Analysis report block based filtering for profiling

src/argparser.py

@@ -26,6 +26,7 @@
 import os
 import shutil
 from pathlib import Path
+import re
 
 
 def print_avail_arch(avail_arch: list):
@@ -114,7 +115,6 @@ def omniarg_parser(
         type=str,
         metavar="",
         dest="name",
-        required=True,
         help="\t\t\tAssign a name to workload.",
     )
     profile_group.add_argument("--target", type=str, default=None, help=argparse.SUPPRESS)
@@ -176,16 +176,49 @@ def omniarg_parser(
         required=False,
         help="\t\t\tDispatch ID filtering.",
     )
+    def validate_block(value):
+        # Metric id regex, for example, 10, 4, 4.3
+        metric_id_pattern = re.compile(r'^\d+$|^\d+\.\d+$')
+        hardware_block_pattern = re.compile(r'^(SQ|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF)$')
+        if metric_id_pattern.match(value):
+            return (str(value), "metric_id")
+        if hardware_block_pattern.match(value):
+            return (str(value), "hardware_block")
+        raise argparse.ArgumentTypeError(f"Invalid hardware block or metric id: {value}")
     profile_group.add_argument(
         "-b",
         "--block",
-        type=str,
-        dest="ipblocks",
+        type=validate_block,
+        dest="filter_blocks",
         metavar="",
         nargs="+",
         required=False,
-        choices=["SQ", "SQC", "TA", "TD", "TCP", "TCC", "SPI", "CPC", "CPF"],
-        help="\t\t\tHardware block filtering:\n\t\t\t   SQ\n\t\t\t   SQC\n\t\t\t   TA\n\t\t\t   TD\n\t\t\t   TCP\n\t\t\t   TCC\n\t\t\t   SPI\n\t\t\t   CPC\n\t\t\t   CPF",
+        default=[],
+        help="""\t\t\tSpecify metric id(s) from --list-metrics for filtering (e.g. 10, 4, 4.3).
+    \t\t\tCan provide multiple space separated arguments. Can also accept Hardware blocks.
+    \t\t\tHardware block filtering (will be deprecated in next release):
+    \t\t\t   SQ
+    \t\t\t   SQC
+    \t\t\t   TA
+    \t\t\t   TD
+    \t\t\t   TCP
+    \t\t\t   TCC
+    \t\t\t   SPI
+    \t\t\t   CPC
+    \t\t\t   CPF""",)
+    profile_group.add_argument(
+        "--list-metrics",
+        metavar="",
+        nargs="?",
+        const="",
+        help=print_avail_arch(supported_archs.keys()),
+    )
+    profile_group.add_argument(
+        "--config-dir",
+        dest="config_dir",
+        metavar="",
+        help="\t\tSpecify the directory of customized report section configs.",
+        default=rocprof_compute_home.joinpath("rocprof_compute_soc/analysis_configs/"),
     )
 
     result = shutil.which("rocscope")
@@ -486,7 +519,7 @@ def omniarg_parser(
         dest="filter_metrics",
         metavar="",
         nargs="+",
-        help="\t\tSpecify hardware block/metric id(s) from --list-metrics for filtering.",
+        help="\t\tSpecify metric id(s) from --list-metrics for filtering.",
     )
     analyze_group.add_argument(
         "--gpu-id",

src/rocprof_compute_analyze/analysis_base.py

@@ -45,6 +45,7 @@ def __init__(self, args, supported_archs):
         self.__args = args
         self._runs = OrderedDict()
         self._arch_configs = {}
+        self._profiling_config = dict()
         self.__supported_archs = supported_archs
         self._output = None
         self.__socs: dict = None  # available OmniSoC objs
@@ -254,6 +255,9 @@ def pre_processing(self):
             open(self.__args.output_file, "w+") if self.__args.output_file else sys.stdout
         )
 
