+Conv_78,,vaiml_par_0,Supported
+Conv_81,,vaiml_par_0,Supported
+Conv_83,,vaiml_par_0,Supported
+Conv_92,,vaiml_par_0,Supported
+Conv_94,,vaiml_par_0,Supported
+Div_101,,vaiml_par_0,Supported
+Div_110,,vaiml_par_0,Supported
+Div_120,,vaiml_par_0,Supported
+Div_129,,vaiml_par_0,Supported
+Div_140,,vaiml_par_0,Supported
+Div_149,,vaiml_par_0,Supported
+Div_16,,vaiml_par_0,Supported
+Div_160,,vaiml_par_0,Supported
+Div_169,,vaiml_par_0,Supported
+Div_180,,vaiml_par_0,Supported
+Div_189,,vaiml_par_0,Supported
+Div_2,,vaiml_par_0,Supported
+Div_201,,vaiml_par_0,Supported
+Div_211,,vaiml_par_0,Supported
+Div_220,,vaiml_par_0,Supported
+Div_232,,vaiml_par_0,Supported
+Div_24,,vaiml_par_0,Supported
+Div_243,,vaiml_par_0,Supported
+Div_252,,vaiml_par_0,Supported
+Div_264,,vaiml_par_0,Supported
+Div_274,,vaiml_par_0,Supported
+Div_283,,vaiml_par_0,Supported
+Div_295,,vaiml_par_0,Supported
+Div_306,,vaiml_par_0,Supported
+Div_315,,vaiml_par_0,Supported
+Div_327,,vaiml_par_0,Supported
+Div_338,,vaiml_par_0,Supported
+Div_55,,vaiml_par_0,Supported
+Div_72,,vaiml_par_0,Supported
+Div_90,,vaiml_par_0,Supported
+GlobalAveragePool_191,,vaiml_par_0,Supported
+GlobalAveragePool_222,,vaiml_par_0,Supported
+GlobalAveragePool_254,,vaiml_par_0,Supported
+GlobalAveragePool_285,,vaiml_par_0,Supported
+GlobalAveragePool_317,,vaiml_par_0,Supported
+GlobalAveragePool_342,,vaiml_par_0,Supported
+GlobalAveragePool_45,,vaiml_par_0,Supported
+GlobalAveragePool_62,,vaiml_par_0,Supported
+GlobalAveragePool_80,,vaiml_par_0,Supported
+Mul_102,,vaiml_par_0,Supported
+Mul_111,,vaiml_par_0,Supported
+Mul_121,,vaiml_par_0,Supported
+Mul_130,,vaiml_par_0,Supported
+Mul_141,,vaiml_par_0,Supported
+Mul_150,,vaiml_par_0,Supported
+Mul_161,,vaiml_par_0,Supported
+Mul_170,,vaiml_par_0,Supported
+Mul_181,,vaiml_par_0,Supported
+Mul_190,,vaiml_par_0,Supported
+Mul_202,,vaiml_par_0,Supported
+Mul_212,,vaiml_par_0,Supported
+Mul_221,,vaiml_par_0,Supported
+Mul_233,,vaiml_par_0,Supported
+Mul_244,,vaiml_par_0,Supported
+Mul_25,,vaiml_par_0,Supported
+Mul_253,,vaiml_par_0,Supported
+Mul_265,,vaiml_par_0,Supported
+Mul_275,,vaiml_par_0,Supported
+Mul_284,,vaiml_par_0,Supported
+Mul_296,,vaiml_par_0,Supported
+Mul_307,,vaiml_par_0,Supported
+Mul_316,,vaiml_par_0,Supported
+Mul_328,,vaiml_par_0,Supported
+Mul_339,,vaiml_par_0,Supported
+Mul_345,,vaiml_par_0,Supported
+Mul_354,,vaiml_par_0,Supported
+Mul_360,,vaiml_par_0,Supported
+Mul_361,,vaiml_par_0,Supported
+Mul_380,,vaiml_par_0,Supported
+Mul_386,,vaiml_par_0,Supported
+Mul_387,,vaiml_par_0,Supported
+Mul_406,,vaiml_par_0,Supported
+Mul_412,,vaiml_par_0,Supported
+Mul_413,,vaiml_par_0,Supported
+Mul_426,,vaiml_par_0,Supported
+Mul_432,,vaiml_par_0,Supported
+Mul_433,,vaiml_par_0,Supported
+Mul_56,,vaiml_par_0,Supported
+Mul_73,,vaiml_par_0,Supported
+Mul_91,,vaiml_par_0,Supported
+Relu_193,,vaiml_par_0,Supported
+Relu_224,,vaiml_par_0,Supported
+Relu_256,,vaiml_par_0,Supported
+Relu_27,,vaiml_par_0,Supported
+Relu_287,,vaiml_par_0,Supported
+Relu_31,,vaiml_par_0,Supported
+Relu_319,,vaiml_par_0,Supported
+Relu_33,,vaiml_par_0,Supported
+Relu_341,,vaiml_par_0,Supported
+Relu_36,,vaiml_par_0,Supported
+Relu_374,,vaiml_par_0,Supported
+Relu_38,,vaiml_par_0,Supported
+Relu_400,,vaiml_par_0,Supported
+Relu_42,,vaiml_par_0,Supported
+Relu_420,,vaiml_par_0,Supported
+Relu_44,,vaiml_par_0,Supported
+Relu_440,,vaiml_par_0,Supported
+Relu_442,,vaiml_par_0,Supported
+Relu_47,,vaiml_par_0,Supported
+Relu_59,,vaiml_par_0,Supported
+Relu_61,,vaiml_par_0,Supported
+Relu_64,,vaiml_par_0,Supported
+Relu_77,,vaiml_par_0,Supported
+Relu_79,,vaiml_par_0,Supported
+Relu_82,,vaiml_par_0,Supported
+Resize_365,,vaiml_par_0,Supported
+Resize_391,,vaiml_par_0,Supported
+Resize_417,,vaiml_par_0,Supported
+Resize_437,,vaiml_par_0,Supported
+Sigmoid_344,,vaiml_par_0,Supported
+Sigmoid_352,,vaiml_par_0,Supported
+Sigmoid_378,,vaiml_par_0,Supported
+Sigmoid_404,,vaiml_par_0,Supported
+Sigmoid_424,,vaiml_par_0,Supported
+Slice_371,,vaiml_par_0,Supported
+Slice_397,,vaiml_par_0,Supported
+Slice_7,,vaiml_par_0,Supported
+Split_349,,vaiml_par_0,Supported
+Split_353,,vaiml_par_0,Supported
+Split_375,,vaiml_par_0,Supported
+Split_379,,vaiml_par_0,Supported
+Split_401,,vaiml_par_0,Supported
+Split_405,,vaiml_par_0,Supported
+Split_421,,vaiml_par_0,Supported
+Split_425,,vaiml_par_0,Supported
+Split_444,,vaiml_par_0,Supported
+Sub_14,,vaiml_par_0,Supported
+Sub_359,,vaiml_par_0,Supported
+Sub_385,,vaiml_par_0,Supported
+Sub_411,,vaiml_par_0,Supported
+Sub_431,,vaiml_par_0,Supported
+Tanh_357,,vaiml_par_0,Supported
+Tanh_383,,vaiml_par_0,Supported
+Tanh_409,,vaiml_par_0,Supported
+Tanh_429,,vaiml_par_0,Supported
+Transpose_10,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_11,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_12,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_448,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_449,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_450,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_451,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_452,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_453,,,Not supported. Check aie_unsupported_original_ops.json
+Transpose_8,,vaiml_par_0,Supported
+Transpose_9,,,Not supported. Check aie_unsupported_original_ops.json

segmentation_1_4_0_fp32_combined/original-info-signature.txt

@@ -0,0 +1 @@
+4f00fb244983f7c2158dc9333522f122

segmentation_1_4_0_fp32_combined/original-model-signature.txt

@@ -0,0 +1 @@
+6bbb891ab96ca9362e0e61024cd02778

segmentation_1_4_0_fp32_combined/preliminary-vaiml-pass-summary.txt

@@ -0,0 +1,14 @@
+----- Preliminary Summary of VAIML Pass ------
+Model data type: float32
+Device data type: bfloat16
+Number of operators in the model: 317
+GOPs of the model: 3.73517
+Number of operators supported by VAIML: 306(96.530%)
+GOPs supported by VAIML: 3.735 (100.000%)
+Number of subgraphs supported by VAIML: 1
+
+Number of identified subgraphs: 1
+Stats for identified subgraphs
+vaiml_par_0 stats:
+    Operators: 306 (96.530%)
+    GOPs: 3.735(100.000%)  OPs: 3,735,173,696

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/.target

@@ -0,0 +1 @@
+hw

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/0_0.log

@@ -0,0 +1,59 @@
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+Configuration: Release_LLVM
+Compiling "0_0.ll"
+chess-clang --chess-proc-dir=/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -S -O2 -std=c++2a -fno-builtin-memcpy -mllvm -instcombine-code-sinking=false -mllvm -disable-lsr -mllvm -replexitval=never -mllvm -enable-load-pre=false -mllvm -chess-disable-add-to-or -mllvm -chess-combine-gep-indices=none -mllvm -chess-disable-fold-phi-of-loads -mllvm -chess-aainfo2chains-algo=4 -mllvm -chess-aggressive-aainfo=false -mllvm -chess-enable-indvarsimplify=0 -mllvm -chess-disable-cse-across-loopboundary -mllvm -chess-tbaa-detect-common-underlying-object=true -mllvm -chess-protect-llvm-global-reg-access=true -fno-jump-tables -fno-discard-value-names -g ../../ir/0_0.ll -o../Release/chesswork848/0_0.sfg --chess-proc-name=me
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+noodle -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -iaie_core.h +Sinl +Olbb=200 +Opmsa +NOpld +Olzyinl +w../Release/chesswork848 ../Release/chesswork848/0_0.sfg +Q1=+Sinl,+Olbb=200,+Opmsa,+NOpld,+Olzyinl +Q2=+Sinl,+Olbb=200,+Opmsa,+NOpld,+Olzyinl +Q3=+Sinl,+Olbb=1000,+Opmsa,+NOpld,+Olzyinl +Qfast=+Sinl,+Olbb=1000,+Opmsa,+NOpld,+Olzyinl,+Opfp +Qs=+Sinl,+Olbb=200,+Opmsa,+NOpld,+Olzyinl +Qz=+Sinl,+Olbb=200,+Opmsa,+NOpld,+Olzyinl me
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+chess-backend 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation --print-subtools --cosel -m +ef +s -M3 --amnesia -p10 -q2 -ecrSCDEn -ecrMCDEn -ecrVaddSign -ecrUnpackSign -ecrPackSign -ecrUPSSign -ecrUPSMode -ecrSRSSign -ecrSRSMode -ecrF2IMask -ecrUnpackSize -ecrPackSize -ecrSat -ecrRnd +Oefc +Opbr +Odhls +Oprefer-local-reg-moves -Onocb --mist1 -k64 --showcolor -b -Obbl --mist2 -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 +Omod -k64 +Omsbr=100 +Opnll +A +pnopALU +pnopLDA +pnopLDB +pnopSTS +pnopVEC +Ofexm +Omsanafs +Onzmem +Onombt +Ochex +Omsmfi +Omslactc=lckLdaRsrc_E1,lckLdbRsrc_E1:2 +Odra +Oslr=crSRSSign +Oslr=crUPSMode +Oslr=crSRSMode +Oslr=crRnd +Oslr=crSat +Onop-syntax=NOPA +Onop-syntax=NOPB +Onop-syntax=NOPM +Onop-syntax=NOPV +Onop-syntax=NOPS +Onop-syntax=NOPX +Onop-syntax=NOPXM --tale -g -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -V0_0 -L
+chess-backend 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x --print-subtools --cosel -m +ef +s -M3 --amnesia -p10 -q2 -ecrSCDEn -ecrMCDEn -ecrVaddSign -ecrUnpackSign -ecrPackSign -ecrUPSSign -ecrUPSMode -ecrSRSSign -ecrSRSMode -ecrF2IMask -ecrUnpackSize -ecrPackSize -ecrSat -ecrRnd +Oefc +Opbr +Odhls +Oprefer-local-reg-moves -Onocb --mist1 -k64 --showcolor -b -Obbl --mist2 -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 +Omod -k64 +Omsbr=100 +Opnll +A +pnopALU +pnopLDA +pnopLDB +pnopSTS +pnopVEC +Ofexm +Omsanafs +Onzmem +Onombt +Ochex +Omsmfi +Omslactc=lckLdaRsrc_E1,lckLdbRsrc_E1:2 +Odra +Oslr=crSRSSign +Oslr=crUPSMode +Oslr=crSRSMode +Oslr=crRnd +Oslr=crSat +Onop-syntax=NOPA +Onop-syntax=NOPB +Onop-syntax=NOPM +Onop-syntax=NOPV +Onop-syntax=NOPS +Onop-syntax=NOPX +Onop-syntax=NOPXM --tale -g -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -V0_0 -L
+chess-backend --gvt me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation --tale -g -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -V0_0 -L
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+--cosel -m +ef +s -M3 --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+--cosel -m +ef +s -M3 --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+--amnesia -p10 -q2 -ecrSCDEn -ecrMCDEn -ecrVaddSign -ecrUnpackSign -ecrPackSign -ecrUPSSign -ecrUPSMode -ecrSRSSign -ecrSRSMode -ecrF2IMask -ecrUnpackSize -ecrPackSize -ecrSat -ecrRnd +Oefc +Opbr +Odhls +Oprefer-local-reg-moves -Onocb --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+--mist1 -k64 --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+--amnesia -p10 -q2 -ecrSCDEn -ecrMCDEn -ecrVaddSign -ecrUnpackSign -ecrPackSign -ecrUPSSign -ecrUPSMode -ecrSRSSign -ecrSRSMode -ecrF2IMask -ecrUnpackSize -ecrPackSize -ecrSat -ecrRnd +Oefc +Opbr +Odhls +Oprefer-local-reg-moves -Onocb --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+--showcolor -b -Obbl --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+--mist2 -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 +Omod -k64 +Omsbr=100 +Opnll +A +pnopALU +pnopLDA +pnopLDB +pnopSTS +pnopVEC +Ofexm +Omsanafs +Onzmem +Onombt +Ochex +Omsmfi +Omslactc=lckLdaRsrc_E1,lckLdbRsrc_E1:2 +Odra +Oslr=crSRSSign +Oslr=crUPSMode +Oslr=crSRSMode +Oslr=crRnd +Oslr=crSat +Onop-syntax=NOPA +Onop-syntax=NOPB +Onop-syntax=NOPM +Onop-syntax=NOPV +Onop-syntax=NOPS +Onop-syntax=NOPX +Onop-syntax=NOPXM --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+Warning in "/usr/local/lib/python3.10/dist-packages/include/adf/aie/tile_control.h", line 292, column 8:  in "/usr/local/lib/python3.10/dist-packages/include/adf/aie/tile_control.h", line 292: (loop #8)
+         loop software pipelining (to 2 cycles) is feasible for a minimum loop count of 5,
+         but requires the creation of a post-amble, for which the loop was not prepared
+         ... consider annotating the loop with `chess_prepare_for_pipelining', as well as 
+             increasing the current `chess_loop_range(1,)` annotation to `chess_loop_range(5,)', or remove it.
+
+--tale -g -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -V0_0 -L --common 0_0-F_ZN3adf11block_writeEPKNS_7reg_valEj_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation
+--mist1 -k64 --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+--showcolor -b -Obbl --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+--mist2 -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 +Omod -k64 +Omsbr=100 +Opnll +A +pnopALU +pnopLDA +pnopLDB +pnopSTS +pnopVEC +Ofexm +Omsanafs +Onzmem +Onombt +Ochex +Omsmfi +Omslactc=lckLdaRsrc_E1,lckLdbRsrc_E1:2 +Odra +Oslr=crSRSSign +Oslr=crUPSMode +Oslr=crSRSMode +Oslr=crRnd +Oslr=crSat +Onop-syntax=NOPA +Onop-syntax=NOPB +Onop-syntax=NOPM +Onop-syntax=NOPV +Onop-syntax=NOPS +Onop-syntax=NOPX +Onop-syntax=NOPXM --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+Warning in "0_0/src/0_0.cc", line 37, column 12:  in "0_0/src/0_0.cc", line 37: (loop #13)
+         loop software pipelining (to 8 cycles) is feasible but requires the creation of a post-amble, 
+         for which the loop was not prepared
+         ... consider annotating the loop with `chess_prepare_for_pipelining'
+
+Warning:  in "0_0/src/0_0.cc", line 12: (loop #3)
+        Non leaf loop was prepared for pipelining. But the pipelined solutions have not been selected.
+        Consider removing the chess_prepare_for_pipelining directive as it may improve results
+--tale -g -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -V0_0 -L --common 0_0-main_ me /usr/local/lib/python3.10/dist-packages/data/aie2p/lib +H/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/elongation -x
+bridge -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -i -g -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 0_0.objlist -o../0_0.o -pme
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+darts -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -d -h -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -L +Ihex +nanno ../Release/0_0.o me
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+Linking "../Release/0_0"
+bridge -o../Release/0_0 ../Release/0_0.o -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -g -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0.bcf -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/softfloat/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork848 -pme
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+darts -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -d -h -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -L +Ihex +nanno +u ../Release/0_0 me
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+Compilation finished successfully (19 errors, 3 warnings)

