Analysis report block based filtering for profiling (#566)

* Analysis report block based filtering for profiling

* Profiling mode changes

- `-b` option now additionally accepts metric id(s), similar to `-b` option in analyze mode (e.g. 6, 6.2, 6.23)
    - Only counters mentioned in the selected analysis report blocks will be collected
        - Add parsing logic to identify hardware counters from analysis report blocks
        - Add filtering logic to only write filtered counters in perfmon files
        - Log not collected counters in one line
- `--list-metrics` option added in profile mode to list possible metric id(s) similar to analyze mode
- Write arguments provided during profiling in profiling_configuration.yaml file

* Analysis mode changes

- During analysis mode, only show report blocks selected during profiling
    - If `-b` option is provided in analysis mode, then follow provided filters
- Do not show empty tables in analysis report

* Miscellaneous changes

- Update CHANGELOG
- Add test cases
    - Instruction mix report block filter
    - Instruction mix and Memory chart report block filter
    - Instruction mix report block filter and CPC hardware block filter
    - TA hardware block filter
    - --list-metrics in profile mode should work
- Move binary handler fixtures to conftest.py to avoid importing
  fixtures
- cmake file in tests directory has been updated to compile sample/vmem.hip for testing

* Public documentation changes

- Use the term "Hardware report block" instead of "Hardware block"
- Add documentation for "--list-metrics" option in profile mode
- Add example of filtering by hardware report block such as instruction
  mix and wavefront launch statistics
- Add deprecation warning for hardware component (sq, tcc) based filtering

src/utils/file_io.py

@@ -36,7 +36,7 @@ import yaml
 import config
 from utils import schema
 from utils.kernel_name_shortener import kernel_name_shortener
-from utils.utils import console_debug, console_error, demarcate
+from utils.utils import console_debug, console_error, console_log, demarcate
 
 # TODO: use pandas chunksize or dask to read really large csv file
 # from dask import dataframe as dd
@@ -85,6 +85,21 @@ def load_panel_configs(dir):
     return od
 
 
+def load_profiling_config(config_dir):
+    """
+    Load profiling config from yaml file.
+    """
+    try:
+        with open(Path(config_dir).joinpath("profiling_config.yaml")) as file:
+            prof_config = yaml.safe_load(file)
+            return prof_config
+    except FileNotFoundError:
+        console_log(
+            f"Could not find profiling_config.yaml in {config_dir} for filtering analysis report"
+        )
+    return dict()
+
+
 @demarcate
 def create_df_kernel_top_stats(
     df_in,

src/utils/parser.py

@@ -492,7 +492,9 @@ def build_dfs(archConfigs, filter_metrics, sys_info):
                 if type == "metric_table":
                     headers = ["Metric_ID"]
                     data_source_idx = str(data_config["id"] // 100)
-                    if data_source_idx != 0 or data_source_idx in filter_metrics:
+                    if data_source_idx != 0 or (
+                        filter_metrics and data_source_idx in filter_metrics
+                    ):
                         metric_list[data_source_idx] = panel["title"]
                     if (
                         "cli_style" in data_config

src/utils/tty.py

@@ -29,7 +29,7 @@ import pandas as pd
 from tabulate import tabulate
 
 from utils import parser
-from utils.utils import console_log, console_warning
+from utils.utils import console_log, console_warning, convert_metric_id_to_panel_idx
 
 hidden_columns = ["Tips", "coll_level"]
 hidden_sections = [1900, 2000]
@@ -60,11 +60,20 @@ def get_table_string(df, transpose=False, decimal=2):
     )
 
 
-def show_all(args, runs, archConfigs, output):
+def show_all(args, runs, archConfigs, output, profiling_config):
     """
     Show all panels with their data in plain text mode.
     """
     comparable_columns = parser.build_comparable_columns(args.time_unit)
+    filter_panel_ids = [
+        convert_metric_id_to_panel_idx(section)
+        for section in [
+            name
+            for name, type in profiling_config.get("filter_blocks", {}).items()
+            if type == "metric_id"
+        ]
+    ]
+    comparable_columns = parser.build_comparable_columns(args.time_unit)
 
