diff --git a/profiler/cluster_analyse/analysis/communication_analysis.py b/profiler/cluster_analyse/analysis/communication_analysis.py index 1d03687298659c62823e143cf65d6455c2ca13ed..a7b27913443f0fdb15d59811bd0aedffbbf01a3a 100644 --- a/profiler/cluster_analyse/analysis/communication_analysis.py +++ b/profiler/cluster_analyse/analysis/communication_analysis.py @@ -31,7 +31,7 @@ class BaseCommAnalysis: @staticmethod def compute_ratio(dividend: float, divisor: float): - if abs(divisor) < 1e-15: + if abs(divisor) < Constant.EPS: return 0 else: return round(dividend / divisor, 4) diff --git a/profiler/cluster_analyse/cluster_analysis.py b/profiler/cluster_analyse/cluster_analysis.py index 3491808524f7d3a4322176b0e6071c4463c5741a..57c65678ab798b7dc478b744775fc803be25eb79 100644 --- a/profiler/cluster_analyse/cluster_analysis.py +++ b/profiler/cluster_analyse/cluster_analysis.py @@ -42,7 +42,6 @@ class Interface: CommunicationGroupGenerator(self.collection_path, data_map).generate() except RuntimeError: print("Can not get communication info from ranks") - finally: communication_group = {} communication_ops = [] collective_group_dict = {} diff --git a/profiler/cluster_analyse/cluster_data_preprocess/pytorch_data_preprocessor.py b/profiler/cluster_analyse/cluster_data_preprocess/pytorch_data_preprocessor.py index 8df922ea19ba9f185a59544d7000dbd07161a8cb..18fd6a23b74830fc3b2bcc69b6c2ad61413f0d0f 100644 --- a/profiler/cluster_analyse/cluster_data_preprocess/pytorch_data_preprocessor.py +++ b/profiler/cluster_analyse/cluster_data_preprocess/pytorch_data_preprocessor.py @@ -14,8 +14,9 @@ # limitations under the License. from collections import defaultdict -from common_func.file_manager import FileManager import os +from common_func.file_manager import FileManager +from common_func.path_manager import PathManager class PytorchDataPreprocessor: @@ -23,7 +24,7 @@ class PytorchDataPreprocessor: PROFILER_INFO_EXTENSION = '.json' def __init__(self, path: str): - self.path = os.path.realpath(path) + self.path = PathManager.get_realpath(path) def get_data_map(self) -> dict: ascend_pt_dirs = [] @@ -40,14 +41,22 @@ class PytorchDataPreprocessor: rank_id_map[rank_id].append(dir_name) ret_dict = dict() - for (rank_id, dir_list) in rank_id_map.items(): - dir_list.sort(key=lambda x: x.split('_')[-3]) - ret_dict[rank_id] = os.path.join(self.path, dir_list[0]) + try: + for (rank_id, dir_list) in rank_id_map.items(): + dir_list.sort(key=lambda x: x.split('_')[-3]) + ret_dict[rank_id] = os.path.join(self.path, dir_list[0]) + except Exception as e: + raise RuntimeError("Found invalid directory name!") from e return ret_dict def get_rank_id(self, dir_name: str) -> int: files = os.listdir(dir_name) for file_name in files: if file_name.startswith(self.PROFILER_INFO_HEAD) and file_name.endswith(self.PROFILER_INFO_EXTENSION): - return int(file_name[len(self.PROFILER_INFO_HEAD): -1 * len(self.PROFILER_INFO_EXTENSION)]) + rank_id_str = file_name[len(self.PROFILER_INFO_HEAD): -1 * len(self.PROFILER_INFO_EXTENSION)] + try: + rank_id = int(rank_id_str) + except ValueError: + rank_id = -1 + return rank_id return -1 diff --git a/profiler/cluster_analyse/cluster_kernels_analysis/cluster_prof_Info_analysis.py b/profiler/cluster_analyse/cluster_kernels_analysis/cluster_prof_Info_analysis.py index 88ff0dd3fc79ffa3044ee3919b217a05f0e93695..d761a2f60541fa45bf09d664bf8dfe67e622e933 100644 --- a/profiler/cluster_analyse/cluster_kernels_analysis/cluster_prof_Info_analysis.py +++ b/profiler/cluster_analyse/cluster_kernels_analysis/cluster_prof_Info_analysis.py @@ -14,16 +14,23 @@ # limitations under the License. from pathlib import Path - -import pandas as pd +import sys import argparse import re +import os +import stat +import shutil +import warnings import plotly.graph_objects as go from plotly.subplots import make_subplots from plotly.offline import plot -import os +import pandas as pd -import warnings +sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from common_func.path_manager import PathManager + +MAX_READ_FILE_BYTES = 64 * 1024 * 1024 class FormDataProcessor: @@ -33,7 +40,9 @@ class FormDataProcessor: def get_files_with_prefix_recursive(self, csv_path, match_str): matched_ir_files = list(Path(csv_path).rglob(match_str)) - assert len(matched_ir_files) > 0, f"Didn't find any file in folder {csv_path} that matches {match_str}" + if not matched_ir_files: + msg = f"Didn't find any file in folder {csv_path} that matches {match_str}" + raise RuntimeError(msg) return [str(item) for item in matched_ir_files] def readSummaryData(self, columns_to_keep): @@ -42,6 +51,8 @@ class FormDataProcessor: for f in self.files: if "mindstudio_profiler_output" in f: continue + # 判断csv文件大小 + PathManager.check_path_readable(f) # 读取CSV文件 df = pd.read_csv(f) # 保留需要的列 @@ -51,13 +62,19 @@ class FormDataProcessor: print(f"{f}文件没有所需的列，请确认profiling数据的正确性:\n,以下列可能不存在{columns_to_keep}\n") continue # 从文件名提取设备ID + try: + df['device_id'] = self.getDeviceId(f) + except Exception: + print(f"文件 \"{f}\" 的路径或者是文件夹名没有按照要求，请确保存在[device_]这一级文件夹,具体操作指导见readme\n") + continue # 添加新列 "device_id" - df['device_id'] = self.getDeviceId(f) - df['node_id'] = self.getNodeId(f) - + try: + df['node_id'] = self.getNodeId(f) + except Exception: + print(f"文件 \"{f}\" 的路径或者是文件夹名没有按照要求，请确保存在[node*]这一级文件夹,具体操作指导见readme\n") + continue # 将数据添加到最终的数据框中 - - all_data = all_data.append(df, ignore_index=True) + all_data = all_data._append(df, ignore_index=True) return all_data def getChipType(self): @@ -129,8 +146,6 @@ class ViewInfoManager: class OpSummaryAnalyzerBase: def __init__(self, chip_type, analyzer_type, dir_path): self.chip_type = chip_type - self.result_dir = f"{dir_path}/result" - os.makedirs(self.result_dir, exist_ok=True) # 文件路径不存在则创建 view_info = ViewInfoManager(chip_type).getColumnsInfo(analyzer_type) self.columns_to_view = view_info['columns_to_view'] self.calculate_fun = view_info['calculate_fun'] @@ -139,6 +154,13 @@ class OpSummaryAnalyzerBase: if 'extend_attr_to_group' in view_info: extend_attr_to_group = view_info['extend_attr_to_group'] self.attrs_to_group.extend(extend_attr_to_group) + # 创建结果文件 + self.result_dir = os.path.join(dir_path, "result") + PathManager.check_path_length(self.result_dir) + if os.path.exists(self.result_dir): + shutil.rmtree(self.result_dir, onerror=self.on_rm_error) + PathManager.check_path_writeable(dir_path) + PathManager.make_dir_safety(self.result_dir) def getColumnsToGroup(self): return self.columns_to_group @@ -152,6 +174,13 @@ class OpSummaryAnalyzerBase: view_data = summary_data.groupby(self.attrs_to_group).agg(calculate_dict).reset_index() return view_data + def on_rm_error(self, func, path, exc_info): + # path contains the path of the file that couldn't be removed + # let's just assume that it's read-only and unlink it. + os.chmod(path, stat.S_IWRITE) + os.unlink(path) + + class TimeToCsvAnalyzer(OpSummaryAnalyzerBase): def __init__(self, chip_type, dir_path): super().