+        # Read profiling config
+        self._profiling_config = file_io.load_profiling_config(self.__args.path[0][0])
+
         # initalize runs
         self._runs = self.initalize_runs()
 

src/rocprof_compute_analyze/analysis_cli.py

@@ -100,4 +100,5 @@ def run_analysis(self):
                     self._runs[self.get_args().path[0][0]].sys_info.iloc[0]["gpu_arch"]
                 ],
                 self._output,
+                self._profiling_config,
             )

src/rocprof_compute_base.py

@@ -33,6 +33,7 @@
 from pathlib import Path
 
 import pandas as pd
+import yaml
 
 import config
 from argparser import omniarg_parser
@@ -250,25 +251,25 @@ def run_profiler(self):
             from rocprof_compute_profile.profiler_rocprof_v1 import rocprof_v1_profiler
 
             profiler = rocprof_v1_profiler(
-                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch]
+                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch], self.__supported_archs
             )
         elif self.__profiler_mode == "rocprofv2":
             from rocprof_compute_profile.profiler_rocprof_v2 import rocprof_v2_profiler
 
             profiler = rocprof_v2_profiler(
-                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch]
+                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch], self.__supported_archs
             )
         elif self.__profiler_mode == "rocprofv3":
             from rocprof_compute_profile.profiler_rocprof_v3 import rocprof_v3_profiler
 
             profiler = rocprof_v3_profiler(
-                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch]
+                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch], self.__supported_archs
             )
         elif self.__profiler_mode == "rocscope":
             from rocprof_compute_profile.profiler_rocscope import rocscope_profiler
 
             profiler = rocscope_profiler(
-                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch]
+                self.__args, self.__profiler_mode, self.__soc[self.__mspec.gpu_arch], self.__supported_archs
             )
         else:
             console_error("Unsupported profiler")
@@ -278,6 +279,11 @@ def run_profiler(self):
         # -----------------------
 
         self.__soc[self.__mspec.gpu_arch].profiling_setup()
+        # Write profiling configuration as yaml file
+        with open(Path(self.__args.path).joinpath("profiling_config.yaml"), "w") as f:
+            args_dict = vars(self.__args)
+            args_dict["config_dir"] = str(args_dict["config_dir"])
+            yaml.dump(args_dict, f)
         # enable file-based logging
         setup_file_handler(self.__args.loglevel, self.__args.path)
 

src/rocprof_compute_profile/profiler_base.py

@@ -36,6 +36,7 @@
 from tqdm import tqdm
 
 import config
+from utils import file_io, parser, schema
 from utils.utils import (
     capture_subprocess_output,
     console_debug,
@@ -51,15 +52,18 @@
 
 
 class RocProfCompute_Base:
-    def __init__(self, args, profiler_mode, soc):
+    def __init__(self, args, profiler_mode, soc, supported_archs):
         self.__args = args
         self.__profiler = profiler_mode
+        self.__supported_archs = supported_archs
         self._soc = soc  # OmniSoC obj
         self.__perfmon_dir = str(
             Path(str(config.rocprof_compute_home)).joinpath(
                 "rocprof_compute_soc", "profile_configs"
             )
         )
+        self.__filter_hardware_blocks = [block[0] for block in args.filter_blocks if block[1] == "hardware_block"]
+        self.__filter_metric_ids = [block[0] for block in args.filter_blocks if block[1] == "metric_id"]
 
     def get_args(self):
         return self.__args
@@ -260,6 +264,27 @@ def join_prof(self, out=None):
         else:
             return df
 
+    @demarcate
+    def list_metrics(self):
+        args = self.__args
+        if args.list_metrics in self.__supported_archs.keys():
+            ac = schema.ArchConfig()
+            ac.panel_configs = file_io.top_stats_build_in_config
+            sys_info = self._soc._mspec.get_class_members().iloc[0],
+            parser.build_dfs(archConfigs=ac, filter_metrics=[], sys_info=sys_info)
+            for key, value in ac[args.list_metrics].metric_list.items():
+                prefix = ""
+                if "." not in str(key):
+                    prefix = ""
+                elif str(key).count(".") == 1:
+                    prefix = "\t"
+                else:
+                    prefix = "\t\t"
+                print(prefix + key, "->", value)
+            sys.exit(0)
+        else:
+            console_error("Unsupported arch")
+
     # ----------------------------------------------------
     # Required methods to be implemented by child classes
     # ----------------------------------------------------
@@ -268,6 +293,15 @@ def pre_processing(self):
         """Perform any pre-processing steps prior to profiling."""
         console_debug("profiling", "pre-processing using %s profiler" % self.__profiler)
 