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.#

@@ -0,0 +1,2 @@
+3d25a3bfdb1b94e31ca421fe169265bb6b32498c
+1a735f496f1284ab86135ede88939a8aeeb375a3

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.##

@@ -0,0 +1,2 @@
+46f16ef751fb28f6dce00ef4d676df021c165b9a
+92e103875c6a39bc8cdbe4a21c02c5a94ba3cc96

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.calltree

@@ -0,0 +1,32 @@
+
+// File generated by bridge version V-2024.06#84922c0d9f#241219, Fri Mar 21 03:42:51 2025
+// Copyright 2014-2024 Synopsys, Inc. All rights reserved.
+// bridge -o../Release/0_0 ../Release/0_0.o -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -g -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0.bcf -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/softfloat/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork848 -pme
+
+
+// Release: ipp V-2024.06-TGT-241219
+
+_main_init
+    _main
+        _ZN3adf11block_writeEPKNS_7reg_valEj
+        _Z13kernelWrapperPPvjjjj
+    __cxa_finalize
+        _fini (referenced text)
+
+
+Call tree stack and functions sizes:
+
+stack stack stack call  func  func  function name
+      desc  level level       desc
+----- ----- ----- ----- ----- ----- --------------------------------------------------------------
+    0   320     0     0   224  1998 _main_init
+  192   320     1     1  1108  1774     _main
+    0     0     2     2   174   174         _ZN3adf11block_writeEPKNS_7reg_valEj
+    *     *     2     2     *     *         _Z13kernelWrapperPPvjjjj (_extern)
+   64   128     2     2   324   492         __cxa_finalize
+   64    64     3     3   168   168             _fini
+
+
+Maximum call level : 3
+Maximum stack level: 3
+Maximum stack size : 320