     for panel_id, panel in archConfigs.panel_configs.items():
         # Skip panels that don't support baseline comparison
@@ -74,6 +83,27 @@ def show_all(args, runs, archConfigs, output):
 
         for data_source in panel["data source"]:
             for type, table_config in data_source.items():
+                # If block filtering was used during analysis, then dont use profiling config
+                # If block filtering was used in profiling config, only show those panels
+                # If block filtering not used in profiling config, show all panels
+                # Skip this table if table id or panel id is not present in block filters
+                # However, always show panel id <= 100
+                if (
+                    not args.filter_metrics
+                    and filter_panel_ids
+                    and table_config["id"] not in filter_panel_ids
+                    and panel_id not in filter_panel_ids
+                    and panel_id > 100
+                ):
+                    table_id_str = (
+                        str(table_config["id"] // 100)
+                        + "."
+                        + str(table_config["id"] % 100)
+                    )
+                    console_log(
+                        f"Not showing table not selected during profiling: {table_id_str} {table_config['title']}"
+                    )
+                    continue
                 # take the 1st run as baseline
                 base_run, base_data = next(iter(runs.items()))
                 base_df = base_data.dfs[table_config["id"]]
@@ -207,7 +237,25 @@ def show_all(args, runs, archConfigs, output):
                         + str(table_config["id"] % 100)
                     )
 
-                    if "title" in table_config and table_config["title"]:
+                    # Check if any column in df is empty
+                    is_empty_columns_exist = any(
+                        [
+                            df.columns[col_idx]
+                            for col_idx in range(len(df.columns))
+                            if df.replace("", None).iloc[:, col_idx].isnull().all()
+                        ]
+                    )
+                    # Do not print the table if any column is empty
+                    if is_empty_columns_exist:
+                        console_log(
+                            f"Not showing table with empty column(s): {table_id_str} {table_config['title']}"
+                        )
+
+                    if (
+                        "title" in table_config
+                        and table_config["title"]
+                        and not is_empty_columns_exist
+                    ):
                         ss += table_id_str + " " + table_config["title"] + "\n"
 
                     if args.df_file_dir:
@@ -238,10 +286,13 @@ def show_all(args, runs, archConfigs, output):
                         and "columnwise" in table_config
                         and table_config["columnwise"] == True
                     )
-                    ss += (
-                        get_table_string(df, transpose=transpose, decimal=args.decimal)
-                        + "\n"
-                    )
+                    if not is_empty_columns_exist:
+                        ss += (
+                            get_table_string(
+                                df, transpose=transpose, decimal=args.decimal
+                            )
+                            + "\n"
+                        )
 
         if ss:
             print("\n" + "-" * 80, file=output)

src/utils/utils.py

@@ -191,7 +191,7 @@ def capture_subprocess_output(subprocess_args, new_env=None, profileMode=False):
     global rocprof_args
     # Format command for debug messages, formatting for rocprofv1 and rocprofv2
     command = " ".join(rocprof_args)
-    console_debug("subprocess", "Running: " + command)
+    console_debug("subprocess", "Running: " + command + " " + " ".join(subprocess_args))
     # Start subprocess
     # bufsize = 1 means output is line buffered
     # universal_newlines = True is required for line buffering
@@ -820,7 +820,7 @@ def gen_sysinfo(
     df["workload_name"] = workload_name
 
     blocks = []
-    if ip_blocks == None:
+    if not ip_blocks:
         t = ["SQ", "LDS", "SQC", "TA", "TD", "TCP", "TCC", "SPI", "CPC", "CPF"]
         blocks += t
     else:
@@ -1249,3 +1249,16 @@ def merge_counters_spatial_multiplex(df_multi_index):
 
     final_df = pd.concat(result_dfs, keys=coll_levels, axis=1, copy=False)
     return final_df
+
+
+def convert_metric_id_to_panel_idx(metric_id):
+    # "4.02" -> 402
+    # "4.23" -> 423
+    # "4" -> 400
+    tokens = metric_id.split(".")
+    if len(tokens) == 1:
+        return int(tokens[0]) * 100
+    elif len(tokens) == 2:
+        return int(tokens[0]) * 100 + int(tokens[1])
+    else:
+        raise Exception(f"Invalid metric id: {metric_id}")