+        if self.__args.list_metrics is not None:
+            if not self.__args.list_metrics:
+                arch = self._soc.__arch
+            else:
+                arch = self.__args.list_metrics
+            self.list_metrics(arch)
+        elif self.__args.name is None:
+            sys.exit("Either --list-name or --name is required")
+
         # verify soc compatibility
         if self.__profiler not in self._soc.get_compatible_profilers():
             console_error(
@@ -320,10 +354,14 @@ def run_profiling(self, version: str, prog: str):
         console_log("Command: " + str(self.__args.remaining))
         console_log("Kernel Selection: " + str(self.__args.kernel))
         console_log("Dispatch Selection: " + str(self.__args.dispatch))
-        if self.__args.ipblocks == None:
+        if self.__filter_hardware_blocks == None:
             console_log("Hardware Blocks: All")
         else:
-            console_log("Hardware Blocks: " + str(self.__args.ipblocks))
+            console_log("Hardware Blocks: " + str(self.__filter_hardware_blocks))
+        if self.__filter_metric_ids == None:
+            console_log("Report Sections: All")
+        else:
+            console_log("Report Sections: " + str(self.__filter_metric_ids))
 
         msg = "Collecting Performance Counters"
         (
@@ -424,7 +462,7 @@ def post_processing(self):
         gen_sysinfo(
             workload_name=self.__args.name,
             workload_dir=self.get_args().path,
-            ip_blocks=self.__args.ipblocks,
+            ip_blocks=[block[0] for block in self.__args.filter_blocks if block[1] == "hardware_block"],
             app_cmd=self.__args.remaining,
             skip_roof=self.__args.no_roof,
             roof_only=self.__args.roof_only,

src/rocprof_compute_profile/profiler_rocprof_v1.py

@@ -30,8 +30,8 @@
 
 
 class rocprof_v1_profiler(RocProfCompute_Base):
-    def __init__(self, profiling_args, profiler_mode, soc):
-        super().__init__(profiling_args, profiler_mode, soc)
+    def __init__(self, profiling_args, profiler_mode, soc, supported_archs):
+        super().__init__(profiling_args, profiler_mode, soc, supported_archs)
         self.ready_to_profile = (
             self.get_args().roof_only
             and not Path(self.get_args().path).joinpath("pmc_perf.csv").is_file()

src/rocprof_compute_profile/profiler_rocprof_v2.py

@@ -31,8 +31,8 @@
 
 
 class rocprof_v2_profiler(RocProfCompute_Base):
-    def __init__(self, profiling_args, profiler_mode, soc):
-        super().__init__(profiling_args, profiler_mode, soc)
+    def __init__(self, profiling_args, profiler_mode, soc, supported_archs):
+        super().__init__(profiling_args, profiler_mode, soc, supported_archs)
         self.ready_to_profile = (
             self.get_args().roof_only
             and not Path(self.get_args().path).joinpath("pmc_perf.csv").is_file()

src/rocprof_compute_profile/profiler_rocprof_v3.py

@@ -32,8 +32,8 @@
 
 
 class rocprof_v3_profiler(RocProfCompute_Base):
-    def __init__(self, profiling_args, profiler_mode, soc):
-        super().__init__(profiling_args, profiler_mode, soc)
+    def __init__(self, profiling_args, profiler_mode, soc, supported_archs):
+        super().__init__(profiling_args, profiler_mode, soc, supported_archs)
         self.ready_to_profile = (
             self.get_args().roof_only
             and not Path(self.get_args().path).joinpath("pmc_perf.csv").is_file()

src/rocprof_compute_profile/profiler_rocscope.py

@@ -27,8 +27,8 @@
 
 
 class rocscope_profiler(RocProfCompute_Base):
-    def __init__(self, profiling_args, profiler_mode, soc):
-        super().__init__(profiling_args, profiler_mode, soc)
+    def __init__(self, profiling_args, profiler_mode, soc, supported_archs):
+        super().__init__(profiling_args, profiler_mode, soc, supported_archs)
 
     # -----------------------
     # Required child methods