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.cmico

@@ -0,0 +1 @@
++Mdec

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.lst

@@ -0,0 +1,824 @@
+
+// File generated by darts version V-2024.06#84922c0d9f#241219, Fri Mar 21 03:42:52 2025
+// Copyright 2014-2024 Synopsys, Inc. All rights reserved.
+// darts -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -d -h -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -L +Ihex +nanno +u ../Release/0_0 me
+
+// Release: ipp V-2024.06-TGT-241219
+
+.text_segment PM      0
+.entry_point
+.label __AIE_ARCH_MODEL_VERSION__21011100__inlined__1__me_basic___main_init_
+.label _main_init
+.function_start
+           0    0x00 0x07 0xb9 0xf5 0x80 0x44                                                                                                                                              MOVXM sp, #506560
+           6    0x00 0x00 0x04 0x20 0x00 0x44                                                                                                                                              MOVXM r8, #0
+          12    0x00 0x00 0x08 0x20 0x00 0x44                                                                                                                                              MOVXM r16, #0
+          18    0x12 0x21 0x07 0x98                                                                                                                                                        EQ r16, r8, r16
+          22    0x80 0x00 0x40 0x40 0x01 0x84                                                                                                                                              JNZ r16, #128
+.delay_slot
+.swstall delay_slot
+          28    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          30    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          32    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          34    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          36    0x00 0x00                                                                        NOPX
+          38    0x00 0x2c 0xf7 0x80 0x8b 0x01 0x28 0x50 0x72 0xba                                NOPA;                                                       MOVS p7, p0;                                                MOV r9, r1
+          48    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x3f 0xff 0xff 0x37 0xfe 0x10 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         MOVXM p6, #-4;                                                        NOPV
+.label TGT_F_main_init_64
+.loop_nesting 1
+          64    0xdf 0x83 0xd5 0x39 0x81 0xd4                                                    LDA p0, [p6], #-4;                                                                                                      MOV r10, p6
+          70    0x00 0x00                                                                        NOPX
+          72    0x00 0x00                                                                        NOPX
+          74    0x00 0x00                                                                        NOPX
+          76    0x00 0x00                                                                        NOPX
+          78    0x00 0x00                                                                        NOPX
+          80    0x00 0x00                                                                        NOPX
+.no_stack_arguments
+          82    0x10 0x30 0x00 0x18                                                                                                                                                        JL p0
+.delay_slot
+.swstall delay_slot
+          86    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          88    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          90    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          92    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+          94    0x00 0x00                                                                        NOPX
+.return_address
+          96    0x12 0xa0 0x88 0x98                                                                                                                                                        NE r16, r10, r8
+         100    0x80 0x00 0x20 0x40 0x01 0x84                                                                                                                                              JNZ r16, #64
+.delay_slot
+.swstall delay_slot
+         106    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         108    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         110    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         112    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         114    0x00 0x00                                                                        NOPX
+.loop_nesting 0
+         116    0x00 0x2c 0xf0 0x00 0x20 0x9c 0x8b 0x00 0x2a 0x50 0x70 0xf6                      NOPA;                         NOPB;                         MOVS p0, p7;                                                MOV r1, r9
+.label TGT_F_main_init_128
+.no_stack_arguments
+         128    0x00 0x00 0x70 0x00 0x01 0x04                                                                                                                                              JL #224
+.delay_slot
+.swstall delay_slot
+         134    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         136    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         138    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         140    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         142    0x00 0x00                                                                        NOPX
+.return_address
+.no_stack_arguments
+         144    0x00 0x03 0x50 0x00 0x01 0x04                                                                                                                                              JL #1696
+.delay_slot
+         150    0x18 0x60 0x00 0xb8                                                                                                                                                                                      MOV p0, #0
+.delay_slot
+.swstall delay_slot
+         154    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         156    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         158    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         160    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+.return_address
+.swstall chess_separator_scheduler
+         176    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         178    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         180    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         182    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         184    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         186    0x00 0x00                                                                        NOPX
+         188    0x10 0x08 0x00 0x18                                                                                                                                                        DONE
+.swstall chess_separator_scheduler
+         192    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         194    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         196    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         198    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         200    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+         202    0x00 0x00                                                                        NOPX
+.swstall for_chess_exit
+.exit
+         204    0x00 0x01 0x67 0x98                                                              NOPA
+.label TGT_F_main_init_208
+.loop_nesting 1
+         208    0x00 0x00 0x68 0x00 0x00 0x84                                                                                                                                              J #208
+.delay_slot
+.swstall delay_slot
+         214    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         216    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         218    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         220    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         222    0x00 0x00                                                                        NOPX
+.label _main_init__end
+.label _main___func_begin0
+.label _main
+.function_start
+         224    0xec 0x00 0x80 0x00 0x06 0x00 0x00 0x00 0x70 0xba                                MOVA m0, #-160;                                                                           PADDXM [sp], #192
+         234    0xe9 0x04 0x80 0x00 0xc0 0x48 0xb2 0xf0 0x78 0xba                                MOVA m1, #-184;                                                                           MOVX r12, #2;                 MOV p1, sp
+         244    0x00 0x19 0x02 0x17 0x20 0x00 0x4f 0x86 0x0e 0x02 0xd0 0x91 0x60 0x7e            MOVA r25, #0;                 PADDB [p1], m0;               MOVS p6, p1;                  MOVXM p0, #651488
+         258    0x00 0x2c 0xfc 0x57 0x20 0x20 0x05 0x61 0x00 0x0b 0xff 0x93 0xb0 0x7e            NOPA;                         PADDB [p6], m1;               ST p1, [sp, #-4];             MOVX r16, #1;                 MOV r24, #0
+.label TGT_F_main_48
+.loop_nesting 1
+         272    0x08 0x4f 0x3e 0x98                                                                                                                          ST.TM r25, [p0], #16
+         276    0x08 0xcf 0x3e 0x98                                                                                                                          ST.TM r25, [p0], #-16
+         280    0x00 0x00                                                                        NOPX
+         282    0x00 0x00                                                                        NOPX
+         284    0x00 0x00                                                                        NOPX
+         286    0x17 0xc3 0x08 0x18                                                                                                                                                        ACQ #62, r16
+         290    0xf4 0x9c 0x80 0x00 0x01 0xef 0xb1 0x40 0x10 0xba                                MOVA m7, #-92;                                                                            MOVXM p7, #504448
+         300    0x00 0x00                                                                        NOPX
+         302    0x00 0x00                                                                        NOPX
+         304    0x0f 0xf8 0x1d 0x98                                                                                                                          ST p0, [sp, #-8]
+         308    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         312    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         316    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         320    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         324    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         328    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         332    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         336    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         340    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         344    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         348    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         352    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         356    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         360    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         364    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         368    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         372    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         376    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         380    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         384    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         388    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+         392    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         396    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+         400    0x09 0xeb 0x31 0x98                                                                                                                          ST r25, [p1], m7
+         404    0x00 0x2c 0xf0 0x00 0x20 0x00 0x00 0x03 0xfa 0x4e 0xc1 0x36                      NOPA;                         NOPB;                         ST p1, [sp, #-12];            NOPX
+.label TGT_F_main_192
+.loop_nesting 2
+         416    0xe3 0xc6 0xd0 0x00 0x00 0x00 0x78 0xf8 0x10 0xba                                LDA r17, [p7], #4;                                                                        MOVXM ls, #496
+         426    0xe3 0xaa 0xd0 0x00 0x00 0x01 0xb9 0x28 0x10 0xba                                LDA r10, [p7], #4;                                                                        MOVXM le, #592
+         436    0x07 0x1d 0x36 0x98                                                              LDA r9, [p7], #4
+         440    0x07 0x1d 0x16 0x98                                                              LDA r8, [p7], #4
+         444    0x07 0x2e 0x76 0x98                                                              LDA r19, [p7], #8
+         448    0xff 0x93 0x24 0xdd 0x81 0xd4                                                    LDA p1, [sp, #-4];                                                                                                      MOV p2, p7
+         454    0x00 0x00                                                                        NOPX
+         456    0x04 0x00 0x27 0x31 0x39 0xe4                                                                                                                                              MOVX r16, #0;                 MOV el7, r24
+         462    0x1c 0x90 0x9c 0xf8                                                                                                                                                                                      MOV el9, r16
+         466    0x1d 0x14 0xa9 0x58                                                                                                                                                                                      ADD.NC r20, r9, r10
+         470    0x00 0x2c 0xf0 0x98 0x8b 0x02 0x8d 0x10 0xa2 0xba                                NOPA;                                                       MOVS p0, p6;                                                ADD.NC r20, r20, r8
+         480    0x00 0xd2 0x00 0x00 0x20 0x01 0x5b 0x01 0x30 0x0a 0xbc 0xe8 0xa8 0x00 0x00 0xe1  MOVA r18, #6;                 NOPB;                         NOPS;                         MOVX r19, #0;                 ADD.NC lc, r19, r20;                    NOPV
+.label ZLS_F_main_272
+.loop_nesting 3
+.begin_of_loop
+         496    0x43 0xe4 0xd1 0x1d 0xe9 0x82 0x6c 0xc0 0x42 0xba                                LDA dn6, [p2], #4;                                          ST el7, [p1], #4;                                           ADD.NC r19, r19, #1
+         506    0x43 0xd2 0xd9 0x32 0x04 0x14                                                    LDA r20, [p2], #4;                                                                                                      ADD.NC r18, r18, #4
+         512    0x02 0x1f 0xe6 0x98                                                              LDA dc7, [p2], #4
+         516    0x02 0x1e 0xee 0x98                                                              LDA el11, [p2], #4
+         520    0x00 0x00                                                                        NOPX
+         522    0x00 0x00                                                                        NOPX
+         524    0x00 0x00                                                                        NOPX
+         526    0x09 0x1f 0x21 0x98                                                                                                                          ST dn6, [p1], #4
+         530    0x00 0x00                                                                        NOPX
+         532    0x09 0x1f 0xe1 0x98                                                                                                                          ST dc7, [p1], #4
+         536    0x23 0xcd 0x30 0x00 0x01 0xa5 0x70 0x02                                                                                                      ST el9, [p1], #4;                                           NOPM
+         544    0x00 0x2c 0xf0 0x00 0x21 0x1e 0x91 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST r20, [p1], #4;             NOPX;                         NOPM;                                   NOPV
+         560    0x00 0x2c 0xf0 0x00 0x21 0xbe 0xe9 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST el11, [p1], #-20;          NOPX;                         NOPM;                                   NOPV
+         576    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x02 0xa9 0x60 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         MOV r21, p1;                            NOPV
+.label ZLE_F_main_368
+.end_of_loop
+         592    0x00 0x2c 0xf0 0x00 0x20 0x1e 0xb1 0x80 0x00 0x00 0xb5 0x46 0x08 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST r21, [p0], #4;             NOPX;                         ADD.NC p1, r21, #24;                    NOPV
+.loop_nesting 2
+         608    0x00 0x0b 0x00 0x27 0x46 0x6e 0x6f 0x60 0x78 0xba                                MOVA r11, #0;                                                                             LSHL r20, r19, r12;           MOV r19, p7
+         618    0x9b 0x74 0x69 0xb2 0x01 0x24                                                                                                                                              ADD r13, r19, #-24;           ADD.NC r19, r18, #1
+         624    0xf1 0xa1 0x60 0x25 0x26 0x6f 0x45 0x10 0x79 0x3a                                                                                            MOVS p7, r13;                 LSHL r18, r18, r12;           MOV dj6, r20
+         634    0x9c 0x99 0xbb 0x12 0x41 0xe4                                                                                                                                              LSHL r18, r19, r12;           MOV dj5, r18
+         640    0xf4 0x4a 0xde 0x8d 0x92 0x94                                                    LDA r18, [p7, dj5];                                                                                                     ADD.NC dn7, r13, r18
+         646    0xd8 0x74 0x30 0x02 0x2c 0x7f 0xc0 0x02                                                                                                      ST dn7, [p6, dj6];                                          ADD.NC r17, r17, #-1
+         654    0x00 0x00                                                                        NOPX
+         656    0x00 0x00                                                                        NOPX
+         658    0x00 0x00                                                                        NOPX
+         660    0x00 0x00                                                                        NOPX
+         662    0x00 0x00                                                                        NOPX
+         664    0x00 0x2b 0x60 0x02 0x4c 0xe4 0xa0 0x02                                                                                                      NOPS;                                                       ADD.NC r18, r19, r18
+.label TGT_F_main_448
+.loop_nesting 3
+         672    0x14 0xa1 0x01 0x98                                                                                                                                                        SUB r16, r18, r16
+         676    0x14 0x1e 0xcd 0x98                                                                                                                                                        LSHL r15, r16, r12
+         680    0xf1 0xa1 0x60 0x03 0xc3 0xd0 0x70 0x02                                                                                                      MOVS p7, r13;                                               MOV dj7, r15
+         688    0x07 0xe0 0x16 0x98                                                              LDA r0, [p7, dj7]
+.no_stack_arguments
+         692    0x00 0x02 0xa0 0x00 0x01 0x04                                                                                                                                              JL #1344
+.delay_slot
+         698    0x1b 0x98 0x00 0x98                                                                                                                                                                                      ADD.NC r14, r16, #1
+.delay_slot
+.swstall delay_slot
+         702    0x00 0x00                                                                        NOPX
+.delay_slot
+         704    0x13 0xa0 0xcd 0x98                                                                                                                                                        LSHL r16, r14, r12
+.delay_slot
+         708    0x18 0x66 0xc1 0x58                                                                                                                                                                                      ADD.NC p0, r13, r16
+.delay_slot
+         712    0xfe 0x46 0xb0 0x00 0x01 0xa5 0x70 0x02                                                                                                      ST r17, [sp, #-16];                                         NOPM
+.return_address
+         720    0x04 0x40 0xa1 0x0f 0x41 0xe4                                                                                                                                              MOVX r17, #1;                 MOV dj0, r15
+         726    0xe0 0x4a 0xd0 0x00 0x00 0x1e 0x8b 0xe0 0x10 0xba                                LDA r18, [p7, dj0];                                                                       MOVXM r20, #30656
+         736    0x00 0x00 0x7a 0xaf 0x84 0x44                                                                                                                                              MOVXM r21, #30658
+         742    0x00 0x08 0x00 0xc0 0x00 0x44                                                                                                                                              MOVXM p0, #524288
+         748    0x00 0x70 0x08 0x20 0x06 0x44                                                                                                                                              MOVXM r16, #7340035
+         754    0x00 0x00                                                                        NOPX
+         756    0x00 0x00                                                                        NOPX
+         758    0x00 0x00                                                                        NOPX
+         760    0x14 0xa3 0x1d 0x98                                                                                                                                                        LSHL r17, r18, r17
+         764    0x1c 0x98 0xb9 0x58                                                                                                                                                                                      ADD.NC r18, r17, r14
+         768    0x14 0xa6 0xcd 0x98                                                                                                                                                        LSHL r19, r18, r12
+         772    0x18 0x89 0xa0 0xf8                                                                                                                                                                                      MOV dj0, r19
+         776    0x07 0x02 0xd6 0x98                                                              LDA r22, [p7, dj0]
+         780    0x00 0x00                                                                        NOPX
+         782    0x00 0x00                                                                        NOPX
+         784    0x00 0x00                                                                        NOPX
+         786    0x00 0x00                                                                        NOPX
+         788    0x00 0x00                                                                        NOPX
+         790    0x00 0x00                                                                        NOPX
+         792    0x15 0xb6 0xcc 0x98                                                                                                                                                        LTU r27, r22, r12
+         796    0x15 0x69 0x42 0x18                                                                                                                                                        SEL.EQZ r20, r21, r20, r27
+         800    0x1d 0x1b 0x51 0x58                                                                                                                                                                                      ADD.NC r20, r22, r20
+         804    0x15 0x28 0xcd 0x98                                                                                                                                                        LSHL r20, r20, r12
+         808    0x00 0x2b 0x60 0x00 0x45 0x10 0x70 0x02                                                                                                      NOPS;                                                       MOV dj0, r20
+.label TGT_F_main_592
+.loop_nesting 4
+         816    0x00 0x02 0x93 0x98                                                              LDA.TM r20, [p0, dj0]
+         820    0x00 0x00                                                                        NOPX
+         822    0x00 0x00                                                                        NOPX
+         824    0x00 0x00                                                                        NOPX
+         826    0x00 0x00                                                                        NOPX
+         828    0x00 0x00                                                                        NOPX
+         830    0x00 0x00                                                                        NOPX
+         832    0x15 0x2b 0x04 0x98                                                                                                                                                        AND r21, r20, r16
+         836    0xa8 0x01 0x98 0x40 0x01 0x84                                                                                                                                              JNZ r21, #816
+.delay_slot
+.swstall delay_slot
+         842    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         844    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         846    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         848    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         850    0x00 0x00                                                                        NOPX
+.loop_nesting 3
+         852    0x1b 0xd9 0x00 0x98                                                                                                                                                                                      ADD.NC r15, r18, #1
+         856    0x13 0xdc 0xcd 0x98                                                                                                                                                        LSHL r14, r15, r12
+         860    0x19 0x87 0x20 0xf8                                                                                                                                                                                      MOV dj1, r14
+         864    0x07 0x20 0x16 0x98                                                              LDA r0, [p7, dj1]
+.no_stack_arguments
+         868    0x00 0x02 0xa0 0x00 0x01 0x04                                                                                                                                              JL #1344
+.delay_slot
+.swstall delay_slot
+         874    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+         876    0x00 0x00                                                                        NOPX
+.delay_slot
+         878    0x13 0x5a 0x23 0x18                                                                                                                                                        ADD r13, r13, #8
+.delay_slot
+         882    0x18 0x69 0xb5 0x58                                                                                                                                                                                      ADD.NC p0, r19, r13
+.delay_slot
+         886    0x00 0x2c 0xf7 0xea 0x35 0x80 0x00 0x00 0x00 0x7a                                NOPA;                                                       ST r17, [sp, #-24];           NOPX
+.return_address
+         896    0x00 0x0e 0x00 0x01 0x00 0x28 0x43 0x90 0x78 0xba                                MOVA r14, #0;                                                                             MOVX r16, #1;                 MOV dj0, r14
+         906    0xe0 0x4a 0xd8 0xad 0xfc 0x14                                                    LDA r18, [p7, dj0];                                                                                                     ADD.NC r17, r13, #-4
+         912    0x0f 0xee 0x35 0x98                                                                                                                          ST r17, [sp, #-20]
+         916    0x00 0x00                                                                        NOPX
+         918    0x00 0x00                                                                        NOPX
+         920    0x00 0x00                                                                        NOPX
+         922    0x00 0x00                                                                        NOPX
+         924    0x00 0x00                                                                        NOPX
+         926    0x14 0xa5 0x0d 0x98                                                                                                                                                        LSHL r18, r18, r16
+         930    0x14 0xa1 0x05 0x98                                                                                                                                                        OR r16, r18, r16
+         934    0x1c 0x97 0xc1 0x58                                                                                                                                                                                      ADD.NC r18, r15, r16
+         938    0xfc 0x42 0xb0 0x24 0xc6 0x6c 0x37 0x60 0x79 0x3a                                                                                            ST r16, [sp, #-32];           LSHL r12, r18, r12;           MOV p0, p7
+         948    0xfc 0xca 0xb0 0x23 0x06 0x04 0x43 0x10 0x79 0x3a                                                                                            ST r18, [sp, #-28];           ADD r16, r17, r12;            MOV dj0, r12
+         958    0x00 0x42 0xd7 0xde 0x15 0x80 0x00 0x03 0xb1 0xf0 0x10 0x76                      LDA r16, [p0, dj0];                                         ST r16, [sp, #-36];           MOVXM p7, #992
+         970    0x00 0x00                                                                        NOPX
+         972    0x00 0x00                                                                        NOPX
+         974    0x00 0x00                                                                        NOPX
+         976    0x00 0x00                                                                        NOPX
+         978    0x00 0x00                                                                        NOPX
+         980    0x00 0x00                                                                        NOPX
+         982    0x00 0x2c 0xf0 0x00 0x10 0x01 0xec 0x3f 0xce 0xba                                NOPA;                         NOPB;                                                                                     ADD.NC r15, r16, #-1
+.label TGT_F_main_768
+.loop_nesting 4
+         992    0x12 0xe0 0xe5 0x98                                                                                                                                                        OR r16, r11, r14
+         996    0x80 0x02 0x28 0x40 0x01 0x84                                                                                                                                              JNZ r16, #1104
+.delay_slot
+.swstall delay_slot
+        1002    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1004    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1006    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1008    0x00 0x00                                                                        NOPX
+.delay_slot
+        1010    0x11 0xa1 0x60 0x00 0xc3 0x10 0x70 0x02                                                                                                      MOVS p0, r13;                                               MOV dj1, r12
+        1018    0x07 0xdc 0x99 0x18                                                              LDA p1, [sp, #-36]
+        1022    0x00 0x00                                                                        NOPX
+        1024    0x00 0x00                                                                        NOPX
+        1026    0x00 0x00                                                                        NOPX
+        1028    0x00 0x00                                                                        NOPX
+        1030    0x00 0x00                                                                        NOPX
+        1032    0x00 0x00                                                                        NOPX
+        1034    0x01 0x06 0x16 0x98                                                              LDA r16, [p1]
+        1038    0x00 0x00                                                                        NOPX
+        1040    0x00 0x00                                                                        NOPX
+        1042    0x00 0x00                                                                        NOPX
+        1044    0x00 0x00                                                                        NOPX
+        1046    0x00 0x00                                                                        NOPX
+        1048    0x00 0x00                                                                        NOPX
+        1050    0x80 0x02 0x28 0x00 0x01 0x84                                                                                                                                              JZ r16, #1104
+.delay_slot
+.swstall delay_slot
+        1056    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1058    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1060    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1062    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1064    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1066    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1068    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1070    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1072    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1074    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1076    0x00 0x00                                                                        NOPX
+        1078    0x10 0x08 0x00 0x18                                                                                                                                                        DONE
+.swstall chess_separator_scheduler
+        1082    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1084    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1086    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1088    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1090    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+        1092    0x00 0x2c 0xf0 0x00 0x20 0x00 0x00 0x00 0x00 0xad 0x81 0x36                      NOPA;                         NOPB;                         NOPS;                         NOPX
+.label TGT_F_main_880
+        1104    0x04 0x02 0xd0 0xd9 0x81 0xd4                                                    LDA r0, [p0, dj1];                                                                                                      MOV p0, p6
+.no_stack_arguments
+        1110    0x00 0x04 0x98 0x00 0x01 0x04                                                                                                                                              JL #2352
+.delay_slot
+.swstall delay_slot
+        1116    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1118    0x00 0x00                                                                        NOPX
+.delay_slot
+        1120    0x18 0x55 0x20 0xf8                                                                                                                                                                                      MOV r1, r10
+.delay_slot
+        1124    0x18 0x94 0xa0 0xf8                                                                                                                                                                                      MOV r2, r9
+.delay_slot
+        1128    0x00 0x2b 0x60 0x00 0x6a 0x10 0x70 0x02                                                                                                      NOPS;                                                       MOV r3, r8
+.return_address
+        1136    0x13 0xdf 0xe0 0x18                                                                                                                                                        JNZD r15, r15, p7
+.delay_slot
+.swstall delay_slot
+        1140    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1142    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1144    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1146    0x00 0x00                                                                        NOPX
+.delay_slot
+        1148    0x1b 0x97 0x00 0x98                                                                                                                                                                                      ADD.NC r14, r14, #1
+.loop_nesting 3
+        1152    0xfe 0x46 0x20 0x00 0xc0 0x49 0x6a 0xc0 0x48 0xba                                LDA r17, [sp, #-16];                                                                      MOVX r12, #2;                 ADD.NC r11, r11, #1
+        1162    0xfd 0xca 0x20 0x00 0x00 0x03 0xb1 0x50 0x10 0xba                                LDA r18, [sp, #-20];                                                                      MOVXM p7, #672
+        1172    0x07 0xe6 0x71 0x18                                                              LDA r19, [sp, #-28]
+        1176    0x07 0xe2 0x11 0x18                                                              LDA r16, [sp, #-32]
+        1180    0x07 0xea 0x91 0x18                                                              LDA r20, [sp, #-24]
+        1184    0x00 0x00                                                                        NOPX
+        1186    0x00 0x00                                                                        NOPX
+        1188    0x14 0x63 0xe0 0x18                                                                                                                                                        JNZD r17, r17, p7
+.delay_slot
+        1192    0x14 0x9b 0xf3 0x18                                                                                                                                                        ADD r13, r18, #-4
+.delay_slot
+        1196    0x1c 0x99 0x81 0x98                                                                                                                                                                                      ADD.NC r18, r19, #3
+.delay_slot
+.swstall delay_slot
+        1200    0x00 0x00                                                                        NOPX
+.delay_slot
+        1202    0x1c 0x1a 0x41 0x58                                                                                                                                                                                      ADD.NC r16, r20, r16
+.delay_slot
+        1206    0x1c 0x18 0x02 0x98                                                                                                                                                                                      ADD.NC r16, r16, #5
+.loop_nesting 2
+        1210    0x07 0xd2 0x07 0x8d 0x0b 0x25 0x06 0x6e 0x88 0x3f 0x58 0x76                      MOVA r18, #62;                                              MOVS p7, r13;                 LSHL r16, r18, r12;           MOV r20, #63
+        1222    0x00 0x30 0x00 0x3f 0x67 0xe8 0x44 0x10 0x78 0xba                                MOVA r16, #1;                                                                             MOVX r22, #-1;                MOV dj0, r16
+        1232    0xe0 0x46 0xd0 0x00 0x01 0xee 0x69 0x40 0x10 0xba                                LDA r17, [p7, dj0];                                                                       MOVXM r19, #504448
+        1242    0x9e 0xda 0xfc 0x20 0x01 0x64                                                                                                                                              EQ r27, r19, r13;             MOV r24, #0
+        1248    0x15 0x2f 0x22 0x18                                                                                                                                                        SEL.EQZ r23, r20, r18, r27
+        1252    0x00 0x07 0xba 0xad 0x00 0x44                                                                                                                                              MOVXM r21, #505472
+        1258    0x00 0x00                                                                        NOPX
+        1260    0x00 0x00                                                                        NOPX
+        1262    0x00 0x00                                                                        NOPX
+        1264    0x14 0x74 0xd0 0x18                                                                                                                                                        EQZ r26, r17
+        1268    0x15 0xd1 0x68 0x18                                                                                                                                                        REL r23, r22
+        1272    0x14 0xa5 0x42 0x18                                                                                                                                                        SEL.EQZ r18, r18, r20, r27
+        1276    0x00 0x00                                                                        NOPX
+        1278    0x00 0x00                                                                        NOPX
+        1280    0x14 0x97 0x08 0x18                                                                                                                                                        ACQ.COND r18, r16, r26
+        1284    0x88 0x00 0xd0 0x00 0x01 0x84                                                                                                                                              JZ r17, #416
+.delay_slot
+        1290    0x14 0xe1 0x52 0x18                                                                                                                                                        SEL.EQZ r16, r19, r21, r27
+.delay_slot
+        1294    0x1f 0x68 0x20 0xf8                                                                                                                                                                                      MOV p7, r16
+.delay_slot
+.swstall delay_slot
+        1298    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1300    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1302    0x00 0x00                                                                        NOPX
+.loop_nesting 1
+        1304    0xff 0x03 0x20 0x01 0x90 0x0a 0x08 0x01 0x58 0xba                                LDA p0, [sp, #-8];                                                                        MOVX r25, #0;                 MOV r16, #1
+        1314    0x00 0x00 0x88 0x00 0x00 0x84                                                                                                                                              J #272
+.delay_slot
+.swstall delay_slot
+        1320    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1322    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1324    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1326    0x00 0x00                                                                        NOPX
+.delay_slot
+        1328    0x07 0xf4 0x99 0x18                                                              LDA p1, [sp, #-12]
+.label _main__end
+.label _main___func_end0
+
+.text_segment PM   1344
+.label __ZN3adf11block_writeEPKNS_7reg_valEj___func_begin0
+.label _ZN3adf11block_writeEPKNS_7reg_valEj
+.function_start
+        1344    0x00 0x02 0xf0 0x00 0x01 0x84                                                                                                                                              JZ r0, #1504
+.delay_slot
+.swstall delay_slot
+        1350    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1352    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1354    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1356    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1358    0x00 0x00                                                                        NOPX
+        1360    0xf8 0x1e 0x2a 0xe0 0x41 0xe4                                                                                                                                              MOVX r0, #-4;                 MOV lc, r0
+        1366    0x00 0x00 0x01 0xea 0xe0 0x44                                                                                                                                              MOVXM ls, #1392
+        1372    0x00 0x00 0x06 0xeb 0xa0 0x44                                                                                                                                              MOVXM le, #1488
+        1378    0x00 0x2c 0xf0 0x00 0x20 0x00 0x40 0x16 0x00 0x02 0x00 0x2b 0x60 0x7e            NOPA;                         NOPB;                         NOPS;                         MOVXM p1, #524288
+.label ZLS_F_ZN3adf11block_writeEPKNS_7reg_valEj_48
+.loop_nesting 1
+.begin_of_loop
+        1392    0x00 0x1c 0x56 0x98                                                              LDA r2, [p0], #4
+        1396    0x00 0x1c 0x36 0x98                                                              LDA r1, [p0], #4
+        1400    0x00 0x00                                                                        NOPX
+        1402    0x00 0x2c 0xf0 0x00 0x20 0x3c                                                    NOPA;                         NOPB
+        1408    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+        1424    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+        1440    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+        1456    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x04 0x30 0x24 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         AND r3, r2, r0;               NOPM;                                   NOPV
+        1472    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x40 0xd0 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         MOV dj0, r3;                            NOPV
+.label ZLE_F_ZN3adf11block_writeEPKNS_7reg_valEj_144
+.end_of_loop
+        1488    0x00 0x2c 0xf0 0x00 0x21 0x00 0x3e 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST.TM r1, [p1, dj0];          NOPX;                         NOPM;                                   NOPV
+.label TGT_F_ZN3adf11block_writeEPKNS_7reg_valEj_160
+.loop_nesting 0
+        1504    0x10 0x28 0x00 0x18                                                                                                                                                        RET lr
+.delay_slot
+.swstall delay_slot
+        1508    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1510    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1512    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1514    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1516    0x00 0x00                                                                        NOPX
+.label _ZN3adf11block_writeEPKNS_7reg_valEj__end
+.label __ZN3adf11block_writeEPKNS_7reg_valEj___func_end0
+
+.text_segment PM   1520
+.label _fini
+.function_start
+        1520    0x00 0x08 0x00 0x00 0x01 0xc4                                                                                                                                              PADDXM [sp], #64
+        1526    0xfe 0xba 0xb0 0x00 0x00 0x02 0x08 0x00 0x11 0x3a                                                                                            ST r14, [sp, #-12];           MOVXM r16, #0
+        1536    0xff 0x73 0xb0 0x00 0x00 0x01 0xc8 0x00 0x11 0x3a                                                                                            ST p7, [sp, #-8];             MOVXM r14, #0
+        1546    0x74 0x20 0xfe 0xd0 0x41 0xe4                                                                                                                                              EQ r16, r14, r16;             MOV p7, r16
+        1552    0x80 0x03 0x38 0x40 0x01 0x84                                                                                                                                              JNZ r16, #1648
+.delay_slot
+        1558    0x0f 0xfd 0xf5 0x98                                                                                                                          ST r15, [sp, #-4]
+.delay_slot
+        1562    0x0f 0xf0 0x3d 0x98                                                                                                                          ST lr, [sp, #-16]
+.delay_slot
+.swstall delay_slot
+        1566    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1568    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1570    0x00 0x2c 0xf0 0x02 0xb6 0x00 0x00 0x40 0x1a 0x57 0x00 0x00 0x1c 0x2e            NOPA;                                                       NOPS;                                                       NOPM;                                   NOPV
+.label TGT_F_fini_64
+.loop_nesting 1
+        1584    0x07 0x1c 0x1e 0x98                                                              LDA p0, [p7], #4
+        1588    0x00 0x00                                                                        NOPX
+        1590    0x00 0x00                                                                        NOPX
+        1592    0x00 0x00                                                                        NOPX
+        1594    0x00 0x00                                                                        NOPX
+        1596    0x00 0x00                                                                        NOPX
+        1598    0x00 0x00                                                                        NOPX
+.no_stack_arguments
+        1600    0x10 0x30 0x00 0x18                                                                                                                                                        JL p0
+.delay_slot
+        1604    0x1b 0xde 0xc0 0xf8                                                                                                                                                                                      MOV r15, p7
+.delay_slot
+.swstall delay_slot
+        1608    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1610    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1612    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1614    0x00 0x00                                                                        NOPX
+.return_address
+        1616    0x13 0xe0 0xe8 0x98                                                                                                                                                        NE r16, r15, r14
+        1620    0x80 0x03 0x18 0x40 0x01 0x84                                                                                                                                              JNZ r16, #1584
+.delay_slot
+.swstall delay_slot
+        1626    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1628    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1630    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1632    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1634    0x00 0x2c 0xf0 0x02 0xb6 0x00 0x00 0x40 0x1a 0x57 0x00 0x00 0x1c 0x2e            NOPA;                                                       NOPS;                                                       NOPM;                                   NOPV
+.label TGT_F_fini_128
+.loop_nesting 0
+        1648    0x07 0xf0 0x39 0x18                                                              LDA lr, [sp, #-16]
+        1652    0x07 0xf5 0xd1 0x18                                                              LDA r14, [sp, #-12]
+        1656    0x07 0xfd 0xf1 0x18                                                              LDA r15, [sp, #-4]
+        1660    0x07 0xfb 0x99 0x18                                                              LDA p7, [sp, #-8]
+        1664    0x00 0x00                                                                        NOPX
+        1666    0x00 0x00                                                                        NOPX
+        1668    0x00 0x00                                                                        NOPX
+        1670    0x10 0x28 0x00 0x18                                                                                                                                                        RET lr
+.delay_slot
+        1674    0xff 0xf8 0x00 0x00 0x01 0xc4                                                                                                                                              PADDXM [sp], #-64
+.delay_slot
+.swstall delay_slot
+        1680    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1682    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1684    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1686    0x00 0x00                                                                        NOPX
+.label _fini__end
+
+.text_segment PM   1696
+.label __cxa_finalize
+.function_start
+        1696    0xff 0xa1 0x00 0x00 0x02 0x00 0x00 0x00 0x70 0xba                                MOVA r1, #-3;                                                                             PADDXM [sp], #64
+        1706    0xfb 0x07 0xb0 0x00 0x41 0x08 0x6d 0xe0 0x79 0x3a                                                                                            ST lr, [sp, #-40];            MOVX r4, #8;                  MOV r3, packSign1
+        1716    0xfa 0x8e 0xb0 0x00 0x69 0xe0 0x70 0x02                                                                                                      ST r3, [sp, #-44];                                          MOV r3, packSign0
+        1724    0xfc 0x0e 0xb0 0x00 0x6e 0x30 0x70 0x02                                                                                                      ST r3, [sp, #-32];                                          MOV r3, unpackSign1
+        1732    0xfc 0x8e 0xb0 0x00 0x6a 0x30 0x70 0x02                                                                                                      ST r3, [sp, #-28];                                          MOV r3, unpackSign0
+        1740    0xfd 0x8e 0xb0 0x00 0x01 0xf0 0x32 0x10 0x11 0x3a                                                                                            ST r3, [sp, #-20];            MOVXM p0, #508960
+        1750    0x00 0x8a 0xd1 0xb1 0xc1 0xd4                                                    LDA r2, [p0];                                                                                                           MOV r3, crSRSMode
+        1756    0xfe 0x0e 0xb0 0x00 0x6b 0xb0 0x70 0x02                                                                                                      ST r3, [sp, #-16];                                          MOV r3, crPackSize
+        1764    0xfe 0x8e 0xb0 0x00 0x6a 0x70 0x70 0x02                                                                                                      ST r3, [sp, #-12];                                          MOV r3, crSat
+        1772    0x00 0x92 0x30 0x01 0x2c 0x30 0x70 0x02                                                                                                      ST r4, [p0];                                                MOV r9, upsSign1
+        1780    0xff 0x0e 0xb0 0x01 0x08 0x30 0x70 0x02                                                                                                      ST r3, [sp, #-8];                                           MOV r8, upsSign0
+        1788    0x1a 0xda 0x60 0xf8                                                                                                                                                                                      MOV r11, vaddSign1
+        1792    0x1a 0x92 0x60 0xf8                                                                                                                                                                                      MOV r10, vaddSign0
+        1796    0x10 0xbc 0x66 0x3f 0x81 0xe4                                                                                                                                              ADD r2, r2, #-8;              MOV r12, srsSign1
+        1802    0x13 0x43 0xd0 0xa5 0xc1 0xe4                                                                                                                                              ASHL r13, r2, r1;             MOV r1, crUnpackSize
+        1808    0xff 0x86 0xb0 0x00 0x2f 0xb0 0x70 0x02                                                                                                      ST r1, [sp, #-4];                                           MOV r1, crRnd
+        1816    0xfd 0x06 0xb0 0x00 0x2e 0x70 0x70 0x02                                                                                                      ST r1, [sp, #-24];                                          MOV r1, crUPSMode
+        1824    0xfb 0x86 0xb0 0x01 0xcb 0xe0 0x70 0x02                                                                                                      ST r1, [sp, #-36];                                          MOV r14, srsSign0
+        1832    0x00 0x07 0xc0 0xa8 0x00 0x44                                                                                                                                              MOVXM r1, #508928
+        1838    0x1e 0x60 0x89 0x58                                                                                                                                                                                      ADD.NC p6, r1, r2
+        1842    0x00 0x2c 0xf0 0x00 0x20 0x00 0x00 0x76 0x74 0x02 0x00 0x2b 0x60 0x7e            NOPA;                         NOPB;                         NOPS;                         MOVXM p7, #1856
+.label TGT_F__cxa_finalize_160
+.loop_nesting 1
+        1856    0x06 0x1c 0x9e 0x98                                                              LDA p1, [p6], #4
+        1860    0x06 0xdc 0x1e 0x98                                                              LDA p0, [p6], #-12
+        1864    0x00 0x00                                                                        NOPX
+        1866    0x00 0x00                                                                        NOPX
+        1868    0x00 0x00                                                                        NOPX
+        1870    0x00 0x00                                                                        NOPX
+        1872    0x00 0x00                                                                        NOPX
+.no_stack_arguments
+        1874    0x10 0x30 0x40 0x18                                                                                                                                                        JL p1
+.delay_slot
+        1878    0x1b 0xd0 0x20 0xf8                                                                                                                                                                                      MOV r15, r0
+.delay_slot
+.swstall delay_slot
+        1882    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1884    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1886    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1888    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+.return_address
+        1904    0x13 0x5b 0xe0 0x18                                                                                                                                                        JNZD r13, r13, p7
+.delay_slot
+        1908    0x18 0x17 0xa0 0xf8                                                                                                                                                                                      MOV r0, r15
+.delay_slot
+.swstall delay_slot
+        1912    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1914    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1916    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+        1918    0x00 0x00                                                                        NOPX
+.loop_nesting 0
+        1920    0xfb 0x07 0x20 0x13 0xea 0x02 0x9a 0xd0 0x78 0xba                                LDA lr, [sp, #-40];                                                                       MOVX upsSign1, r9;            MOV vaddSign1, r11
+        1930    0xfa 0x86 0x20 0x11 0xca 0x00 0x9a 0x90 0x78 0xba                                LDA r1, [sp, #-44];                                                                       MOVX upsSign0, r8;            MOV vaddSign0, r10
+        1940    0xfc 0x0a 0x26 0x79 0x80 0x2c                                                    LDA r2, [sp, #-32];                                                                       MOVX srsSign1, r12
+        1946    0xfc 0x8e 0x27 0x71 0x80 0x2c                                                    LDA r3, [sp, #-28];                                                                       MOVX srsSign0, r14
+        1952    0x07 0xec 0xf1 0x18                                                              LDA r7, [sp, #-20]
+        1956    0x07 0xf0 0x91 0x18                                                              LDA r4, [sp, #-16]
+        1960    0x07 0xf4 0xb1 0x18                                                              LDA r5, [sp, #-12]
+        1964    0x07 0xf8 0xd1 0x18                                                              LDA r6, [sp, #-8]
+        1968    0xff 0x86 0x20 0xf8 0x80 0x2c                                                    LDA r1, [sp, #-4];                                                                        MOVX packSign1, r1
+        1974    0xfd 0x0a 0x21 0x70 0x80 0x2c                                                    LDA r2, [sp, #-24];                                                                       MOVX packSign0, r2
+        1980    0xfb 0x8e 0x21 0xfb 0x80 0x2c                                                    LDA r3, [sp, #-36];                                                                       MOVX unpackSign1, r3
+        1986    0xff 0xf8 0x00 0x00 0x01 0xc4                                                                                                                                              PADDXM [sp], #-64
+        1992    0x05 0x00 0x04 0x67 0x41 0xe4                                                                                                                                              RET lr;                       MOV unpackSign0, r7
+.delay_slot
+        1998    0x27 0x60 0x07 0x65 0x41 0xe4                                                                                                                                              MOVX crSRSMode, r4;           MOV crPackSize, r5
+.delay_slot
+        2004    0x11 0xbb 0x80 0x18                                                                                                                                                        MOVX crSat, r6
+.delay_slot
+        2008    0x10 0x7c 0x80 0x18                                                                                                                                                        MOVX crUnpackSize, r1
+.delay_slot
+        2012    0x10 0xba 0x80 0x18                                                                                                                                                        MOVX crRnd, r2
+.delay_slot
+        2016    0x10 0xfc 0x00 0x18                                                                                                                                                        MOVX crUPSMode, r3
+.label __cxa_finalize__end
+
+.bss_segment DMb 504448	    2048
+
+.data_segment DMb 508928
+.label _ZL7atexits
+	0xf0
+	0x5
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+	0x0
+.label _ZL10atexit_cnt
+	0x8
+	0x0
+	0x0
+	0x0
+
+.stack DM_stack 506560 508928

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.map

@@ -0,0 +1,143 @@
+
+// File generated by bridge version V-2024.06#84922c0d9f#241219, Fri Mar 21 03:42:51 2025
+// Copyright 2014-2024 Synopsys, Inc. All rights reserved.
+// bridge -o../Release/0_0 ../Release/0_0.o -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -g -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0.bcf -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/softfloat/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork848 -pme
+
+// Release: ipp V-2024.06-TGT-241219
+
+Memory map for memory 'DM_bankA':
+
+    Size   = 1048576
+    Width  = 8 bits
+    Offset = 0
+    Used   = 36
+
+    0x0007c400..0x0007c41f (        32 items) : atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)::_ZL7atexits (Data, Local, .data.DM_bankA.4)
+
+                Called functions  : _fini
+
+    0x0007c420..0x0007c423 (         4 items) : atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)::_ZL10atexit_cnt (Data, Local, .data.DM_bankA.4)
+
+Memory map for memory 'DM_stack':
+
+    Size   = 1048576
+    Width  = 8 bits
+    Offset = 0
+    Used   = 2368
+
+    0x0007bac0..0x0007c3ff (      2368 items) : Stack
+
+Memory map for memory 'DMb':
+
+    Size   = 1048576
+    Width  = 8 bits
+    Offset = 0
+    Used   = 4452
+
+    0x00000000..0x0007b27f (    504448 items) : Reserved
+    0x0007b280..0x0007b67f (      1024 items) : ../Release/0_0.o::lcpPing (Data, Global, .bss.DMb.4)
+    0x0007b680..0x0007ba7f (      1024 items) : ../Release/0_0.o::lcpPong (Data, Global, .bss.DMb.4)
+    0x0007ba80..0x0007babf (        64 items) : Reserved
+    0x0007bac0..0x0007c3ff (      2368 items) : Stack
+    0x0007c400..0x0007c41f : Occupied in alias or record memory 'DM_bankA' by symbol '_ZL7atexits'
+    0x0007c420..0x0007c423 : Occupied in alias or record memory 'DM_bankA' by symbol '_ZL10atexit_cnt'
+    0x0007c440..0x000fffff (    539584 items) : Reserved
+
+Memory map for memory 'PM':
+
+    Size   = 1048576
+    Width  = 8 bits
+    Offset = 0
+    Used   = 1998
+
+    0x00000000..0x000000df (       224 items) : me_basic.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release/libme.a)::_main_init (Function, Global, .text) (stack frame size = 0)
+
+                Called functions  : _main
+                                    __cxa_finalize
+
+                Referenced symbols: _sp_start_value_DM_stack
+                                    _ctors_start
+                                    _ctors_end
+
+    0x000000e0..0x00000533 (      1108 items) : ../Release/0_0.o::_main (Function, Global, .text) (stack frame size = 192)
+
+                Called functions  : _ZN3adf11block_writeEPKNS_7reg_valEj
+                                    _Z13kernelWrapperPPvjjjj
+
+                Referenced symbols: lcpPing
+                                    lcpPong
+
+    0x00000540..0x000005ed (       174 items) : ../Release/0_0.o::_ZN3adf11block_writeEPKNS_7reg_valEj (Function, Weak, .text) (stack frame size = 0)
+    0x000005f0..0x00000697 (       168 items) : me_basic.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release/libme.a)::_fini (Function, Global, .text) (stack frame size = 64)
+
+                Referenced symbols: _dtors_start
+                                    _dtors_end
+
+    0x000006a0..0x000007e3 (       324 items) : atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)::__cxa_finalize (Function, Global, .text) (stack frame size = 64)
+
+                Referenced symbols: _ZL10atexit_cnt
+                                    _ZL7atexits
+
+    0x00000930..0x00003fff (     14032 items) : Reserved
+
+External symbols:
+
+    _Z13kernelWrapperPPvjjjj = 0x930
+    __dso_handle = 0x0
+    _ctors_end = 0x0
+    _ctors_start = 0x0
+    _dtors_end = 0x0
+    _dtors_start = 0x0
+    _pc_end = 0x7e4
+    _pc_start = 0x0
+    _sp_end_DM_stack = 0x7c400
+    _sp_start_DM_stack = 0x7bac0
+
+Section summary for memory 'DM_bankA':
+
+      .data  File
+ ----------  ----------
+         36  atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
+ ----------  ----------
+         36  Total
+
+Section summary for memory 'DM_stack':
+
+     .stack  File
+ ----------  ----------
+       2368 
+ ----------  ----------
+       2368  Total
+
+Section summary for memory 'DMb':
+
+       .bss       .data  File
+ ----------  ----------  ----------
+       2048           0  ../Release/0_0.o
+          0          36  atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a) (in DM_bankA)
+ ----------  ----------  ----------
+       2048          36  Total
+
+Section summary for memory 'PM':
+
+      .text  File
+ ----------  ----------
+       1282  ../Release/0_0.o
+        392  me_basic.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release/libme.a)
+        324  atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
+ ----------  ----------
+       1998  Total
+
+File summary:
+
+atexit.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release/libc.a)
+            DM_bankA                  36
+                  PM                 324
+
+../Release/0_0.o
+                 DMb                2048
+                  PM                1282
+
+me_basic.o(/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release/libme.a)
+                  PM                 392
+

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.o.lst

@@ -0,0 +1,471 @@
+
+// File generated by darts version V-2024.06#84922c0d9f#241219, Fri Mar 21 03:42:50 2025
+// Copyright 2014-2024 Synopsys, Inc. All rights reserved.
+// darts -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -d -h -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -L +Ihex +nanno ../Release/0_0.o me
+
+// Release: ipp V-2024.06-TGT-241219
+.data_segment_name
+.bss local .at 524288 _ZL22TM_Address_Space_Start TM 4
+
+
+.data_segment_name
+.bss global 4 lcpPing DMb 1024
+
+.data_segment_name
+.bss global 4 lcpPong DMb 1024
+
+.undef global data _ZN12me_primitive11control_satE
+
+.undef global data _ZN12me_primitive11control_rndE
+
+.text_segment_name
+.text weak 16 _ZN3adf11block_writeEPKNS_7reg_valEj
+.label __ZN3adf11block_writeEPKNS_7reg_valEj___func_begin0
+.function_start
+	     0    0x00 0x00 0x50 0x00 0x01 0x84                                                                                                                                              JZ r0, #TGT_F_ZN3adf11block_writeEPKNS_7reg_valEj_160
+.delay_slot
+.swstall delay_slot
+	     6    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	     8    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	    10    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	    12    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	    14    0x00 0x00                                                                        NOPX
+	    16    0xf8 0x1e 0x2a 0xe0 0x41 0xe4                                                                                                                                              MOVX r0, #-4;                 MOV lc, r0
+	    22    0x00 0x00 0x01 0xe0 0x60 0x44                                                                                                                                              MOVXM ls, #(ZLS_F_ZN3adf11block_writeEPKNS_7reg_valEj_48 + 0)
+	    28    0x00 0x00 0x06 0xe1 0x20 0x44                                                                                                                                              MOVXM le, #(ZLE_F_ZN3adf11block_writeEPKNS_7reg_valEj_144 + 0)
+	    34    0x00 0x2c 0xf0 0x00 0x20 0x00 0x40 0x16 0x00 0x02 0x00 0x2b 0x60 0x7e            NOPA;                         NOPB;                         NOPS;                         MOVXM p1, #524288
+.label ZLS_F_ZN3adf11block_writeEPKNS_7reg_valEj_48
+.loop_nesting 1
+.begin_of_loop
+	    48    0x00 0x1c 0x56 0x98                                                              LDA r2, [p0], #4
+	    52    0x00 0x1c 0x36 0x98                                                              LDA r1, [p0], #4
+	    56    0x00 0x00                                                                        NOPX
+	    58    0x00 0x2c 0xf0 0x00 0x20 0x3c                                                    NOPA;                         NOPB
+	    64    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+	    80    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+	    96    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         NOPM;                                   NOPV
+	   112    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x04 0x30 0x24 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         AND r3, r2, r0;               NOPM;                                   NOPV
+	   128    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x00 0x40 0xd0 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         MOV dj0, r3;                            NOPV
+.label ZLE_F_ZN3adf11block_writeEPKNS_7reg_valEj_144
+.end_of_loop
+	   144    0x00 0x2c 0xf0 0x00 0x21 0x00 0x3e 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST.TM r1, [p1, dj0];          NOPX;                         NOPM;                                   NOPV
+.label TGT_F_ZN3adf11block_writeEPKNS_7reg_valEj_160
+.loop_nesting 0
+	   160    0x10 0x28 0x00 0x18                                                                                                                                                        RET lr
+.delay_slot
+.swstall delay_slot
+	   164    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   166    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   168    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   170    0x00 0x00                                                                        NOPX
+.label _ZN3adf11block_writeEPKNS_7reg_valEj__end last
+.label __ZN3adf11block_writeEPKNS_7reg_valEj___func_end0 last
+.delay_slot
+.swstall delay_slot
+	   172    0x00 0x00                                                                        NOPX
+
+.text_segment_name
+.text global 10 _main
+.label _main___func_begin0
+.function_start
+	     0    0xec 0x00 0x80 0x00 0x06 0x00 0x00 0x00 0x70 0xba                                MOVA m0, #-160;                                                                           PADDXM [sp], #192
+	    10    0xe9 0x04 0x80 0x00 0xc0 0x48 0xb2 0xf0 0x78 0xba                                MOVA m1, #-184;                                                                           MOVX r12, #2;                 MOV p1, sp
+	    20    0x00 0x19 0x02 0x17 0x20 0x00 0x4f 0x86 0x0e 0x02 0xd0 0x91 0x60 0x7e            MOVA r25, #0;                 PADDB [p1], m0;               MOVS p6, p1;                  MOVXM p0, #651488
+	    34    0x00 0x2c 0xfc 0x57 0x20 0x20 0x05 0x61 0x00 0x0b 0xff 0x93 0xb0 0x7e            NOPA;                         PADDB [p6], m1;               ST p1, [sp, #-4];             MOVX r16, #1;                 MOV r24, #0
+.label TGT_F_main_48
+.loop_nesting 1
+	    48    0x08 0x4f 0x3e 0x98                                                                                                                          ST.TM r25, [p0], #16
+	    52    0x08 0xcf 0x3e 0x98                                                                                                                          ST.TM r25, [p0], #-16
+	    56    0x00 0x00                                                                        NOPX
+	    58    0x00 0x00                                                                        NOPX
+	    60    0x00 0x00                                                                        NOPX
+	    62    0x17 0xc3 0x08 0x18                                                                                                                                                        ACQ #62, r16
+	    66    0xf4 0x9c 0x80 0x00 0x00 0x03 0xb0 0x00 0x10 0xba                                MOVA m7, #-92;                                                                            MOVXM p7, #lcpPing
+	    76    0x00 0x00                                                                        NOPX
+	    78    0x00 0x00                                                                        NOPX
+	    80    0x0f 0xf8 0x1d 0x98                                                                                                                          ST p0, [sp, #-8]
+	    84    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	    88    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	    92    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	    96    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   100    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   104    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   108    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   112    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   116    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   120    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   124    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   128    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   132    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   136    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   140    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   144    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   148    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   152    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   156    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   160    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   164    0x09 0x1f 0x11 0x98                                                                                                                          ST r24, [p1], #4
+	   168    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   172    0x09 0x1f 0x31 0x98                                                                                                                          ST r25, [p1], #4
+	   176    0x09 0xeb 0x31 0x98                                                                                                                          ST r25, [p1], m7
+	   180    0x00 0x2c 0xf0 0x00 0x20 0x00 0x00 0x03 0xfa 0x4e 0xc1 0x36                      NOPA;                         NOPB;                         ST p1, [sp, #-12];            NOPX
+.label TGT_F_main_192
+.loop_nesting 2
+	   192    0xe3 0xc6 0xd0 0x00 0x00 0x00 0x78 0x88 0x10 0xba                                LDA r17, [p7], #4;                                                                        MOVXM ls, #(ZLS_F_main_272 + 0)
+	   202    0xe3 0xaa 0xd0 0x00 0x00 0x01 0xb8 0xb8 0x10 0xba                                LDA r10, [p7], #4;                                                                        MOVXM le, #(ZLE_F_main_368 + 0)
+	   212    0x07 0x1d 0x36 0x98                                                              LDA r9, [p7], #4
+	   216    0x07 0x1d 0x16 0x98                                                              LDA r8, [p7], #4
+	   220    0x07 0x2e 0x76 0x98                                                              LDA r19, [p7], #8
+	   224    0xff 0x93 0x24 0xdd 0x81 0xd4                                                    LDA p1, [sp, #-4];                                                                                                      MOV p2, p7
+	   230    0x00 0x00                                                                        NOPX
+	   232    0x04 0x00 0x27 0x31 0x39 0xe4                                                                                                                                              MOVX r16, #0;                 MOV el7, r24
+	   238    0x1c 0x90 0x9c 0xf8                                                                                                                                                                                      MOV el9, r16
+	   242    0x1d 0x14 0xa9 0x58                                                                                                                                                                                      ADD.NC r20, r9, r10
+	   246    0x00 0x2c 0xf0 0x98 0x8b 0x02 0x8d 0x10 0xa2 0xba                                NOPA;                                                       MOVS p0, p6;                                                ADD.NC r20, r20, r8
+	   256    0x00 0xd2 0x00 0x00 0x20 0x01 0x5b 0x01 0x30 0x0a 0xbc 0xe8 0xa8 0x00 0x00 0xe1  MOVA r18, #6;                 NOPB;                         NOPS;                         MOVX r19, #0;                 ADD.NC lc, r19, r20;                    NOPV
+.label ZLS_F_main_272
+.loop_nesting 3
+.begin_of_loop
+	   272    0x43 0xe4 0xd1 0x1d 0xe9 0x82 0x6c 0xc0 0x42 0xba                                LDA dn6, [p2], #4;                                          ST el7, [p1], #4;                                           ADD.NC r19, r19, #1
+	   282    0x43 0xd2 0xd9 0x32 0x04 0x14                                                    LDA r20, [p2], #4;                                                                                                      ADD.NC r18, r18, #4
+	   288    0x02 0x1f 0xe6 0x98                                                              LDA dc7, [p2], #4
+	   292    0x02 0x1e 0xee 0x98                                                              LDA el11, [p2], #4
+	   296    0x00 0x00                                                                        NOPX
+	   298    0x00 0x00                                                                        NOPX
+	   300    0x00 0x00                                                                        NOPX
+	   302    0x09 0x1f 0x21 0x98                                                                                                                          ST dn6, [p1], #4
+	   306    0x00 0x00                                                                        NOPX
+	   308    0x09 0x1f 0xe1 0x98                                                                                                                          ST dc7, [p1], #4
+	   312    0x23 0xcd 0x30 0x00 0x01 0xa5 0x70 0x02                                                                                                      ST el9, [p1], #4;                                           NOPM
+	   320    0x00 0x2c 0xf0 0x00 0x21 0x1e 0x91 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST r20, [p1], #4;             NOPX;                         NOPM;                                   NOPV
+	   336    0x00 0x2c 0xf0 0x00 0x21 0xbe 0xe9 0x80 0x00 0x00 0x01 0xa5 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST el11, [p1], #-20;          NOPX;                         NOPM;                                   NOPV
+	   352    0x00 0x2c 0xf0 0x00 0x20 0x01 0x5b 0x00 0x00 0x02 0xa9 0x60 0x78 0x00 0x00 0xe1  NOPA;                         NOPB;                         NOPS;                         NOPX;                         MOV r21, p1;                            NOPV
+.label ZLE_F_main_368
+.end_of_loop
+	   368    0x00 0x2c 0xf0 0x00 0x20 0x1e 0xb1 0x80 0x00 0x00 0xb5 0x46 0x08 0x00 0x00 0xe1  NOPA;                         NOPB;                         ST r21, [p0], #4;             NOPX;                         ADD.NC p1, r21, #24;                    NOPV
+.loop_nesting 2
+	   384    0x00 0x0b 0x00 0x27 0x46 0x6e 0x6f 0x60 0x78 0xba                                MOVA r11, #0;                                                                             LSHL r20, r19, r12;           MOV r19, p7
+	   394    0x9b 0x74 0x69 0xb2 0x01 0x24                                                                                                                                              ADD r13, r19, #-24;           ADD.NC r19, r18, #1
+	   400    0xf1 0xa1 0x60 0x25 0x26 0x6f 0x45 0x10 0x79 0x3a                                                                                            MOVS p7, r13;                 LSHL r18, r18, r12;           MOV dj6, r20
+	   410    0x9c 0x99 0xbb 0x12 0x41 0xe4                                                                                                                                              LSHL r18, r19, r12;           MOV dj5, r18
+	   416    0xf4 0x4a 0xde 0x8d 0x92 0x94                                                    LDA r18, [p7, dj5];                                                                                                     ADD.NC dn7, r13, r18
+	   422    0xd8 0x74 0x30 0x02 0x2c 0x7f 0xc0 0x02                                                                                                      ST dn7, [p6, dj6];                                          ADD.NC r17, r17, #-1
+	   430    0x00 0x00                                                                        NOPX
+	   432    0x00 0x00                                                                        NOPX
+	   434    0x00 0x00                                                                        NOPX
+	   436    0x00 0x00                                                                        NOPX
+	   438    0x00 0x00                                                                        NOPX
+	   440    0x00 0x2b 0x60 0x02 0x4c 0xe4 0xa0 0x02                                                                                                      NOPS;                                                       ADD.NC r18, r19, r18
+.label TGT_F_main_448
+.loop_nesting 3
+	   448    0x14 0xa1 0x01 0x98                                                                                                                                                        SUB r16, r18, r16
+	   452    0x14 0x1e 0xcd 0x98                                                                                                                                                        LSHL r15, r16, r12
+	   456    0xf1 0xa1 0x60 0x03 0xc3 0xd0 0x70 0x02                                                                                                      MOVS p7, r13;                                               MOV dj7, r15
+	   464    0x07 0xe0 0x16 0x98                                                              LDA r0, [p7, dj7]
+.no_stack_arguments
+	   468    0x00 0x00 0x00 0x00 0x01 0x04                                                                                                                                              JL #_ZN3adf11block_writeEPKNS_7reg_valEj
+.delay_slot
+	   474    0x1b 0x98 0x00 0x98                                                                                                                                                                                      ADD.NC r14, r16, #1
+.delay_slot
+.swstall delay_slot
+	   478    0x00 0x00                                                                        NOPX
+.delay_slot
+	   480    0x13 0xa0 0xcd 0x98                                                                                                                                                        LSHL r16, r14, r12
+.delay_slot
+	   484    0x18 0x66 0xc1 0x58                                                                                                                                                                                      ADD.NC p0, r13, r16
+.delay_slot
+	   488    0xfe 0x46 0xb0 0x00 0x01 0xa5 0x70 0x02                                                                                                      ST r17, [sp, #-16];                                         NOPM
+.return_address
+	   496    0x04 0x40 0xa1 0x0f 0x41 0xe4                                                                                                                                              MOVX r17, #1;                 MOV dj0, r15
+	   502    0xe0 0x4a 0xd0 0x00 0x00 0x1e 0x8b 0xe0 0x10 0xba                                LDA r18, [p7, dj0];                                                                       MOVXM r20, #30656
+	   512    0x00 0x00 0x7a 0xaf 0x84 0x44                                                                                                                                              MOVXM r21, #30658
+	   518    0x00 0x08 0x00 0xc0 0x00 0x44                                                                                                                                              MOVXM p0, #524288
+	   524    0x00 0x70 0x08 0x20 0x06 0x44                                                                                                                                              MOVXM r16, #7340035
+	   530    0x00 0x00                                                                        NOPX
+	   532    0x00 0x00                                                                        NOPX
+	   534    0x00 0x00                                                                        NOPX
+	   536    0x14 0xa3 0x1d 0x98                                                                                                                                                        LSHL r17, r18, r17
+	   540    0x1c 0x98 0xb9 0x58                                                                                                                                                                                      ADD.NC r18, r17, r14
+	   544    0x14 0xa6 0xcd 0x98                                                                                                                                                        LSHL r19, r18, r12
+	   548    0x18 0x89 0xa0 0xf8                                                                                                                                                                                      MOV dj0, r19
+	   552    0x07 0x02 0xd6 0x98                                                              LDA r22, [p7, dj0]
+	   556    0x00 0x00                                                                        NOPX
+	   558    0x00 0x00                                                                        NOPX
+	   560    0x00 0x00                                                                        NOPX
+	   562    0x00 0x00                                                                        NOPX
+	   564    0x00 0x00                                                                        NOPX
+	   566    0x00 0x00                                                                        NOPX
+	   568    0x15 0xb6 0xcc 0x98                                                                                                                                                        LTU r27, r22, r12
+	   572    0x15 0x69 0x42 0x18                                                                                                                                                        SEL.EQZ r20, r21, r20, r27
+	   576    0x1d 0x1b 0x51 0x58                                                                                                                                                                                      ADD.NC r20, r22, r20
+	   580    0x15 0x28 0xcd 0x98                                                                                                                                                        LSHL r20, r20, r12
+	   584    0x00 0x2b 0x60 0x00 0x45 0x10 0x70 0x02                                                                                                      NOPS;                                                       MOV dj0, r20
+.label TGT_F_main_592
+.loop_nesting 4
+	   592    0x00 0x02 0x93 0x98                                                              LDA.TM r20, [p0, dj0]
+	   596    0x00 0x00                                                                        NOPX
+	   598    0x00 0x00                                                                        NOPX
+	   600    0x00 0x00                                                                        NOPX
+	   602    0x00 0x00                                                                        NOPX
+	   604    0x00 0x00                                                                        NOPX
+	   606    0x00 0x00                                                                        NOPX
+	   608    0x15 0x2b 0x04 0x98                                                                                                                                                        AND r21, r20, r16
+	   612    0xa8 0x01 0x28 0x40 0x01 0x84                                                                                                                                              JNZ r21, #TGT_F_main_592
+.delay_slot
+.swstall delay_slot
+	   618    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   620    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   622    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   624    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   626    0x00 0x00                                                                        NOPX
+.loop_nesting 3
+	   628    0x1b 0xd9 0x00 0x98                                                                                                                                                                                      ADD.NC r15, r18, #1
+	   632    0x13 0xdc 0xcd 0x98                                                                                                                                                        LSHL r14, r15, r12
+	   636    0x19 0x87 0x20 0xf8                                                                                                                                                                                      MOV dj1, r14
+	   640    0x07 0x20 0x16 0x98                                                              LDA r0, [p7, dj1]
+.no_stack_arguments
+	   644    0x00 0x00 0x00 0x00 0x01 0x04                                                                                                                                              JL #_ZN3adf11block_writeEPKNS_7reg_valEj
+.delay_slot
+.swstall delay_slot
+	   650    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   652    0x00 0x00                                                                        NOPX
+.delay_slot
+	   654    0x13 0x5a 0x23 0x18                                                                                                                                                        ADD r13, r13, #8
+.delay_slot
+	   658    0x18 0x69 0xb5 0x58                                                                                                                                                                                      ADD.NC p0, r19, r13
+.delay_slot
+	   662    0x00 0x2c 0xf7 0xea 0x35 0x80 0x00 0x00 0x00 0x7a                                NOPA;                                                       ST r17, [sp, #-24];           NOPX
+.return_address
+	   672    0x00 0x0e 0x00 0x01 0x00 0x28 0x43 0x90 0x78 0xba                                MOVA r14, #0;                                                                             MOVX r16, #1;                 MOV dj0, r14
+	   682    0xe0 0x4a 0xd8 0xad 0xfc 0x14                                                    LDA r18, [p7, dj0];                                                                                                     ADD.NC r17, r13, #-4
+	   688    0x0f 0xee 0x35 0x98                                                                                                                          ST r17, [sp, #-20]
+	   692    0x00 0x00                                                                        NOPX
+	   694    0x00 0x00                                                                        NOPX
+	   696    0x00 0x00                                                                        NOPX
+	   698    0x00 0x00                                                                        NOPX
+	   700    0x00 0x00                                                                        NOPX
+	   702    0x14 0xa5 0x0d 0x98                                                                                                                                                        LSHL r18, r18, r16
+	   706    0x14 0xa1 0x05 0x98                                                                                                                                                        OR r16, r18, r16
+	   710    0x1c 0x97 0xc1 0x58                                                                                                                                                                                      ADD.NC r18, r15, r16
+	   714    0xfc 0x42 0xb0 0x24 0xc6 0x6c 0x37 0x60 0x79 0x3a                                                                                            ST r16, [sp, #-32];           LSHL r12, r18, r12;           MOV p0, p7
+	   724    0xfc 0xca 0xb0 0x23 0x06 0x04 0x43 0x10 0x79 0x3a                                                                                            ST r18, [sp, #-28];           ADD r16, r17, r12;            MOV dj0, r12
+	   734    0x00 0x42 0xd7 0xde 0x15 0x80 0x00 0x03 0xb1 0x80 0x10 0x76                      LDA r16, [p0, dj0];                                         ST r16, [sp, #-36];           MOVXM p7, #(TGT_F_main_768 + 0)
+	   746    0x00 0x00                                                                        NOPX
+	   748    0x00 0x00                                                                        NOPX
+	   750    0x00 0x00                                                                        NOPX
+	   752    0x00 0x00                                                                        NOPX
+	   754    0x00 0x00                                                                        NOPX
+	   756    0x00 0x00                                                                        NOPX
+	   758    0x00 0x2c 0xf0 0x00 0x10 0x01 0xec 0x3f 0xce 0xba                                NOPA;                         NOPB;                                                                                     ADD.NC r15, r16, #-1
+.label TGT_F_main_768
+.loop_nesting 4
+	   768    0x12 0xe0 0xe5 0x98                                                                                                                                                        OR r16, r11, r14
+	   772    0x80 0x01 0xb8 0x40 0x01 0x84                                                                                                                                              JNZ r16, #TGT_F_main_880
+.delay_slot
+.swstall delay_slot
+	   778    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   780    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   782    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   784    0x00 0x00                                                                        NOPX
+.delay_slot
+	   786    0x11 0xa1 0x60 0x00 0xc3 0x10 0x70 0x02                                                                                                      MOVS p0, r13;                                               MOV dj1, r12
+	   794    0x07 0xdc 0x99 0x18                                                              LDA p1, [sp, #-36]
+	   798    0x00 0x00                                                                        NOPX
+	   800    0x00 0x00                                                                        NOPX
+	   802    0x00 0x00                                                                        NOPX
+	   804    0x00 0x00                                                                        NOPX
+	   806    0x00 0x00                                                                        NOPX
+	   808    0x00 0x00                                                                        NOPX
+	   810    0x01 0x06 0x16 0x98                                                              LDA r16, [p1]
+	   814    0x00 0x00                                                                        NOPX
+	   816    0x00 0x00                                                                        NOPX
+	   818    0x00 0x00                                                                        NOPX
+	   820    0x00 0x00                                                                        NOPX
+	   822    0x00 0x00                                                                        NOPX
+	   824    0x00 0x00                                                                        NOPX
+	   826    0x80 0x01 0xb8 0x00 0x01 0x84                                                                                                                                              JZ r16, #TGT_F_main_880
+.delay_slot
+.swstall delay_slot
+	   832    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   834    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   836    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   838    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   840    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   842    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   844    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   846    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   848    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   850    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   852    0x00 0x00                                                                        NOPX
+	   854    0x10 0x08 0x00 0x18                                                                                                                                                        DONE
+.swstall chess_separator_scheduler
+	   858    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   860    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   862    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   864    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   866    0x00 0x00                                                                        NOPX
+.swstall chess_separator_scheduler
+	   868    0x00 0x2c 0xf0 0x00 0x20 0x00 0x00 0x00 0x00 0xad 0x81 0x36                      NOPA;                         NOPB;                         NOPS;                         NOPX
+.label TGT_F_main_880
+	   880    0x04 0x02 0xd0 0xd9 0x81 0xd4                                                    LDA r0, [p0, dj1];                                                                                                      MOV p0, p6
+.no_stack_arguments
+	   886    0x00 0x00 0x00 0x00 0x01 0x04                                                                                                                                              JL #_Z13kernelWrapperPPvjjjj
+.delay_slot
+.swstall delay_slot
+	   892    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   894    0x00 0x00                                                                        NOPX
+.delay_slot
+	   896    0x18 0x55 0x20 0xf8                                                                                                                                                                                      MOV r1, r10
+.delay_slot
+	   900    0x18 0x94 0xa0 0xf8                                                                                                                                                                                      MOV r2, r9
+.delay_slot
+	   904    0x00 0x2b 0x60 0x00 0x6a 0x10 0x70 0x02                                                                                                      NOPS;                                                       MOV r3, r8
+.return_address
+	   912    0x13 0xdf 0xe0 0x18                                                                                                                                                        JNZD r15, r15, p7
+.delay_slot
+.swstall delay_slot
+	   916    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   918    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   920    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	   922    0x00 0x00                                                                        NOPX
+.delay_slot
+	   924    0x1b 0x97 0x00 0x98                                                                                                                                                                                      ADD.NC r14, r14, #1
+.loop_nesting 3
+	   928    0xfe 0x46 0x20 0x00 0xc0 0x49 0x6a 0xc0 0x48 0xba                                LDA r17, [sp, #-16];                                                                      MOVX r12, #2;                 ADD.NC r11, r11, #1
+	   938    0xfd 0xca 0x20 0x00 0x00 0x03 0xb0 0xe0 0x10 0xba                                LDA r18, [sp, #-20];                                                                      MOVXM p7, #(TGT_F_main_448 + 0)
+	   948    0x07 0xe6 0x71 0x18                                                              LDA r19, [sp, #-28]
+	   952    0x07 0xe2 0x11 0x18                                                              LDA r16, [sp, #-32]
+	   956    0x07 0xea 0x91 0x18                                                              LDA r20, [sp, #-24]
+	   960    0x00 0x00                                                                        NOPX
+	   962    0x00 0x00                                                                        NOPX
+	   964    0x14 0x63 0xe0 0x18                                                                                                                                                        JNZD r17, r17, p7
+.delay_slot
+	   968    0x14 0x9b 0xf3 0x18                                                                                                                                                        ADD r13, r18, #-4
+.delay_slot
+	   972    0x1c 0x99 0x81 0x98                                                                                                                                                                                      ADD.NC r18, r19, #3
+.delay_slot
+.swstall delay_slot
+	   976    0x00 0x00                                                                        NOPX
+.delay_slot
+	   978    0x1c 0x1a 0x41 0x58                                                                                                                                                                                      ADD.NC r16, r20, r16
+.delay_slot
+	   982    0x1c 0x18 0x02 0x98                                                                                                                                                                                      ADD.NC r16, r16, #5
+.loop_nesting 2
+	   986    0x07 0xd2 0x07 0x8d 0x0b 0x25 0x06 0x6e 0x88 0x3f 0x58 0x76                      MOVA r18, #62;                                              MOVS p7, r13;                 LSHL r16, r18, r12;           MOV r20, #63
+	   998    0x00 0x30 0x00 0x3f 0x67 0xe8 0x44 0x10 0x78 0xba                                MOVA r16, #1;                                                                             MOVX r22, #-1;                MOV dj0, r16
+	  1008    0xe0 0x46 0xd0 0x00 0x00 0x02 0x68 0x00 0x10 0xba                                LDA r17, [p7, dj0];                                                                       MOVXM r19, #lcpPing
+	  1018    0x9e 0xda 0xfc 0x20 0x01 0x64                                                                                                                                              EQ r27, r19, r13;             MOV r24, #0
+	  1024    0x15 0x2f 0x22 0x18                                                                                                                                                        SEL.EQZ r23, r20, r18, r27
+	  1028    0x00 0x00 0x0a 0xa0 0x00 0x44                                                                                                                                              MOVXM r21, #lcpPong
+	  1034    0x00 0x00                                                                        NOPX
+	  1036    0x00 0x00                                                                        NOPX
+	  1038    0x00 0x00                                                                        NOPX
+	  1040    0x14 0x74 0xd0 0x18                                                                                                                                                        EQZ r26, r17
+	  1044    0x15 0xd1 0x68 0x18                                                                                                                                                        REL r23, r22
+	  1048    0x14 0xa5 0x42 0x18                                                                                                                                                        SEL.EQZ r18, r18, r20, r27
+	  1052    0x00 0x00                                                                        NOPX
+	  1054    0x00 0x00                                                                        NOPX
+	  1056    0x14 0x97 0x08 0x18                                                                                                                                                        ACQ.COND r18, r16, r26
+	  1060    0x88 0x00 0x60 0x00 0x01 0x84                                                                                                                                              JZ r17, #TGT_F_main_192
+.delay_slot
+	  1066    0x14 0xe1 0x52 0x18                                                                                                                                                        SEL.EQZ r16, r19, r21, r27
+.delay_slot
+	  1070    0x1f 0x68 0x20 0xf8                                                                                                                                                                                      MOV p7, r16
+.delay_slot
+.swstall delay_slot
+	  1074    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	  1076    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	  1078    0x00 0x00                                                                        NOPX
+.loop_nesting 1
+	  1080    0xff 0x03 0x20 0x01 0x90 0x0a 0x08 0x01 0x58 0xba                                LDA p0, [sp, #-8];                                                                        MOVX r25, #0;                 MOV r16, #1
+	  1090    0x00 0x00 0x18 0x00 0x00 0x84                                                                                                                                              J #TGT_F_main_48
+.delay_slot
+.swstall delay_slot
+	  1096    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	  1098    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	  1100    0x00 0x00                                                                        NOPX
+.delay_slot
+.swstall delay_slot
+	  1102    0x00 0x00                                                                        NOPX
+.label _main__end last
+.label _main___func_end0 last
+.delay_slot
+	  1104    0x07 0xf4 0x99 0x18                                                              LDA p1, [sp, #-12]
+
+.undef global data main
+
+.undef global data lcpPing
+
+.undef global data lcpPong
+
+.undef global text _ZN3adf11block_writeEPKNS_7reg_valEj
+
+.undef global text _Z13kernelWrapperPPvjjjj
+
+
+
+.direct_eval +,-,(,)

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/Release/0_0.sdr

@@ -0,0 +1,90 @@
+
+// File generated by bridge version V-2024.06#84922c0d9f#241219, Fri Mar 21 03:42:51 2025
+// Copyright 2014-2024 Synopsys, Inc. All rights reserved.
+// bridge -o../Release/0_0 ../Release/0_0.o -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/isg -g -I/usr/local/lib/python3.10/dist-packages/include -I/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend -I/usr/local/lib/python3.10/site-packages/include/aie_api -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common -I/usr/local/lib/python3.10/dist-packages/vitis_mllib -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc -I/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf -I/app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/. -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/include -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libs/libcxx-9.0.0/include-lite -I/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/include -D__AIENGINE__ -D__AIE_ARCH__=21 -DDEPLOYMENT_ELF=1 -D__LOCK_FENCE_MODE__=0 -D__IO_BUFFER_FORCE_LIGHT_WEIGHT__ -DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1 -DAIE_OPTION_SCALAR_FLOAT_ON_VECTOR -D__tct_tgt__=241219 -c0_0.bcf -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/softfloat/lib/Release -L/usr/local/lib/python3.10/dist-packages/data/aie2p/lib/runtime_cxx/libcxx-lite/lib/Release_LLVM -lme -lc -lm -lc++lite -lsoftfloat -S -export-locals -iconfig extra_memories.bcf -yTM -m -fC -fS -fH +m -T +work ../Release/chesswork848 -pme
+
+// Release: ipp V-2024.06-TGT-241219
+
+// Symbols in memory 'DM_bankA':
+// Symbols in memory 'DM_bankAB':
+// Symbols in memory 'DM_bankAC':
+// Symbols in memory 'DM_bankAD':
+// Symbols in memory 'DM_bankB':
+// Symbols in memory 'DM_bankBC':
+// Symbols in memory 'DM_bankBD':
+// Symbols in memory 'DM_bankC':
+// Symbols in memory 'DM_bankCD':
+// Symbols in memory 'DM_bankD':
+// Symbols in memory 'DM_stack':
+// Symbols in memory 'DM_test':
+// Symbols in memory 'DMb':
+_symbol lcpPing 0x0007b280
+_symbol lcpPong 0x0007b680
+// Symbols in memory 'DMh':
+// Symbols in memory 'DMh_bankA':
+// Symbols in memory 'DMh_bankAB':
+// Symbols in memory 'DMh_bankAC':
+// Symbols in memory 'DMh_bankAD':
+// Symbols in memory 'DMh_bankB':
+// Symbols in memory 'DMh_bankBC':
+// Symbols in memory 'DMh_bankBD':
+// Symbols in memory 'DMh_bankC':
+// Symbols in memory 'DMh_bankCD':
+// Symbols in memory 'DMh_bankD':
+// Symbols in memory 'DMh_stack':
+// Symbols in memory 'DMs':
+// Symbols in memory 'DMs_bankA':
+// Symbols in memory 'DMs_bankAB':
+// Symbols in memory 'DMs_bankAC':
+// Symbols in memory 'DMs_bankAD':
+// Symbols in memory 'DMs_bankB':
+// Symbols in memory 'DMs_bankBC':
+// Symbols in memory 'DMs_bankBD':
+// Symbols in memory 'DMs_bankC':
+// Symbols in memory 'DMs_bankCD':
+// Symbols in memory 'DMs_bankD':
+// Symbols in memory 'DMs_stack':
+// Symbols in memory 'DMv':
+// Symbols in memory 'DMv_bankA':
+// Symbols in memory 'DMv_bankAB':
+// Symbols in memory 'DMv_bankAC':
+// Symbols in memory 'DMv_bankAD':
+// Symbols in memory 'DMv_bankB':
+// Symbols in memory 'DMv_bankBC':
+// Symbols in memory 'DMv_bankBD':
+// Symbols in memory 'DMv_bankC':
+// Symbols in memory 'DMv_bankCD':
+// Symbols in memory 'DMv_bankD':
+// Symbols in memory 'DMv_stack':
+// Symbols in memory 'DMw':
+// Symbols in memory 'DMw_bankA':
+// Symbols in memory 'DMw_bankAB':
+// Symbols in memory 'DMw_bankAC':
+// Symbols in memory 'DMw_bankAD':
+// Symbols in memory 'DMw_bankB':
+// Symbols in memory 'DMw_bankBC':
+// Symbols in memory 'DMw_bankBD':
+// Symbols in memory 'DMw_bankC':
+// Symbols in memory 'DMw_bankCD':
+// Symbols in memory 'DMw_bankD':
+// Symbols in memory 'DMw_stack':
+// Symbols in memory 'DMx':
+// Symbols in memory 'DMx_bankA':
+// Symbols in memory 'DMx_bankAB':
+// Symbols in memory 'DMx_bankAC':
+// Symbols in memory 'DMx_bankAD':
+// Symbols in memory 'DMx_bankB':
+// Symbols in memory 'DMx_bankBC':
+// Symbols in memory 'DMx_bankBD':
+// Symbols in memory 'DMx_bankC':
+// Symbols in memory 'DMx_bankCD':
+// Symbols in memory 'DMx_bankD':
+// Symbols in memory 'DMx_stack':
+// Symbols in memory 'PM':
+_symbol _main_init 0x00000000
+_symbol _main 0x000000e0
+_symbol _ZN3adf11block_writeEPKNS_7reg_valEj 0x00000540
+_symbol _fini 0x000005f0
+_symbol __cxa_finalize 0x000006a0
+// Symbols in memory 'PMw':
+// Symbols in memory 'TM4':

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/elf_ctrl_pkt.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bae6d17370fa6ff9dce1f15ddab525892dba32c85b49d7303d98c7938009da9
+size 6148

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981b0e1230eb5dbd26bf35b2717875f8d4f352bc7974fd48c2ee0d81ca343686
+size 296

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06471c10dc9f1b825c878a76d2d029bada052ace379236c9916a0d302d6e270
+size 300

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_100.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae43a8dcc0cd99130f42249d4f2a9f1fc91c3c99699db65bb98ad360a326ef6
+size 376

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/lcp/0_0_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05761cae01b301200d2d2ef4aa2f3f81493591bd9ea0b012b956cd6fef12f5dd
+size 384

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/Work/aie/0_0/xlopt.log

@@ -0,0 +1,81 @@
+ERROR: ld.so: object '/lib64/libudev.so.1' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
+
+
+--------------- FILTER ANALYSIS INFO LOG ---------------
+
+Reading Header IR from ir/_header.ll 
+
+--------------------------------------------------------
+
+Add module pass 363{anonymous}::GuidancePass
+Add module pass 363{anonymous}::ChessOptionsPass
+Add module pass 363{anonymous}::DisableInliningInMainPass
+Add module pass 363cdno::xlopt::AIEMergeSubWordStoresOpt
+Add module pass 363{anonymous}::XLModuleAdaptor<llvm::PromotePass>
+Add module pass 363{anonymous}::IpConstPropPass
+Add module pass 363{anonymous}::XLModuleAdaptor<llvm::SimplifyCFGPass>
+Add module pass 363{anonymous}::XLModuleAdaptor<llvm::LoopSimplifyPass>
+Add module pass 363{anonymous}::XLModuleAdaptor<llvm::FunctionToLoopPassAdaptor>
+Add module pass 363{anonymous}::XLModuleAdaptor<{anonymous}::AIELoopInfoPass>
+Add module pass 363cdno::xlopt::AIEAnnotatePragmaPass
+Add module pass 363{anonymous}::XLModuleAdaptor<{anonymous}::AIELoopPeelPass>
+Add module pass 363{anonymous}::AIEAliasAnalysisPass
+
+
+--------------- MEMORY MANAGEMENT GUIDANCE LOG ---------------
+
+SIZE_HINT: Global array lcpPing is 1024 bytes. Consider making it mapper-managed LUT or memory buffer.
+SIZE_HINT: Global array lcpPong is 1024 bytes. Consider making it mapper-managed LUT or memory buffer.
+GLOBAL_RBW_HINT: Global variable 'lcpPong' reads its default/external initialization at 0_0/src/0_0.cc:81 in kernel 'main', and is not explicitly written before this read
+GLOBAL_CONFLICT_HINT: Kernels 'block_write' and 'initialize_lock' have no execution dependence, but access the same global variable 'TM_Address_Space_Start', and one of those accesses is a write
+GLOBAL_CONFLICT_HINT: Kernels 'block_write' and 'wait_dma_channel_done' have no execution dependence, but access the same global variable 'TM_Address_Space_Start', and one of those accesses is a write
+GLOBAL_CONFLICT_HINT: Kernels 'initialize_lock' and 'wait_dma_channel_done' have no execution dependence, but access the same global variable 'TM_Address_Space_Start', and one of those accesses is a write
+
+--------------------------------------------------------------
+
+
+
+--------------- MERGING SUBWORD STORES OPT LOG  ---------------
+
+
+
+--------------- LOOP STATISTICS : main ---------------
+
+Total loops = 7
+Loops with prepare for pipelining pragma = 0
+Loops with unroll pragma = 0
+Loops with flatten pragma = 0
+Loops with min range pragma = 4
+Loops with max range pragma = 2
+Loops with known trip count = 0
+
+------------------------------------------------------
+
+
+
+--------------- LOOP STATISTICS : _ZN3adf11block_writeEPKNS_7reg_valEj ---------------
+
+Total loops = 1
+Loops with prepare for pipelining pragma = 0
+Loops with unroll pragma = 0
+Loops with flatten pragma = 0
+Loops with min range pragma = 0
+Loops with max range pragma = 0
+Loops with known trip count = 0
+
+--------------------------------------------------------------------------------------
+
+
+
+--------------- LOOP STATISTICS : _ZN3adf21wait_dma_channel_doneEj ---------------
+
+Total loops = 1
+Loops with prepare for pipelining pragma = 0
+Loops with unroll pragma = 0
+Loops with flatten pragma = 0
+Loops with min range pragma = 0
+Loops with max range pragma = 0
+Loops with known trip count = 0
+
+----------------------------------------------------------------------------------
+

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/aie.mk

@@ -0,0 +1,2 @@
+aiecompile:
+	aiecompiler /app/vaiml_1.3_examples/camo/segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend/top.cpp   --part=xc10AIE2P_ML-die-0x-e-S-es1 --nodot-graph --runtime-opt=1 --disable-multirate-analysis --enable-core-processor-bus --enable-multi-layer --heapsize=1792 --stacksize=1400  --max-layer-ctrl-param-size=256 --compile-for-aiesim=false --workdir=Work --multi-layer-ctrl-pkt --aie2ipu-base-addr=0 -enable-light-cdo --Xelfgen=-j4   --multi-layer-pipelining --multi-layer-opt=3 --Xpreproc=-D__IO_BUFFER_FORCE_LIGHT_WEIGHT__   --multi-layer-ext-buf-file=/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend/flexmlrt-hsi.json --enable-partition=0:4  --multi-layer-ctrl-pkt-column-span=4  --multi-layer-prebuilt-archive=/usr/local/lib/python3.10/dist-packages/flexml/flexml_extras/data/ryzen-ai/stx/unified-overlay-4x4.json --multi-layer-prebuilt-archive-enable-elf-gen --multi-layer-init-core-elf-ctrl-pkt --multi-layer-pm-id 29006 --Xpreproc="-DAIE_API_EMULATE_BFLOAT16_MMUL_WITH_BFP16=1"  --include=/app/vaiml_1.3_examples/camo/./segmentation_1_4_0_fp32_combined/vaiml_par_0/0/backend --include=/usr/local/lib/python3.10/site-packages/include/aie_api --include=/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/common --include=/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/include/common --include=/usr/local/lib/python3.10/dist-packages/vitis_mllib --include=/usr/local/lib/python3.10/dist-packages/vitis_mllib/L1/include/misc --include=/usr/local/lib/python3.10/dist-packages/vitis_mllib/L2/src/ml_adf --output-archive libadf.a --adf-api-log-level=0  --multi-layer-pm-reloading=1  --Xelfgen=-j1 

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/aiecompiler/xcd.log

@@ -0,0 +1,30 @@
+Fri Mar 21 03:30:56 2025: Running xcd server. This server was built by gradle.
+Fri Mar 21 03:30:56 2025: Server was asked to start on port: '34917'
+Fri Mar 21 03:30:56 2025: Server is using token UUID: 'e14f6479-c44a-42cf-8f07-308e6ee9c741'
+Fri Mar 21 03:30:56 2025: SESSION_MGR: creating session with session uuid: '6d04a3e9-ade5-4ab9-8d63-1f78fcd2ec76' and name 'default'
+Fri Mar 21 03:30:56 2025: Attempting to start server on port '34917'
+Fri Mar 21 03:30:56 2025: XCD main fifo: created main fifo '/tmp/xcdmaine14f6479-c44a-42cf-8f07-308e6ee9c741', fd read = 12
+Fri Mar 21 03:30:56 2025: Running Dispatch Server
+Fri Mar 21 03:30:56 2025: Version 2.2.0
+Fri Mar 21 03:30:57 2025: Dispatch Server: Accepted socket connection from client
+Fri Mar 21 03:30:57 2025: Starting Socket connection
+Fri Mar 21 03:30:57 2025: EXCHANGE_TOKEN received, server token: e14f6479-c44a-42cf-8f07-308e6ee9c741, passed token: e14f6479-c44a-42cf-8f07-308e6ee9c741
+Fri Mar 21 03:30:57 2025: SESSION_MGR: creating session with session uuid: 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' and name 'AIE Compilation'
+Fri Mar 21 03:30:57 2025: KERNEL_SVC: creating session with uuid: 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' and name 'AIE Compilation'
+Fri Mar 21 03:30:57 2025: GUIDANCE_SMGR: creating guidance session with uuid: 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' and name 'AIE Compilation'
+Fri Mar 21 03:31:54 2025: Dispatch Server: Accepted socket connection from client
+Fri Mar 21 03:31:54 2025: Starting Socket connection
+Fri Mar 21 04:04:52 2025: SESSION_MGR: closing session for UUID 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' with name ''
+Fri Mar 21 04:04:52 2025: KERNEL_SVC: closing session for UUID 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' with name ''
+Fri Mar 21 04:04:52 2025: GUIDANCE_SMGR: closing session for UUID 'bef5681c-a6ee-487a-8b13-f1c9f1805b32' with name ''
+Fri Mar 21 04:04:52 2025: STOP_SERVER received, server token: e14f6479-c44a-42cf-8f07-308e6ee9c741, passed token: e14f6479-c44a-42cf-8f07-308e6ee9c741
+Fri Mar 21 04:04:52 2025: Socket received request to stop server.
+Fri Mar 21 04:04:52 2025: Dispatch Server: do_await_stop
+Fri Mar 21 04:04:52 2025: Dispatch Server: stopping mainFifo_
+Fri Mar 21 04:04:52 2025: XCD main fifo: Stopping
+Fri Mar 21 04:04:52 2025: XCD main fifo: do_read error code: Operation canceled
+Fri Mar 21 04:04:52 2025: XCD main fifo: bytes_transferred: 0
+Fri Mar 21 04:04:52 2025: SERVER: destructor for server bound to port 34917
+Fri Mar 21 04:04:52 2025: XCD main fifo: Good unlink of /tmp/xcdmaine14f6479-c44a-42cf-8f07-308e6ee9c741
+Fri Mar 21 04:04:52 2025: Server exiting with status 0.
+Fri Mar 21 04:04:52 2025: Closing log file.

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/flexmlrt-hsi.json

@@ -0,0 +1,1253 @@
+{
+    "inputs" : [
+        {
+            "name" : "compute_graph.ifm_ddr",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                180,
+                320,
+                4
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                320,
+                23,
+                4,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ifm_ddr_1",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                16,
+                90,
+                160
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                90,
+                2,
+                160,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ifm_ddr_2",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                20,
+                45,
+                80
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                45,
+                3,
+                80,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ifm_ddr_3",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                40,
+                23,
+                40
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                23,
+                5,
+                40,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ifm_ddr_4",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                64,
+                12,
+                20
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                12,
+                8,
+                20,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        }
+    ],
+    "outputs" : [
+        {
+            "name" : "compute_graph.ofm_ddr_3_l2l3_291_spill",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                16,
+                90,
+                160
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                90,
+                2,
+                160,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ofm_ddr_2_l2l3_272_spill",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                20,
+                45,
+                80
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                45,
+                3,
+                80,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ofm_ddr_1_l2l3_252_spill",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                40,
+                23,
+                40
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                23,
+                5,
+                40,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ofm_ddr_0_l2l3_229_spill",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                64,
+                12,
+                20
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                12,
+                8,
+                20,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ofm_ddr_5",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                3,
+                180,
+                320
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                180,
+                1,
+                320,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        },
+        {
+            "name" : "compute_graph.ofm_ddr_4",
+            "scale_factor" : -1,
+            "cpu_shape" : [
+                1,
+                1,
+                180,
+                320
+            ],
+            "cpu_format" : "NCHW",
+            "cpu_dtype" : "fp32",
+            "hw_shape" : [
+                180,
+                1,
+                320,
+                1,
+                8
+            ],
+            "hw_format" : "HCWNC8",
+            "hw_dtype" : "bf16"
+        }
+    ],
+    "weights" : {
+        "layers" : [
+            {
+                "name" : "compute_graph.Layer_8_wts_ddr",
+                "offset" : 0
+            },
+            {
+                "name" : "compute_graph.Layer_13_wts_ddr",
+                "offset" : 1216
+            },
+            {
+                "name" : "compute_graph.Layer_14_wts_ddr",
+                "offset" : 1472
+            },
+            {
+                "name" : "compute_graph.Layer_15_wts_ddr",
+                "offset" : 2560
+            },
+            {
+                "name" : "compute_graph.Layer_16_wts_ddr",
+                "offset" : 4736
+            },
+            {
+                "name" : "compute_graph.Layer_18_wts_ddr",
+                "offset" : 5248
+            },
+            {
+                "name" : "compute_graph.Layer_19_wts_ddr",
+                "offset" : 7424
+            },
+            {
+                "name" : "compute_graph.Layer_20_wts_ddr",
+                "offset" : 10688
+            },
+            {
+                "name" : "compute_graph.Layer_22_wts_ddr",
+                "offset" : 11456
+            },
+            {
+                "name" : "compute_graph.Layer_23_wts_ddr",
+                "offset" : 13888
+            },
+            {
+                "name" : "compute_graph.Layer_24_wts_ddr",
+                "offset" : 17152
+            },
+            {
+                "name" : "compute_graph.Layer_27_wts_ddr",
+                "offset" : 19264
+            },
+            {
+                "name" : "compute_graph.Layer_28_wts_ddr",
+                "offset" : 21696
+            },
+            {
+                "name" : "compute_graph.Layer_34_wts_ddr",
+                "offset" : 26048
+            },
+            {
+                "name" : "compute_graph.Layer_35_wts_ddr",
+                "offset" : 28480
+            },
+            {
+                "name" : "compute_graph.Layer_36_wts_ddr",
+                "offset" : 32832
+            },
+            {
+                "name" : "compute_graph.Layer_39_wts_ddr",
+                "offset" : 35648
+            },
+            {
+                "name" : "compute_graph.Layer_40_wts_ddr",
+                "offset" : 39616
+            },
+            {
+                "name" : "compute_graph.Layer_46_wts_ddr",
+                "offset" : 43968
+            },
+            {
+                "name" : "compute_graph.Layer_47_wts_ddr",
+                "offset" : 48320
+            },
+            {
+                "name" : "compute_graph.Layer_48_wts_ddr",
+                "offset" : 52672
+            },
+            {
+                "name" : "compute_graph.Layer_51_wts_ddr",
+                "offset" : 55488
+            },
+            {
+                "name" : "compute_graph.Layer_52_wts_ddr",
+                "offset" : 59456
+            },
+            {
+                "name" : "compute_graph.Layer_58_wts_ddr",
+                "offset" : 63808
+            },
+            {
+                "name" : "compute_graph.Layer_59_wts_ddr",
+                "offset" : 68160
+            },
+            {
+                "name" : "compute_graph.Layer_65_wts_ddr",
+                "offset" : 76864
+            },
+            {
+                "name" : "compute_graph.Layer_70_wts_ddr",
+                "offset" : 78912
+            },
+            {
+                "name" : "compute_graph.Layer_71_wts_ddr",
+                "offset" : 91008
+            },
+            {
+                "name" : "compute_graph.Layer_76_wts_ddr",
+                "offset" : 101760
+            },
+            {
+                "name" : "compute_graph.Layer_81_wts_ddr",
+                "offset" : 103552
+            },
+            {
+                "name" : "compute_graph.Layer_82_wts_ddr",
+                "offset" : 113920
+            },
+            {
+                "name" : "compute_graph.Layer_87_wts_ddr",
+                "offset" : 121984
+            },
+            {
+                "name" : "compute_graph.Layer_92_wts_ddr",
+                "offset" : 123520
+            },
+            {
+                "name" : "compute_graph.Layer_93_wts_ddr",
+                "offset" : 133120
+            },
+            {
+                "name" : "compute_graph.Layer_98_wts_ddr",
+                "offset" : 141184
+            },
+            {
+                "name" : "compute_graph.Layer_103_wts_ddr",
+                "offset" : 142720
+            },
+            {
+                "name" : "compute_graph.Layer_104_wts_ddr",
+                "offset" : 152320
+            },
+            {
+                "name" : "compute_graph.Layer_109_wts_ddr",
+                "offset" : 172480
+            },
+            {
+                "name" : "compute_graph.Layer_116_wts_ddr",
+                "offset" : 176320
+            },
+            {
+                "name" : "compute_graph.Layer_117_wts_ddr",
+                "offset" : 208064
+            },
+            {
+                "name" : "compute_graph.Layer_123_wts_ddr",
+                "offset" : 239808
+            },
+            {
+                "name" : "compute_graph.Layer_124_wts_ddr",
+                "offset" : 271808
+            },
+            {
+                "name" : "compute_graph.Layer_129_wts_ddr",
+                "offset" : 317504
+            },
+            {
+                "name" : "compute_graph.Layer_136_wts_ddr",
+                "offset" : 322880
+            },
+            {
+                "name" : "compute_graph.Layer_137_wts_ddr",
+                "offset" : 390080
+            },
+            {
+                "name" : "compute_graph.Layer_143_wts_ddr",
+                "offset" : 450624
+            },
+            {
+                "name" : "compute_graph.Layer_144_wts_ddr",
+                "offset" : 495424
+            },
+            {
+                "name" : "compute_graph.Layer_149_wts_ddr",
+                "offset" : 541120
+            },
+            {
+                "name" : "compute_graph.Layer_156_wts_ddr",
+                "offset" : 578752
+            },
+            {
+                "name" : "compute_graph.Layer_157_wts_ddr",
+                "offset" : 645952
+            },
+            {
+                "name" : "compute_graph.Layer_163_wts_ddr",
+                "offset" : 706496
+            },
+            {
+                "name" : "compute_graph.Layer_164_wts_ddr",
+                "offset" : 766976
+            },
+            {
+                "name" : "compute_graph.Layer_169_wts_ddr",
+                "offset" : 847616
+            },
+            {
+                "name" : "compute_graph.Layer_176_wts_ddr",
+                "offset" : 901376
+            },
+            {
+                "name" : "compute_graph.Layer_177_wts_ddr",
+                "offset" : 1026816
+            },
+            {
+                "name" : "compute_graph.Layer_183_wts_ddr",
+                "offset" : 1147776
+            },
+            {
+                "name" : "compute_graph.Layer_184_wts_ddr",
+                "offset" : 1248000
+            },
+            {
+                "name" : "compute_graph.Layer_189_wts_ddr",
+                "offset" : 1328640
+            },
+            {
+                "name" : "compute_graph.Layer_196_wts_ddr",
+                "offset" : 1382400
+            },
+            {
+                "name" : "compute_graph.Layer_197_wts_ddr",
+                "offset" : 1507840
+            },
+            {
+                "name" : "compute_graph.Layer_203_wts_ddr",
+                "offset" : 1628800
+            },
+            {
+                "name" : "compute_graph.Layer_204_wts_ddr",
+                "offset" : 1729024
+            },
+            {
+                "name" : "compute_graph.Layer_211_wts_ddr",
+                "offset" : 1809664
+            },
+            {
+                "name" : "compute_graph.Layer_214_wts_ddr",
+                "offset" : 1872384
+            },
+            {
+                "name" : "compute_graph.Layer_218_wts_ddr",
+                "offset" : 1936384
+            },
+            {
+                "name" : "compute_graph.Layer_226_wts_ddr",
+                "offset" : 2012160
+            },
+            {
+                "name" : "compute_graph.Layer_237_wts_ddr",
+                "offset" : 2050048
+            },
+            {
+                "name" : "compute_graph.Layer_241_wts_ddr",
+                "offset" : 2154240
+            },
+            {
+                "name" : "compute_graph.Layer_249_wts_ddr",
+                "offset" : 2201600
+            },
+            {
+                "name" : "compute_graph.Layer_257_wts_ddr",
+                "offset" : 2225280
+            },
+            {
+                "name" : "compute_graph.Layer_261_wts_ddr",
+                "offset" : 2258432
+            },
+            {
+                "name" : "compute_graph.Layer_269_wts_ddr",
+                "offset" : 2272640
+            },
+            {
+                "name" : "compute_graph.Layer_276_wts_ddr",
+                "offset" : 2278720
+            },
+            {
+                "name" : "compute_graph.Layer_280_wts_ddr",
+                "offset" : 2288192
+            },
+            {
+                "name" : "compute_graph.Layer_288_wts_ddr",
+                "offset" : 2292928
+            },
+            {
+                "name" : "compute_graph.Layer_295_wts_ddr",
+                "offset" : 2297664
+            },
+            {
+                "name" : "compute_graph.Layer_296_wts_ddr",
+                "offset" : 2303744
+            },
+            {
+                "name" : "compute_graph.Layer_297_wts_ddr",
+                "offset" : 2306112
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr_5",
+                "offset" : 2307200
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr_4",
+                "offset" : 2537600
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr_3",
+                "offset" : 2768000
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr_2",
+                "offset" : 2775680
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr_1",
+                "offset" : 2794080
+            },
+            {
+                "name" : "compute_graph.const_ifm_ddr",
+                "offset" : 2837280
+            }
+        ]
+    },
+    "spills" : {
+        "layers" : [
+            {
+                "name" : "compute_graph.l2l3_1_spill",
+                "offset" : 0
+            },
+            {
+                "name" : "compute_graph.l2l3_2_spill",
+                "offset" : 117760
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_3_spill",
+                "offset" : 206080
+            },
+            {
+                "name" : "compute_graph.l2l3_3_spill",
+                "offset" : 441600
+            },
+            {
+                "name" : "compute_graph.l2l3_4_spill",
+                "offset" : 677120
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_5_spill",
+                "offset" : 912640
+            },
+            {
+                "name" : "compute_graph.l2l3_5_spill",
+                "offset" : 1143040
+            },
+            {
+                "name" : "compute_graph.l2l3_6_spill",
+                "offset" : 1373440
+            },
+            {
+                "name" : "compute_graph.l2l3_7_spill",
+                "offset" : 1603840
+            },
+            {
+                "name" : "compute_graph.l2l3_8_spill",
+                "offset" : 1834240
+            },
+            {
+                "name" : "compute_graph.l2l3_9_spill",
+                "offset" : 1949440
+            },
+            {
+                "name" : "compute_graph.l2l3_10_spill",
+                "offset" : 2064640
+            },
+            {
+                "name" : "compute_graph.l2l3_11_spill",
+                "offset" : 2179840
+            },
+            {
+                "name" : "compute_graph.l2l3_12_spill",
+                "offset" : 2295040
+            },
+            {
+                "name" : "compute_graph.l2l3_13_spill",
+                "offset" : 2410240
+            },
+            {
+                "name" : "compute_graph.l2l3_14_spill",
+                "offset" : 2525440
+            },
+            {
+                "name" : "compute_graph.l2l3_15_spill",
+                "offset" : 2640640
+            },
+            {
+                "name" : "compute_graph.l2l3_16_spill",
+                "offset" : 3101440
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_17_spill",
+                "offset" : 3224320
+            },
+            {
+                "name" : "compute_graph.l2l3_17_spill",
+                "offset" : 3339520
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_1818",
+                "offset" : 3454720
+            },
+            {
+                "name" : "compute_graph.l2l3_19_spill",
+                "offset" : 3497920
+            },
+            {
+                "name" : "compute_graph.l2l3_20_spill",
+                "offset" : 3627520
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_21_spill",
+                "offset" : 3760000
+            },
+            {
+                "name" : "compute_graph.l2l3_21_spill",
+                "offset" : 3889600
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_2424",
+                "offset" : 4019200
+            },
+            {
+                "name" : "compute_graph.l2l3_24_spill",
+                "offset" : 4052320
+            },
+            {
+                "name" : "compute_graph.l2l3_25_spill",
+                "offset" : 4085440
+            },
+            {
+                "name" : "compute_graph.l2l3_31_spill",
+                "offset" : 4118560
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_32_spill",
+                "offset" : 4118596
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_32_spill",
+                "offset" : 4151716
+            },
+            {
+                "name" : "compute_graph.l2l3_32_spill",
+                "offset" : 4184836
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_3434",
+                "offset" : 4217956
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_3636",
+                "offset" : 4236356
+            },
+            {
+                "name" : "compute_graph.l2l3_36_spill",
+                "offset" : 4291556
+            },
+            {
+                "name" : "compute_graph.l2l3_37_spill",
+                "offset" : 4346756
+            },
+            {
+                "name" : "compute_graph.l2l3_43_spill",
+                "offset" : 4401956
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_44_spill",
+                "offset" : 4402016
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_44_spill",
+                "offset" : 4457216
+            },
+            {
+                "name" : "compute_graph.l2l3_44_spill",
+                "offset" : 4512416
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_4646",
+                "offset" : 4567616
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_4848",
+                "offset" : 4586016
+            },
+            {
+                "name" : "compute_graph.l2l3_48_spill",
+                "offset" : 4641216
+            },
+            {
+                "name" : "compute_graph.l2l3_49_spill",
+                "offset" : 4696416
+            },
+            {
+                "name" : "compute_graph.l2l3_55_spill",
+                "offset" : 4751616
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_56_spill",
+                "offset" : 4751676
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_56_spill",
+                "offset" : 4806876
+            },
+            {
+                "name" : "compute_graph.l2l3_56_spill",
+                "offset" : 4862076
+            },
+            {
+                "name" : "compute_graph.l2l3_59_spill",
+                "offset" : 4917276
+            },
+            {
+                "name" : "compute_graph.l2l3_62_spill",
+                "offset" : 5027676
+            },
+            {
+                "name" : "compute_graph.l2l3_63_spill",
+                "offset" : 5138076
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_64_spill",
+                "offset" : 5253276
+            },
+            {
+                "name" : "compute_graph.l2l3_64_spill",
+                "offset" : 5363676
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_113113",
+                "offset" : 5474076
+            },
+            {
+                "name" : "compute_graph.l2l3_113_spill",
+                "offset" : 5531676
+            },
+            {
+                "name" : "compute_graph.l2l3_114_spill",
+                "offset" : 5589276
+            },
+            {
+                "name" : "compute_graph.l2l3_120_spill",
+                "offset" : 5646876
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_121_spill",
+                "offset" : 5647116
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_121_spill",
+                "offset" : 5704716
+            },
+            {
+                "name" : "compute_graph.l2l3_121_spill",
+                "offset" : 5762316
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_123123",
+                "offset" : 5819916
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_133133",
+                "offset" : 5833356
+            },
+            {
+                "name" : "compute_graph.l2l3_133_spill",
+                "offset" : 5913996
+            },
+            {
+                "name" : "compute_graph.l2l3_134_spill",
+                "offset" : 5994636
+            },
+            {
+                "name" : "compute_graph.l2l3_140_spill",
+                "offset" : 6075276
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_141_spill",
+                "offset" : 6075612
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_141_spill",
+                "offset" : 6156252
+            },
+            {
+                "name" : "compute_graph.l2l3_141_spill",
+                "offset" : 6236892
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_153153",
+                "offset" : 6317532
+            },
+            {
+                "name" : "compute_graph.l2l3_153_spill",
+                "offset" : 6398172
+            },
+            {
+                "name" : "compute_graph.l2l3_154_spill",
+                "offset" : 6478812
+            },
+            {
+                "name" : "compute_graph.l2l3_160_spill",
+                "offset" : 6559452
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_161_spill",
+                "offset" : 6559788
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_161_spill",
+                "offset" : 6640428
+            },
+            {
+                "name" : "compute_graph.l2l3_161_spill",
+                "offset" : 6721068
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_163163",
+                "offset" : 6801708
+            },
+            {
+                "name" : "compute_graph.l2l3_164_spill",
+                "offset" : 6820908
+            },
+            {
+                "name" : "compute_graph.l2l3_167_spill",
+                "offset" : 6936108
+            },
+            {
+                "name" : "compute_graph.l2l3_168_spill",
+                "offset" : 7051308
+            },
+            {
+                "name" : "compute_graph.l2l3_169_spill",
+                "offset" : 7166508
+            },
+            {
+                "name" : "compute_graph.l2l3_172_spill",
+                "offset" : 7281708
+            },
+            {
+                "name" : "compute_graph.l2l3_173_spill",
+                "offset" : 7396908
+            },
+            {
+                "name" : "compute_graph.l2l3_174_spill",
+                "offset" : 7512108
+            },
+            {
+                "name" : "compute_graph.l2l3_180_spill",
+                "offset" : 7627308
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_181_spill",
+                "offset" : 7627788
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_181_spill",
+                "offset" : 7742988
+            },
+            {
+                "name" : "compute_graph.l2l3_181_spill",
+                "offset" : 7858188
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_183183",
+                "offset" : 7973388
+            },
+            {
+                "name" : "compute_graph.l2l3_184_spill",
+                "offset" : 7992588
+            },
+            {
+                "name" : "compute_graph.l2l3_187_spill",
+                "offset" : 8107788
+            },
+            {
+                "name" : "compute_graph.l2l3_188_spill",
+                "offset" : 8222988
+            },
+            {
+                "name" : "compute_graph.l2l3_189_spill",
+                "offset" : 8338188
+            },
+            {
+                "name" : "compute_graph.l2l3_192_spill",
+                "offset" : 8453388
+            },
+            {
+                "name" : "compute_graph.l2l3_193_spill",
+                "offset" : 8568588
+            },
+            {
+                "name" : "compute_graph.l2l3_194_spill",
+                "offset" : 8683788
+            },
+            {
+                "name" : "compute_graph.l2l3_200_spill",
+                "offset" : 8798988
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_201_spill",
+                "offset" : 8799468
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_201_spill",
+                "offset" : 8914668
+            },
+            {
+                "name" : "compute_graph.l2l3_201_spill",
+                "offset" : 9029868
+            },
+            {
+                "name" : "compute_graph.l2l3_204_spill",
+                "offset" : 9145068
+            },
+            {
+                "name" : "compute_graph.l2l3_207_spill",
+                "offset" : 9260268
+            },
+            {
+                "name" : "compute_graph.l2l3_208_spill",
+                "offset" : 9375468
+            },
+            {
+                "name" : "compute_graph.l2l3_209_spill",
+                "offset" : 9490668
+            },
+            {
+                "name" : "compute_graph.l2l3_212_spill",
+                "offset" : 9605868
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_0_213_spill",
+                "offset" : 9605932
+            },
+            {
+                "name" : "compute_graph.l2l3_scratch_1_213_spill",
+                "offset" : 9621292
+            },
+            {
+                "name" : "compute_graph.l2l3_213_spill",
+                "offset" : 9636652
+            },
+            {
+                "name" : "compute_graph.l2l3_214_spill",
+                "offset" : 9652012
+            },
+            {
+                "name" : "compute_graph.l2l3_215_spill",
+                "offset" : 9667372
+            },
+            {
+                "name" : "compute_graph.l2l3_216_spill",
+                "offset" : 9675052
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_217",
+                "offset" : 9682732
+            },
+            {
+                "name" : "compute_graph.l2l3_219_spill",
+                "offset" : 9698092
+            },
+            {
+                "name" : "compute_graph.l2l3_220_spill",
+                "offset" : 9713452
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_222222",
+                "offset" : 9721132
+            },
+            {
+                "name" : "compute_graph.l2l3_223_spill",
+                "offset" : 9728812
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_225",
+                "offset" : 9736492
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_230",
+                "offset" : 9751852
+            },
+            {
+                "name" : "compute_graph.l2l3_231_spill",
+                "offset" : 9767212
+            },
+            {
+                "name" : "compute_graph.l2l3_232_spill",
+                "offset" : 9828652
+            },
+            {
+                "name" : "compute_graph.l2l3_233_spill",
+                "offset" : 9887532
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_236",
+                "offset" : 9945132
+            },
+            {
+                "name" : "compute_graph.l2l3_237_spill",
+                "offset" : 10026092
+            },
+            {
+                "name" : "compute_graph.l2l3_238_spill",
+                "offset" : 10062892
+            },
+            {
+                "name" : "compute_graph.l2l3_239_spill",
+                "offset" : 10081292
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_240",
+                "offset" : 10099692
+            },
+            {
+                "name" : "compute_graph.l2l3_242_spill",
+                "offset" : 10136492
+            },
+            {
+                "name" : "compute_graph.l2l3_243_spill",
+                "offset" : 10173292
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_245245",
+                "offset" : 10191692
+            },
+            {
+                "name" : "compute_graph.l2l3_246_spill",
+                "offset" : 10210092
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_248",
+                "offset" : 10228492
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_253",
+                "offset" : 10265292
+            },
+            {
+                "name" : "compute_graph.l2l3_254_spill",
+                "offset" : 10302092
+            },
+            {
+                "name" : "compute_graph.l2l3_255_spill",
+                "offset" : 10449292
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_256",
+                "offset" : 10593292
+            },
+            {
+                "name" : "compute_graph.l2l3_257_spill",
+                "offset" : 10794892
+            },
+            {
+                "name" : "compute_graph.l2l3_258_spill",
+                "offset" : 10866892
+            },
+            {
+                "name" : "compute_graph.l2l3_259_spill",
+                "offset" : 10910092
+            },
+            {
+                "name" : "compute_graph.l2l3_260_spill",
+                "offset" : 10953292
+            },
+            {
+                "name" : "compute_graph.l2l3_262_spill",
+                "offset" : 11025292
+            },
+            {
+                "name" : "compute_graph.l2l3_263_spill",
+                "offset" : 11097292
+            },
+            {
+                "name" : "compute_graph.L3_OFM_Buffer_layer_TGSpilling_265265",
+                "offset" : 11140492
+            },
+            {
+                "name" : "compute_graph.l2l3_266_spill",
+                "offset" : 11183692
+            },
+            {
+                "name" : "compute_graph.l2l3_267_spill",
+                "offset" : 11226892
+            },
+            {
+                "name" : "compute_graph.l2l3_268_spill",
+                "offset" : 11270092
+            },
+            {
+                "name" : "compute_graph.l2l3_273_spill",
+                "offset" : 11342092
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_275",
+                "offset" : 11414092
+            },
+            {
+                "name" : "compute_graph.l2l3_276_spill",
+                "offset" : 11874892
+            },
+            {
+                "name" : "compute_graph.l2l3_277_spill",
+                "offset" : 12105292
+            },
+            {
+                "name" : "compute_graph.l2l3_278_spill",
+                "offset" : 12220492
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_279",
+                "offset" : 12335692
+            },
+            {
+                "name" : "compute_graph.l2l3_280_spill",
+                "offset" : 12566092
+            },
+            {
+                "name" : "compute_graph.l2l3_281_spill",
+                "offset" : 12796492
+            },
+            {
+                "name" : "compute_graph.l2l3_282_spill",
+                "offset" : 13026892
+            },
+            {
+                "name" : "compute_graph.l2l3_283_spill",
+                "offset" : 13142092
+            },
+            {
+                "name" : "compute_graph.l2l3_284_spill",
+                "offset" : 13257292
+            },
+            {
+                "name" : "compute_graph.l2l3_285_spill",
+                "offset" : 13372492
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_287",
+                "offset" : 13487692
+            },
+            {
+                "name" : "compute_graph.l2l3_288_spill",
+                "offset" : 13718092
+            },
+            {
+                "name" : "compute_graph.l2l3_289_spill",
+                "offset" : 13833292
+            },
+            {
+                "name" : "compute_graph.l2l3_290_spill",
+                "offset" : 13948492
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_292",
+                "offset" : 14063692
+            },
+            {
+                "name" : "compute_graph.spill_L3_Concat_Buffer_layer_294",
+                "offset" : 14294092
+            },
+            {
+                "name" : "compute_graph.l2l3_295_spill",
+                "offset" : 15446092
+            },
+            {
+                "name" : "compute_graph.l2l3_296_spill",
+                "offset" : 15906892
+            },
+            {
+                "name" : "compute_graph.l2l3_297_spill",
+                "offset" : 16367692
+            },
+            {
+                "name" : "compute_graph.l2l3_298_spill",
+                "offset" : 16598092
+            },
+            {
+                "name" : "compute_graph.l2l3_300_spill",
+                "offset" : 16828492
+            },
+            {
+                "name" : "compute_graph.l2l3_301_spill",
+                "offset" : 17058892
+            }
+        ]
+    }
+}

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/ml_txn.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8c431abc3fb04c2333b756f029894d8440645eeb714fb234525160657d575e
+size 744144

segmentation_1_4_0_fp32_combined/vaiml_par_0/0/model_top.cpp

@@ -0,0 +1,6 @@
+#include "multi_layer_overlay.h"
+FlexMLGraph compute_graph;
+#if defined(__AIESIM__) || defined(__X86SIM__)
+#include "../aie_runtime_control.cpp"
+int main() { return 0; }
+#endif