__init__(chip_type, "TimeToCsvAnalyzer", dir_path) @@ -160,9 +189,16 @@ class TimeToCsvAnalyzer(OpSummaryAnalyzerBase): view_data = self.calculateViewData(summary_data) # 规范化列名 view_data.columns = [''.join(col) if col[1] == "" else '_'.join(col) for col in view_data.columns] - for column in self.columns_to_view: - view_data[column + '_range'] = view_data[column + '_max'] - view_data[column + '_min'] - view_data.to_csv(self.result_dir + "/cluster_duration_time_analysis.csv", index=False) + try: + for column in self.columns_to_view: + view_data[column + '_range'] = view_data[column + '_max'] - view_data[column + '_min'] + except Exception as e: + raise RuntimeError("Invalid view data!") from e + save_path = os.path.join(self.result_dir, "cluster_duration_time_analysis.csv") + PathManager.check_path_length(save_path) + view_data.to_csv(save_path, index=False) + # 该文件权限设置为只读权限，不允许修改 + os.chmod(save_path, stat.S_IROTH) return view_data @@ -210,7 +246,11 @@ class StatisticalInfoToHtmlAnalyzer(OpSummaryAnalyzerBase): height=int(500 * row_num), width=int(rank_num * 100 * col_num), title_text="Op Performance Comparison") - plot(fig, filename=self.result_dir + "/" + column + "_Info.html") + save_plot_path = os.path.join(self.result_dir, column + "_Info.html") + PathManager.check_path_length(save_plot_path) + plot(fig, filename=save_plot_path) + # 该文件权限设置为只读权限，不允许修改 + os.chmod(save_plot_path, stat.S_IROTH) def getCalNum(self, rank_num): # 计算每行应该画多少个子图 @@ -230,18 +270,28 @@ class DeliverableGenerator: def run(self): summary_data = self.formProcess.readSummaryData(self.columns_to_keep) + # 判断summarydata 数据是否为空，如果是空， 说明所有csv读取数据都失败了 + if summary_data.empty: + print("没有符合要求的csv表格数据，请排查您的PROFILING数据") + return rank_num = self.formProcess.getRankNum() for analyzer in self.analyzers: analyzer.GenerateDeliverable(summary_data, rank_num) def setAnalyzers(self, args): chip_type = self.formProcess.getChipType() + # 判断该路径是不是软链接，并修改为绝对路径 + if os.path.islink(args.dir): + print(f"The file: \"{args.dir}\" is link. Please check the path.") + return + prof_path = os.path.realpath(args.dir) + PathManager.input_path_common_check(prof_path) if args.type == "all": - self.analyzers = [TimeToCsvAnalyzer(chip_type, args.dir), StatisticalInfoToHtmlAnalyzer(chip_type, args.top_n, args.dir)] + self.analyzers = [TimeToCsvAnalyzer(chip_type, prof_path), StatisticalInfoToHtmlAnalyzer(chip_type, args.top_n, prof_path)] elif args.type == "html": - self.analyzers = [StatisticalInfoToHtmlAnalyzer(chip_type, args.top_n, args.dir)] + self.analyzers = [StatisticalInfoToHtmlAnalyzer(chip_type, args.top_n, prof_path)] elif args.type == "csv": - self.analyzers = [TimeToCsvAnalyzer(chip_type, args.dir)] + self.analyzers = [TimeToCsvAnalyzer(chip_type, prof_path)] else: warnings.warn("参数错误，请输入 all html csv 这三种类型") # 发出一个警告信息 @@ -255,15 +305,15 @@ class DeliverableGenerator: def main(): - # 解析命令行参数 - parser = argparse.ArgumentParser() - parser.add_argument("--dir", "-d", default=None, help="root dir of PROF_* data") - parser.add_argument("--top_n", "-n", default=10, help="how many operators to show", type=int) - parser.add_argument("--type", "-t", default='html', help="compare ratio or aicore-time", type=str) - args = parser.parse_args() - - deviverable_gen = DeliverableGenerator(args) - deviverable_gen.run() + # 解析命令行参数 + parser = argparse.ArgumentParser() + parser.add_argument("--dir", "-d", default=None, help="root dir of PROF_* data") + parser.add_argument("--top_n", "-n", default=10, help="how many operators to show", type=int) + parser.add_argument("--type", "-t", default='html', help="compare ratio or aicore-time", type=str) + args = parser.parse_args() + + deviverable_gen = DeliverableGenerator(args) + deviverable_gen.run() if __name__ == "__main__": main() diff --git a/profiler/cluster_analyse/common_func/constant.py b/profiler/cluster_analyse/common_func/constant.py index 8910099c7f845219fb9ec12e0dd1e916d007b2a1..091007cf56be2dc0b96f0ef4a620ce604e861600 100644 --- a/profiler/cluster_analyse/common_func/constant.py +++ b/profiler/cluster_analyse/common_func/constant.py @@ -66,3 +66,10 @@ class Constant(object): # step time RANK = 'rank' STAGE = 'stage' + + # epsilon + EPS = 1e-15 + + # file suffix + JSON_SUFFIX = ".json" + CSV_SUFFIX = ".csv" diff --git a/profiler/cluster_analyse/common_func/file_manager.py b/profiler/cluster_analyse/common_func/file_manager.py index 063332acc0942bfe60314cb6e646bb89ff3e00fe..e4e0416600c5244be7d460fdd5d08a9ee3e47dba 100644 --- a/profiler/cluster_analyse/common_func/file_manager.py +++ b/profiler/cluster_analyse/common_func/file_manager.py @@ -22,19 +22,18 @@ from common_func.path_manager import PathManager class FileManager: + DATA_FILE_AUTHORITY = 0o640 + DATA_DIR_AUTHORITY = 0o750 @classmethod def read_csv_file(cls, file_path: str, class_bean: any) -> list: PathManager.check_path_readable(file_path) + base_name = os.path.basename(file_path) file_size = os.path.getsize(file_path) if file_size <= 0: return [] if file_size > Constant.MAX_CSV_SIZE: - check_msg = input( - f"The file({file_path}) size exceeds the preset max value, do you continue reading the file? [y/n]") - if check_msg.lower() != "y": - print(f"[WARNING] The user choose not to read the file: {file_path}") - return [] + raise RuntimeError(f"The file({base_name}) size exceeds the preset max value.") result_data = [] try: with open(file_path, newline="") as csv_file: @@ -42,44 +41,45 @@ class FileManager: for row in reader: result_data.append(class_bean(row)) except Exception: - raise RuntimeError(f"Failed to read the file: {file_path}") + raise RuntimeError(f"Failed to read the file: {base_name}") return result_data @classmethod def read_json_file(cls, file_path: str) -> dict: PathManager.check_path_readable(file_path) + base_name = os.path.basename(file_path) file_size = os.path.getsize(file_path) if file_size <= 0: return {} if file_size > Constant.MAX_JSON_SIZE: - check_msg = input( - f"The file({file_path}) size exceeds the preset max value, do you continue reading the file? [y/n]") - if check_msg.lower() != "y": - print(f"[WARNING] The user choose not to read the file: {file_path}") - return [] + raise RuntimeError(f"The file({base_name}) size exceeds the preset max value.") try: with open(file_path, "r") as json_file: result_data = json.load(json_file) except Exception: - raise RuntimeError(f"Failed to read the file: {file_path}") + raise RuntimeError(f"Failed to read the file: {base_name}") return result_data @classmethod def create_csv_file(cls, profiler_path: str, data: list, file_name: str, headers: list = None) -> None: if not data: return - output_path = os.path.join(profiler_path, Constant.CLUSTER_ANALYSIS_OUTPUT) + output_path = os.path.join( + profiler_path, Constant.CLUSTER_ANALYSIS_OUTPUT) output_file = os.path.join(output_path, file_name) - PathManager.create_file_safety(output_file) - PathManager.check_path_writeable(output_file) + base_name = os.path.basename(output_file) + PathManager.check_path_writeable(output_path) try: - with open(output_file, "w", newline="") as file: + with os.fdopen( + os.open(output_file, os.O_WRONLY | os.O_CREAT, cls.DATA_FILE_AUTHORITY), + 'w', newline="" + ) as file: writer = csv.writer(file) if headers: writer.writerow(headers) writer.writerows(data) except Exception: - raise RuntimeError(f"Can't create file: {output_file}") + raise RuntimeError(f"Can't create file: {base_name}") @classmethod def create_json_file(cls, profiler_path: str, data: dict, file_name: str) -> None: @@ -87,16 +87,31 @@ class FileManager: return output_path = os.path.join(profiler_path, Constant.CLUSTER_ANALYSIS_OUTPUT) output_file = os.path.join(output_path, file_name) - PathManager.create_file_safety(output_file) - PathManager.check_path_writeable(output_file) + base_name = os.path.basename(output_file) + PathManager.check_path_writeable(output_path) try: - with open(output_file, "w") as file: + with os.fdopen( + os.open(output_file, os.O_WRONLY | os.O_CREAT, cls.DATA_FILE_AUTHORITY), 'w' + ) as file: json.dump(data, file) except Exception: - raise RuntimeError(f"Can't create the file: {output_file}") + raise RuntimeError(f"Can't create the file: {base_name}") @classmethod def create_output_dir(cls, collection_path: str) -> None: - output_path = os.path.join(collection_path, Constant.CLUSTER_ANALYSIS_OUTPUT) + output_path = os.path.join( + collection_path, Constant.CLUSTER_ANALYSIS_OUTPUT) PathManager.remove_path_safety(output_path) PathManager.make_dir_safety(output_path) + + @classmethod + def check_file_size(cls, file_path): + suffix = os.path.splitext(file_path) + base_name = os.path.join(file_path) + if suffix == Constant.CSV_SUFFIX: + limit_size = Constant.MAX_JSON_SIZE + else: + limit_size = Constant.MAX_CSV_SIZE + file_size = os.path.getsize(file_path) + if file_size > limit_size: + raise RuntimeError(f"The file({base_name}) size exceeds the preset max value.") diff --git a/profiler/cluster_analyse/common_func/path_manager.py b/profiler/cluster_analyse/common_func/path_manager.py index 3a332d43a0fe16f0d9ef76cffa010cf95d316b7d..7ef7b4c345c024a0980c6ce2d91839b64c351740 100644 --- a/profiler/cluster_analyse/common_func/path_manager.py +++ b/profiler/cluster_analyse/common_func/path_manager.py @@ -38,9 +38,9 @@ class PathManager: when invalid data throw exception """ cls.input_path_common_check(path) - + base_name = os.path.basename(path) if os.path.isfile(path): - msg = "Invalid input path which is a file path: {path}" + msg = f"Invalid input path which is a file path: {base_name}" raise RuntimeError(msg) @classmethod @@ -55,18 +55,29 @@ class PathManager: when invalid data throw exception """ cls.input_path_common_check(path) - + base_name = os.path.basename(path) if os.path.isdir(path): - msg = "Invalid input path which is a directory path: {path}" + msg = f"Invalid input path which is a directory path: {base_name}" raise RuntimeError(msg) + @classmethod + def check_path_length(cls, path: str): + if len(path) > cls.MAX_PATH_LENGTH: + raise RuntimeError("Length of input path exceeds the limit.") + path_split_list = path.split("/") + for path in path_split_list: + path_list = path.split("\\") + for name in path_list: + if len(name) > cls.MAX_FILE_NAME_LENGTH: + raise RuntimeError("Length of input path exceeds the limit.") + @classmethod def input_path_common_check(cls, path: str): if len(path) > cls.MAX_PATH_LENGTH: raise RuntimeError("Length of input path exceeds the limit.") if os.path.islink(path): - msg = f"Invalid input path which is a soft link: {path}" + msg = f"Invalid input path which is a soft link." raise RuntimeError(msg) if platform.system().lower() == cls.WINDOWS: @@ -74,7 +85,7 @@ class PathManager: else: pattern = r'(\.|/|_|-|\s|[~0-9a-zA-Z])+' if not re.fullmatch(pattern, path): - msg = f"Invalid input path: {path}" + msg = f"Invalid input path." raise RuntimeError(msg) path_split_list = path.split("/") @@ -94,8 +105,9 @@ class PathManager: Exception Description: when invalid path, prompt the user """ + base_name = os.path.basename(path) if not os.path.exists(path): - msg = f"The path does not exist: {path}" + msg = f"Invalid path: {base_name}" raise RuntimeError(msg) if platform.system().lower() == cls.WINDOWS: return @@ -116,10 +128,11 @@ class PathManager: """ cls.check_path_owner_consistent(path) if os.path.islink(path): - msg = f"Invalid path which is a soft link: {path}" + msg = f"Invalid path which is a soft link." raise RuntimeError(msg) + base_name = os.path.basename(path) if not os.access(path, os.W_OK): - msg = f"The path permission check failed: {path}" + msg = f"The path permission check failed: {base_name}" raise RuntimeError(msg) @classmethod @@ -134,15 +147,17 @@ class PathManager: """ cls.check_path_owner_consistent(path) if os.path.islink(path): - msg = f"Invalid path which is a soft link: {path}" + msg = f"Invalid path which is a soft link." raise RuntimeError(msg) + base_name = os.path.basename(path) if not os.access(path, os.R_OK): - msg = f"The path permission check failed: {path}" + msg = f"The path permission check failed: {base_name}" raise RuntimeError(msg) @classmethod def remove_path_safety(cls, path: str): - msg = f"Failed to remove path: {path}" + base_name = os.path.basename(path) + msg = f"Failed to remove path: {base_name}" if os.path.islink(path): raise RuntimeError(msg) if os.path.exists(path): @@ -153,7 +168,8 @@ class PathManager: @classmethod def make_dir_safety(cls, path: str): - msg = f"Failed to make directory: {path}" + base_name = os.path.basename(path) + msg = f"Failed to make directory: {base_name}" if os.path.islink(path): raise RuntimeError(msg) if os.path.exists(path): @@ -165,7 +181,8 @@ class PathManager: @classmethod def create_file_safety(cls, path: str): - msg = f"Failed to create file: {path}" + base_name = os.path.basename(path) + msg = f"Failed to create file: {base_name}" if os.path.islink(path): raise RuntimeError(msg) if os.path.exists(path): @@ -178,6 +195,6 @@ class PathManager: @classmethod def get_realpath(cls, path: str) -> str: if os.path.islink(path): - msg = f"Invalid input path which is a soft link: {path}" + msg = f"Invalid input path which is a soft link." raise RuntimeError(msg) return os.path.realpath(path) diff --git a/profiler/cluster_analyse/communication_group/communication_group_generator.py b/profiler/cluster_analyse/communication_group/communication_group_generator.py index a367e624fb9575bc4f29d732a59b33a57ab678bb..31576eed07c9c4ab59b229472310d1b912798ba7 100644 --- a/profiler/cluster_analyse/communication_group/communication_group_generator.py +++ b/profiler/cluster_analyse/communication_group/communication_group_generator.py @@ -119,14 +119,20 @@ class CommunicationGroupGenerator: return p2p_ops = ops.get(Constant.P2P, {}) for op_name, link_dict in p2p_ops.items(): - for link in link_dict: - src_rank = int(link.split('-')[0]) - dst_rank = int(link.split('-')[1]) - if src_rank != dst_rank: - rank_set = set([src_rank, dst_rank]) - if rank_set in self.p2p_link: - continue - self.p2p_link.append(rank_set) + self.append_p2p_link(op_name, link_dict) + + def append_p2p_link(self, op_name, link_dict): + for link in link_dict: + if '-' not in link: + print(f"{op_name} has an invalid link key {link}!") + break + src_rank = int(link.split('-')[0]) + dst_rank = int(link.split('-')[1]) + if src_rank != dst_rank: + rank_set = set([src_rank, dst_rank]) + if rank_set in self.p2p_link: + continue + self.p2p_link.append(rank_set) def get_collective_ops_name(self, rank_id: int, comm_op_dict: dict): for comm_op in comm_op_dict: diff --git a/profiler/compare_tools/comparator/op_comparator.py b/profiler/compare_tools/comparator/op_comparator.py index cb4b5bfa899ead63b995bacec5a85fa7d52575a3..8ccd428ef82250266722bed0dfd59a97c6dc39c0 100644 --- a/profiler/compare_tools/comparator/op_comparator.py +++ b/profiler/compare_tools/comparator/op_comparator.py @@ -34,8 +34,8 @@ class OpComparator: def _matching_op(cls, base_ops: list, comparison_ops: list, name_func: any) -> list: if not comparison_ops: result_data = [None] * len(base_ops) - for index in range(len(base_ops)): - result_data[index] = [base_ops[index], None] + for index, value in enumerate(base_ops): + result_data[index] = [value, None] return result_data result_data = [] diff --git a/profiler/compare_tools/generation/communication_comparison_generator.py b/profiler/compare_tools/generation/communication_comparison_generator.py index 7838c45aec59e6b794ec26d12f65336a22ee681c..e91126a8b9e4ddcd896ba0f7380e6002137001cf 100644 --- a/profiler/compare_tools/generation/communication_comparison_generator.py +++ b/profiler/compare_tools/generation/communication_comparison_generator.py @@ -14,26 +14,29 @@ class CommunicationComparisonGenerator: self._args = args self._args_manager = ArgsManager() self._compare_result_data = compare_result_data + self._row_index = 3 def create_sheet(self, workbook: Workbook): ws = workbook.create_sheet("CommunicationCompare", 0) ws.sheet_properties.tabColor = Constant.YELLOW_COLOR - # write headers base_headers = Constant.CMP_COMMUNICATION_HEADER comparison_headers = Constant.CMP_COMMUNICATION_HEADER headers = base_headers + comparison_headers + [Constant.DIFF] + self.set_header(ws, base_headers, comparison_headers, headers) + self.write_lines(ws, base_headers, comparison_headers, headers) + + def set_header(self, ws, base_headers, comparison_headers, headers): + # write headers base_trace_start_column = 0 comparison_trace_start_column = len(base_headers) diff_start_column = len(base_headers) + len(comparison_headers) - - for col_index in range(len(headers)): + for col_index, header_name in enumerate(headers): ws.cell(row=1, column=col_index + 1).border = Constant.BORDER ws.cell(row=1, column=col_index + 1).font = Font(name='Arial') ws.cell(row=1, column=col_index + 1).fill = Constant.HEADERS_FILL ws.cell(row=2, column=col_index + 1).border = Constant.BORDER ws.cell(row=2, column=col_index + 1).font = Font(name='Arial', bold=True) ws.cell(row=2, column=col_index + 1).fill = Constant.HEADERS_FILL - header_name = headers[col_index] if col_index < comparison_trace_start_column: ws.cell(row=1, column=col_index + 1).value = Constant.BASE_PROFILING elif col_index < diff_start_column: @@ -50,92 +53,98 @@ class CommunicationComparisonGenerator: ws.merge_cells(start_row=1, start_column=headers.index(Constant.DIFF) + 1, end_row=2, end_column=headers.index(Constant.DIFF) + 1) + def write_lines(self, ws, base_headers, comparison_headers, headers): # write lines - row_index = 3 + self._row_index = 3 for _, row in self._compare_result_data.iterrows(): - # write summary lines - base_name = Constant.NA if math.isnan(row[Constant.BASE_CALLS]) else row[Constant.OP_KEY] - comparison_name = Constant.NA if math.isnan(row[Constant.COMPARISON_CALLS]) else row[Constant.OP_KEY] - if math.isnan(row[Constant.BASE_SUM]) or math.isnan(row[Constant.COMPARISON_SUM]) or row[ - Constant.BASE_SUM] == 0: - diff = Constant.NA + self.write_summary_lines(ws, row, headers) + self._row_index += 1 + self.write_detail_lines(ws, row, base_headers, comparison_headers, headers) + + def write_summary_lines(self, ws, row, headers): + # write summary lines + base_name = Constant.NA if math.isnan(row[Constant.BASE_CALLS]) else row[Constant.OP_KEY] + comparison_name = Constant.NA if math.isnan(row[Constant.COMPARISON_CALLS]) else row[Constant.OP_KEY] + if math.isnan(row[Constant.BASE_SUM]) or math.isnan(row[Constant.COMPARISON_SUM]) or row[ + Constant.BASE_SUM] == 0: + diff = Constant.NA + else: + diff = (row[Constant.COMPARISON_SUM] - row[Constant.BASE_SUM]) / row[Constant.BASE_SUM] + row_data = [base_name, Constant.NA, row[Constant.BASE_CALLS], row[Constant.BASE_SUM], + row[Constant.BASE_AVG], row[Constant.BASE_MAX], row[Constant.BASE_MIN], comparison_name, + Constant.NA, row[Constant.COMPARISON_CALLS], row[Constant.COMPARISON_SUM], + row[Constant.COMPARISON_AVG], row[Constant.COMPARISON_MAX], row[Constant.COMPARISON_MIN], diff] + for index, header_name in enumerate(headers): + if header_name in ( + Constant.CALLS, Constant.TOTAL_DURATION, Constant.AVG_DURATION, Constant.MAX_DURATION, + Constant.MIN_DURATION): + ws.cell(row=self._row_index, column=index + 1).number_format = '0.00' + if header_name == Constant.DIFF: + ws.cell(row=self._row_index, column=index + 1).number_format = '0.00%' + if diff != Constant.NA and diff < 0: + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', + color=Constant.GREEN_COLOR) + elif diff != Constant.NA and diff >= 0: + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', color=Constant.RED_COLOR) else: - diff = (row[Constant.COMPARISON_SUM] - row[Constant.BASE_SUM]) / row[Constant.BASE_SUM] - row_data = [base_name, Constant.NA, row[Constant.BASE_CALLS], row[Constant.BASE_SUM], - row[Constant.BASE_AVG], row[Constant.BASE_MAX], row[Constant.BASE_MIN], comparison_name, - Constant.NA, row[Constant.COMPARISON_CALLS], row[Constant.COMPARISON_SUM], - row[Constant.COMPARISON_AVG], row[Constant.COMPARISON_MAX], row[Constant.COMPARISON_MIN], diff] - for index in range(len(headers)): - if headers[index] in ( + bold = header_name == Constant.COMMUNICAT_OP + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', bold=bold) + value = row_data[index] + if value != Constant.NA: + ws.cell(row=self._row_index, column=index + 1).value = value + ws.cell(row=self._row_index, column=index + 1).border = Constant.BORDER + ws.cell(row=self._row_index, column=index + 1).fill = PatternFill("solid", + fgColor=Constant.SUMMARY_LINE_COLOR) + + def write_detail_lines(self, ws, row, base_headers, comparison_headers, headers): + # write detail lines + base_name = Constant.NA if math.isnan(row[Constant.BASE_CALLS]) else row[Constant.OP_KEY] + comparison_name = Constant.NA if math.isnan(row[Constant.COMPARISON_CALLS]) else row[Constant.OP_KEY] + base_task_list = self._args_manager.base_profiling.communication_task_data.get(base_name, []) + comparison_task_list = self._args_manager.comparison_profiling.communication_task_data.get(comparison_name, []) + if base_task_list: + base_data = [[data.get("name", ""), float(data.get("dur", 0))] for data in base_task_list] + base_df = pd.DataFrame(base_data, columns=[Constant.OP_KEY, Constant.DEVICE_DUR]) + base_data = base_df.groupby(Constant.OP_KEY).agg( + ["count", "sum", "mean", "max", "min"]).reset_index().values.tolist() + else: + base_data = [] + if comparison_task_list: + comparison_data = [[data.get("name", ""), float(data.get("dur", 0))] for data in comparison_task_list] + comparison_df = pd.DataFrame(comparison_data, columns=[Constant.OP_KEY, Constant.DEVICE_DUR]) + comparison_data = comparison_df.groupby(Constant.OP_KEY).agg( + ["count", "sum", "mean", "max", "min"]).reset_index().values.tolist() + else: + comparison_data = [] + for index in range(max(len(base_data), len(comparison_data))): + base_detail_data, comparison_detail_data = [Constant.NA] * len(base_headers), [Constant.NA] * len(comparison_headers) + base_detail_data[0] = "|" + comparison_detail_data[0] = "|" + if index < len(base_data): + total_dur = sum([data[2] for data in base_data]) + percent = 0.0 if total_dur < Constant.EPS else base_data[index][2] / total_dur + dur_percent = "%.2f%%" % (percent * 100) + base_data[index][0] = f"{base_data[index][0]} ({dur_percent})" + base_detail_data[1:] = base_data[index] + if index < len(comparison_data): + total_dur = sum([data[2] for data in comparison_data]) + percent = 0.0 if total_dur < Constant.EPS else comparison_data[index][2] / total_dur + dur_percent = "%.2f%%" % (percent * 100) + comparison_data[index][0] = f"{comparison_data[index][0]} ({dur_percent})" + comparison_detail_data[1:] = comparison_data[index] + + detail_data = base_detail_data + comparison_detail_data + [Constant.NA] + for colum_index in range(len(headers)): + if headers[colum_index] in ( Constant.CALLS, Constant.TOTAL_DURATION, Constant.AVG_DURATION, Constant.MAX_DURATION, Constant.MIN_DURATION): - ws.cell(row=row_index, column=index + 1).number_format = '0.00' - if headers[index] == Constant.DIFF: - ws.cell(row=row_index, column=index + 1).number_format = '0.00%' - if diff != Constant.NA and diff < 0: - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', - color=Constant.GREEN_COLOR) - elif diff != Constant.NA and diff >= 0: - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', color=Constant.RED_COLOR) - else: - bold = headers[index] == Constant.COMMUNICAT_OP - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', bold=bold) - value = row_data[index] + ws.cell(row=self._row_index, column=colum_index + 1) .number_format = '0.00' + value = detail_data[colum_index] if value != Constant.NA: - ws.cell(row=row_index, column=index + 1).value = value - ws.cell(row=row_index, column=index + 1).border = Constant.BORDER - ws.cell(row=row_index, column=index + 1).fill = PatternFill("solid", - fgColor=Constant.SUMMARY_LINE_COLOR) - row_index += 1 - - # write detail lines - base_task_list = self._args_manager.base_profiling.communication_task_data.get(base_name, []) - comparison_task_list = self._args_manager.comparison_profiling.communication_task_data.get(comparison_name, - []) - if base_task_list: - base_data = [[data.get("name", ""), float(data.get("dur", 0))] for data in base_task_list] - base_df = pd.DataFrame(base_data, columns=[Constant.OP_KEY, Constant.DEVICE_DUR]) - base_data = base_df.groupby(Constant.OP_KEY).agg( - ["count", "sum", "mean", "max", "min"]).reset_index().values.tolist() - else: - base_data = [] - if comparison_task_list: - comparison_data = [[data.get("name", ""), float(data.get("dur", 0))] for data in comparison_task_list] - comparison_df = pd.DataFrame(comparison_data, columns=[Constant.OP_KEY, Constant.DEVICE_DUR]) - comparison_data = comparison_df.groupby(Constant.OP_KEY).agg( - ["count", "sum", "mean", "max", "min"]).reset_index().values.tolist() - else: - comparison_data = [] - - for index in range(max(len(base_data), len(comparison_data))): - base_detail_data, comparison_detail_data = [Constant.NA] * len(base_headers), \ - [Constant.NA] * len(comparison_headers) - base_detail_data[0] = "|" - comparison_detail_data[0] = "|" - if index < len(base_data): - total_dur = sum([data[2] for data in base_data]) - dur_percent = "%.2f%%" % (base_data[index][2] / total_dur * 100) - base_data[index][0] = f"{base_data[index][0]} ({dur_percent})" - base_detail_data[1:] = base_data[index] - if index < len(comparison_data): - total_dur = sum([data[2] for data in comparison_data]) - dur_percent = "%.2f%%" % (comparison_data[index][2] / total_dur * 100) - comparison_data[index][0] = f"{comparison_data[index][0]} ({dur_percent})" - comparison_detail_data[1:] = comparison_data[index] - - detail_data = base_detail_data + comparison_detail_data + [Constant.NA] - for colum_index in range(len(headers)): - if headers[colum_index] in ( - Constant.CALLS, Constant.TOTAL_DURATION, Constant.AVG_DURATION, Constant.MAX_DURATION, - Constant.MIN_DURATION): - ws.cell(row=row_index, column=colum_index + 1) .number_format = '0.00' - value = detail_data[colum_index] - if value != Constant.NA: - ws.cell(row=row_index, column=colum_index + 1).value = value - bold = headers[colum_index] == Constant.OP_NAME - ws.cell(row=row_index, column=colum_index + 1).font = Font(name='Arial', bold=bold) - ws.cell(row=row_index, column=colum_index + 1).border = Constant.BORDER - if headers[colum_index] == Constant.COMMUNICAT_OP: - ws.cell(row=row_index, column=colum_index + 1).alignment = Alignment(horizontal="center", - vertical="center") - row_index += 1 + ws.cell(row=self._row_index, column=colum_index + 1).value = value + bold = headers[colum_index] == Constant.OP_NAME + ws.cell(row=self._row_index, column=colum_index + 1).font = Font(name='Arial', bold=bold) + ws.cell(row=self._row_index, column=colum_index + 1).border = Constant.BORDER + if headers[colum_index] == Constant.COMMUNICAT_OP: + ws.cell(row=self._row_index, column=colum_index + 1).alignment = Alignment(horizontal="center", vertical="center") + self._row_index += 1 diff --git a/profiler/compare_tools/generation/op_comparison_generator.py b/profiler/compare_tools/generation/op_comparison_generator.py index 1e48d7d0b4443bb64ff2706e3bb14526f9a875a0..5d1d658f724f0ef6a05eaccab514f826befe88b9 100644 --- a/profiler/compare_tools/generation/op_comparison_generator.py +++ b/profiler/compare_tools/generation/op_comparison_generator.py @@ -1,4 +1,5 @@ import copy +from collections import namedtuple from openpyxl.styles import Font, PatternFill, Alignment from openpyxl.workbook import Workbook @@ -15,6 +16,7 @@ class OpComparisonGenerator: self._compare_type = compare_type self._base_headers = [] self._comparison_headers = [] + self._row_index = 3 self.update_headers() def update_headers(self): @@ -32,10 +34,23 @@ class OpComparisonGenerator: def create_sheet(self, workbook: Workbook): ws = workbook.create_sheet(self._compare_type, 0) ws.sheet_properties.tabColor = Constant.YELLOW_COLOR - # write headers headers = self._base_headers + self._comparison_headers + [Constant.DIFF, Constant.OP_NAME_FILTER, Constant.DIFF_FILTER] + self.writer_headers(ws, headers) + # write lines + self._row_index = 3 + for data in self._compare_result_data: + base_event_list = TreeBuilder.get_total_compare_event(data[0], self._compare_type) if data[0] else [] + comparison_event_list = TreeBuilder.get_total_compare_event(data[1], self._compare_type) if data[1] else [] + diff = self.write_summary_lines(ws, headers, data, base_event_list, comparison_event_list) + self._row_index += 1 + EventListWrapper = namedtuple('EventListWrapper', ['base_event_list', 'comparison_event_list']) + event_list = EventListWrapper(base_event_list, comparison_event_list) + self.write_detail_lines(ws, headers, data, diff, event_list) + + def writer_headers(self, ws, headers): + # write headers base_trace_start_column = 0 comparison_trace_start_column = len(self._base_headers) diff_start_column = len(self._base_headers) + len(self._comparison_headers) @@ -70,90 +85,100 @@ class OpComparisonGenerator: ws.merge_cells(start_row=1, start_column=headers.index(Constant.DIFF_FILTER) + 1, end_row=2, end_column=headers.index(Constant.DIFF_FILTER) + 1) - # write lines - row_index = 3 - for data in self._compare_result_data: - # write summary lines - base_event_list = TreeBuilder.get_total_compare_event(data[0], self._compare_type) if data[0] else [] - comparison_event_list = TreeBuilder.get_total_compare_event(data[1], self._compare_type) if data[1] else [] - base_summary_data, comparison_summary_data = [Constant.NA] * len(self._base_headers), \ - [Constant.NA] * len(self._comparison_headers) - if data[0]: - base_summary_data[0] = data[0].name - base_summary_data[1] = data[0].input_shape - base_summary_data[2] = data[0].input_type - base_summary_data[3] = sum( - [x.compare_index for x in base_event_list]) if base_event_list else Constant.NA - if data[1]: - comparison_summary_data[0] = data[1].name - comparison_summary_data[1] = data[1].input_shape - comparison_summary_data[2] = data[1].input_type - comparison_summary_data[3] = sum( - [x.compare_index for x in comparison_event_list]) if comparison_event_list else Constant.NA - if base_event_list and comparison_event_list and base_summary_data[3]: - diff = (comparison_summary_data[3] - base_summary_data[3]) / base_summary_data[3] - else: - diff = Constant.NA - op_name = data[0].name if data[0] else data[1].name + def write_summary_lines(self, ws, headers, data, base_event_list, comparison_event_list): + def ws_write_diff(ws, index, value): + ws.cell(row=self._row_index, column=index + 1).number_format = '0.00%' + if value != Constant.NA and value < 0: + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', color=Constant.GREEN_COLOR) + elif value != Constant.NA and value >= 0: + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', color=Constant.RED_COLOR) + + def ws_write_diff_filter(ws, index, diff_value): + if diff_value != Constant.NA and diff_value < 0: + ws.cell(row=self._row_index, column=index + 1).fill = PatternFill("solid", + fgColor=Constant.GREEN_COLOR) + elif diff_value != Constant.NA and diff_value >= 0: + ws.cell(row=self._row_index, column=index + 1).fill = PatternFill("solid", fgColor=Constant.RED_COLOR) + # write summary lines + base_summary_data, comparison_summary_data = [Constant.NA] * len(self._base_headers), \ + [Constant.NA] * len(self._comparison_headers) + if data[0]: + base_summary_data[0] = data[0].name + base_summary_data[1] = data[0].input_shape + base_summary_data[2] = data[0].input_type + base_summary_data[3] = sum( + [x.compare_index for x in base_event_list]) if base_event_list else Constant.NA + if data[1]: + comparison_summary_data[0] = data[1].name + comparison_summary_data[1] = data[1].input_shape + comparison_summary_data[2] = data[1].input_type + comparison_summary_data[3] = sum( + [x.compare_index for x in comparison_event_list]) if comparison_event_list else Constant.NA + if base_event_list and comparison_event_list and base_summary_data[3]: + diff = (comparison_summary_data[3] - base_summary_data[3]) / base_summary_data[3] + else: + diff = Constant.NA + op_name = data[0].name if data[0] else data[1].name + + summary_data = base_summary_data + comparison_summary_data + [diff, op_name, Constant.NA] + if len(summary_data) < len(headers): + raise RuntimeError("Fail to write summary lines!") + for index, header_name in enumerate(headers): + value = summary_data[index] + if header_name == Constant.DIFF: + ws_write_diff(ws, index, value) + if header_name == Constant.DIFF_FILTER: + diff_value = summary_data[headers.index(Constant.DIFF)] + ws_write_diff_filter(ws, index, diff_value) + elif header_name != Constant.OP_NAME_FILTER: + ws.cell(row=self._row_index, column=index + 1).fill = PatternFill("solid", + fgColor=Constant.SUMMARY_LINE_COLOR) - summary_data = base_summary_data + comparison_summary_data + [diff, op_name, Constant.NA] - for index in range(len(headers)): - value = summary_data[index] - if headers[index] == Constant.DIFF: - ws.cell(row=row_index, column=index + 1).number_format = '0.00%' - if value != Constant.NA and value < 0: - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', color=Constant.GREEN_COLOR) - elif value != Constant.NA and value >= 0: - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', color=Constant.RED_COLOR) - if headers[index] == Constant.DIFF_FILTER: - diff_value = summary_data[headers.index(Constant.DIFF)] - if diff_value != Constant.NA and diff_value < 0: - ws.cell(row=row_index, column=index + 1).fill = PatternFill("solid", - fgColor=Constant.GREEN_COLOR) - elif diff_value != Constant.NA and diff_value >= 0: - ws.cell(row=row_index, column=index + 1).fill = PatternFill("solid", fgColor=Constant.RED_COLOR) - elif headers[index] != Constant.OP_NAME_FILTER: - ws.cell(row=row_index, column=index + 1).fill = PatternFill("solid", - fgColor=Constant.SUMMARY_LINE_COLOR) + if value != Constant.NA: + ws.cell(row=self._row_index, column=index + 1).value = value + bold = header_name == Constant.OP_NAME + if header_name != Constant.DIFF: + ws.cell(row=self._row_index, column=index + 1).font = Font(name='Arial', bold=bold) + ws.cell(row=self._row_index, column=index + 1).border = Constant.BORDER + return diff - if value != Constant.NA: - ws.cell(row=row_index, column=index + 1).value = value - bold = headers[index] == Constant.OP_NAME - if headers[index] != Constant.DIFF: - ws.cell(row=row_index, column=index + 1).font = Font(name='Arial', bold=bold) - ws.cell(row=row_index, column=index + 1).border = Constant.BORDER - row_index += 1 + def write_detail_lines(self, ws, headers, data, diff, event_list): + def ws_write_helper(ws, colum_index, value, diff, headers): + if value != Constant.NA: + ws.cell(row=self._row_index, column=colum_index + 1).value = value + bold = headers[colum_index] == Constant.OP_NAME + ws.cell(row=self._row_index, column=colum_index + 1).font = Font(name='Arial', bold=bold) + ws.cell(row=self._row_index, column=colum_index + 1).border = Constant.BORDER + if headers[colum_index] == Constant.DIFF_FILTER: + if diff != Constant.NA and diff < 0: + ws.cell(row=self._row_index, column=colum_index + 1).fill = PatternFill("solid", + fgColor=Constant.GREEN_COLOR) + elif diff != Constant.NA and diff >= 0: + ws.cell(row=self._row_index, column=colum_index + 1).fill = PatternFill("solid", + fgColor=Constant.RED_COLOR) + if headers[colum_index] == Constant.OP_NAME: + ws.cell(row=self._row_index, column=colum_index + 1).alignment = Alignment(horizontal="center", + vertical="center") - # write detail lines - base_event_num, comparison_event_num = len(base_event_list), len(comparison_event_list) - for index in range(max(base_event_num, comparison_event_num)): - base_detail_data, comparison_detail_data = [Constant.NA] * len(self._base_headers), \ - [Constant.NA] * len(self._comparison_headers) - base_detail_data[0] = "|" - comparison_detail_data[0] = "|" - if index < base_event_num: - base_event = base_event_list[index] - base_detail_data[1:] = base_event.get_record() - if index < comparison_event_num: - comparison_event = comparison_event_list[index] - comparison_detail_data[1:] = comparison_event.get_record() + base_event_list = event_list.base_event_list + comparison_event_list = event_list.comparison_event_list + # write detail lines + op_name = data[0].name if data[0] else data[1].name + base_event_num, comparison_event_num = len(base_event_list), len(comparison_event_list) + for index in range(max(base_event_num, comparison_event_num)): + base_detail_data, comparison_detail_data = [Constant.NA] * len(self._base_headers), \ + [Constant.NA] * len(self._comparison_headers) + base_detail_data[0] = "|" + comparison_detail_data[0] = "|" + if index < base_event_num: + base_event = base_event_list[index] + base_detail_data[1:] = base_event.get_record() + if index < comparison_event_num: + comparison_event = comparison_event_list[index] + comparison_detail_data[1:] = comparison_event.get_record() - detail_data = base_detail_data + comparison_detail_data + [Constant.NA, op_name, Constant.NA] - for colum_index in range(len(headers)): - value = detail_data[colum_index] - if value != Constant.NA: - ws.cell(row=row_index, column=colum_index + 1).value = value - bold = headers[colum_index] == Constant.OP_NAME - ws.cell(row=row_index, column=colum_index + 1).font = Font(name='Arial', bold=bold) - ws.cell(row=row_index, column=colum_index + 1).border = Constant.BORDER - if headers[colum_index] == Constant.DIFF_FILTER: - if diff != Constant.NA and diff < 0: - ws.cell(row=row_index, column=colum_index + 1).fill = PatternFill("solid", - fgColor=Constant.GREEN_COLOR) - elif diff != Constant.NA and diff >= 0: - ws.cell(row=row_index, column=colum_index + 1).fill = PatternFill("solid", - fgColor=Constant.RED_COLOR) - if headers[colum_index] == Constant.OP_NAME: - ws.cell(row=row_index, column=colum_index + 1).alignment = Alignment(horizontal="center", - vertical="center") - row_index += 1 + detail_data = base_detail_data + comparison_detail_data + [Constant.NA, op_name, Constant.NA] + for colum_index in range(len(headers)): + value = detail_data[colum_index] + ws_write_helper(ws, colum_index, value, diff, headers) + self._row_index += 1 diff --git a/profiler/compare_tools/performance_compare.py b/profiler/compare_tools/performance_compare.py index 2d98fce4be613ea5eedfd4ebb57cf19dc10d837d..5bcfada0bb5fcc14d927f7387c9954160aed7b24 100644 --- a/profiler/compare_tools/performance_compare.py +++ b/profiler/compare_tools/performance_compare.py @@ -6,10 +6,12 @@ import sys import time sys.path.append( - os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "cluster_analyse", "common_func")) + os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "cluster_analyse")) + from generation.comparison_generator import ComparisonGenerator from utils.args_manager import ArgsManager from profiling_analysis.profiling_parse import prof_main +from common_func.path_manager import PathManager def performance_compare(args): @@ -46,7 +48,7 @@ def main(): dir_path = args.output_path if args.output_path else "./" file_name = "performance_comparison_result_{}.xlsx".format( time.strftime("%Y%m%d%H%M%S", time.localtime(time.time()))) - result_file_path = os.path.realpath(os.path.join(dir_path, file_name)) + result_file_path = PathManager.get_realpath(os.path.join(dir_path, file_name)) ComparisonGenerator(args).create_excel(result_file_path) print(f"[INFO] The comparison result file has been generated: {result_file_path}") diff --git a/profiler/compare_tools/profiling_analysis/gpu_parser.py b/profiler/compare_tools/profiling_analysis/gpu_parser.py index b7999257894ea336cf2cf857a05a17a67cc17419..3b470a8d4abdf17842ca9c9c72205f386cafd435 100644 --- a/profiler/compare_tools/profiling_analysis/gpu_parser.py +++ b/profiler/compare_tools/profiling_analysis/gpu_parser.py @@ -13,6 +13,7 @@ # See the License for the specific language governing permissions and # limitations under the License. +import os from collections import Counter, defaultdict import pandas as pd @@ -20,6 +21,26 @@ import profiling_analysis.parser_helper as parser_helper from utils.file_reader import FileReader +class OpTimeWarper: + def __init__( + self, + cube_time: float = 0.0, + fa_time_fwd: float = 0.0, + fa_time_bwd: float = 0.0, + all_op_time: float = 0.0, + compute_stream_dur: float = 0.0, + cube_num: int = 0, + vec_num: int = 0 + ): + self.cube_time = cube_time + self.fa_time_fwd = fa_time_fwd + self.fa_time_bwd = fa_time_bwd + self.all_op_time = all_op_time + self.compute_stream_dur = compute_stream_dur + self.cube_num = cube_num + self.vec_num = vec_num + + class GpuProfilingParser: NCCL_MARK = 'nccl' CUBE_MARK = 'gemm' @@ -37,17 +58,14 @@ class GpuProfilingParser: return True return False - def parse_events(self): + def update_op_list(self, op_list, marks): cube_time = 0.0 all_op_time = 0.0 fa_time_bwd = 0.0 fa_time_fwd = 0.0 cube_num = 0 vec_num = 0 - op_list = [] compute_stream_dur = 0.0 - marks = defaultdict(int) # mark for compute communication_not_overlapped time - for event in self.trace_events: if not isinstance(event, dict): continue @@ -80,8 +98,30 @@ class GpuProfilingParser: vec_num += 1 all_op_time += float(dur) op_list.append([ts, name, cat, dur]) - op_dataframe = pd.DataFrame(op_list, columns=['time start', 'name', 'cat', 'dur']) - op_dataframe.to_csv('gpu_perf.csv', index=False) + time_wrapper = OpTimeWarper( + cube_time=cube_time, + fa_time_fwd=fa_time_fwd, + fa_time_bwd=fa_time_bwd, + all_op_time=all_op_time, + compute_stream_dur=compute_stream_dur, + cube_num=cube_num, + vec_num=vec_num + ) + return time_wrapper + + def parse_events(self): + op_list = [] + marks = defaultdict(int) # mark for compute communication_not_overlapped time + + time_wrapper = self.update_op_list(op_list, marks) + cube_time = time_wrapper.cube_time + fa_time_fwd = time_wrapper.fa_time_fwd + fa_time_bwd = time_wrapper.fa_time_bwd + all_op_time = time_wrapper.all_op_time + compute_stream_dur = time_wrapper.compute_stream_dur + cube_num = time_wrapper.cube_num + vec_num = time_wrapper.vec_num + self.profiling_info.compute_time = len([_ for _, value in marks.items() if value < 0]) / 10 ** 6 self.profiling_info.communication_not_overlapped = len([_ for _, value in marks.items() if value > 0]) / 10 ** 6 self.profiling_info.flash_attention_time_bwd = fa_time_bwd / 10 ** 6 diff --git a/profiler/compare_tools/profiling_analysis/npu_parser.py b/profiler/compare_tools/profiling_analysis/npu_parser.py index 73eeb1fd00bb5b748fec4d49a9d03944ae399dca..a8725a1486c43cbcd77875285526b6d515c95a72 100644 --- a/profiler/compare_tools/profiling_analysis/npu_parser.py +++ b/profiler/compare_tools/profiling_analysis/npu_parser.py @@ -18,6 +18,28 @@ import pandas as pd from collections import defaultdict import profiling_analysis.parser_helper as parser_helper from utils.file_reader import FileReader +from common_func.path_manager import PathManager +from common_func.file_manager import FileManager + + +class NpuInfoWrapper: + def __init__( + self, + compute_time: int, + communication_time: int, + is_cluster: bool, + event_wait_sqe: dict, + ai_core_dict: dict, + event_wait_sqe_res: dict, + ai_core_res: dict, + ): + self.compute_time = compute_time + self.communication_time = communication_time + self.is_cluster = is_cluster + self.event_wait_sqe = event_wait_sqe + self.ai_core_dict = ai_core_dict + self.event_wait_sqe_res = event_wait_sqe_res + self.ai_core_res = ai_core_res class NpuProfilingParser: @@ -65,7 +87,19 @@ class NpuProfilingParser: communication_time += dur min_ts = ts if ts < min_ts else min_ts max_ts = (ts + dur) if (ts + dur) > max_ts else max_ts + npu_info_wrapper = NpuInfoWrapper( + compute_time, communication_time, is_cluster, + event_wait_sqe, ai_core_dict, event_wait_sqe_res, ai_core_res) + self.update_npu_info(max_ts - min_ts, npu_info_wrapper) + def update_npu_info(self, ts_dur, npu_info_wrapper): + compute_time = npu_info_wrapper.compute_time + communication_time = npu_info_wrapper.communication_time + is_cluster = npu_info_wrapper.is_cluster + event_wait_sqe = npu_info_wrapper.event_wait_sqe + ai_core_dict = npu_info_wrapper.ai_core_dict + event_wait_sqe_res = npu_info_wrapper.event_wait_sqe_res + ai_core_res = npu_info_wrapper.ai_core_res # AI_CORE和EVENT_WAIT_SQE共存为计算流 compute_stream = [] parallel_stream = [] @@ -87,7 +121,7 @@ class NpuProfilingParser: self.parallel_time = self.interval_intersection(cs_event_wait_sqe_list, cs_ai_core_list) self.profiling_info.compute_time = compute_time / 10 ** 6 if is_cluster else \ ai_core_res[compute_stream[0]] / 10 ** 6 - self.profiling_info.e2e_time = (max_ts - min_ts) / 10 ** 6 if is_cluster else \ + self.profiling_info.e2e_time = ts_dur / 10 ** 6 if is_cluster else \ (self.max_stream_ts - self.min_stream_ts) / 10 ** 6 self.profiling_info.communication_not_overlapped = communication_time / 10 ** 6 \ if is_cluster else (event_wait_sqe_res[compute_stream[0]] - self.parallel_time) / 10 ** 6 @@ -116,6 +150,8 @@ class NpuProfilingParser: if not self.npu_summary_file: print('[WARNING] Npu kernel details csv file is not available.') return + PathManager.check_path_readable(self.npu_summary_file) + FileManager.check_file_size(self.npu_summary_file) info = pd.read_csv(self.npu_summary_file, index_col=None) cube_time = 0.0 vec_time = 0.0 @@ -155,6 +191,8 @@ class NpuProfilingParser: print('[INFO] Npu op memory csv file is not available.') return try: + PathManager.check_path_readable(self.npu_mem_file) + FileManager.check_file_size(self.npu_mem_file) info = pd.read_csv(self.npu_mem_file, usecols=['Total Reserved(MB)'], index_col=None) except ValueError: print('[ERROR] Load memory info failed.') diff --git a/profiler/compare_tools/utils/args_manager.py b/profiler/compare_tools/utils/args_manager.py index 48bcdd76997b4b25ad80dc4dcc7b438b0b7a8c56..632333b7c1168a274facdab5dfe3892639a543f4 100644 --- a/profiler/compare_tools/utils/args_manager.py +++ b/profiler/compare_tools/utils/args_manager.py @@ -1,6 +1,6 @@ import os.path -from path_manager import PathManager +from common_func.path_manager import PathManager from utils.constant import Constant from utils.file_reader import FileReader from utils.profiling_parser import GPUProfilingParser, NPUProfilingParser diff --git a/profiler/compare_tools/utils/constant.py b/profiler/compare_tools/utils/constant.py index 360c2ab44ae8f56c1708bb2c8213c357445ffcb4..828dc758014a397e8329fc0658141272c160322d 100644 --- a/profiler/compare_tools/utils/constant.py +++ b/profiler/compare_tools/utils/constant.py @@ -15,6 +15,9 @@ class Constant(object): RED_COLOR = "00FF0000" SUMMARY_LINE_COLOR = "F0F8FF" + # epsilon + EPS = 1e-15 + # autority FILE_AUTHORITY = 0o640 DIR_AUTHORITY = 0o750 diff --git a/profiler/compare_tools/utils/file_reader.py b/profiler/compare_tools/utils/file_reader.py index 37853f41f4231217f8d8ece3b1dbc10fd7934b4e..34e4ecab49c7143d231b3b1e2b208fa2f93d8696 100644 --- a/profiler/compare_tools/utils/file_reader.py +++ b/profiler/compare_tools/utils/file_reader.py @@ -2,7 +2,7 @@ import csv import json import os -from path_manager import PathManager +from common_func.path_manager import PathManager from utils.constant import Constant @@ -19,7 +19,7 @@ class FileReader: return [] if file_size > Constant.MAX_FILE_SIZE: check_msg = input( - f"The file({file_path}) size exceeds the preset max value, do you continue reading the file? [y/n]") + f"The file({file_path}) size exceeds the preset max value. Continue reading the file? [y/n]") if check_msg.lower() != "y": print(f"[WARNING] The user choose not to read the file: {file_path}") return [] @@ -41,7 +41,7 @@ class FileReader: return [] if file_size > Constant.MAX_FILE_SIZE: check_msg = input( - f"The file({file_path}) size exceeds the preset max value, do you continue reading the file? [y/n]") + f"The file({file_path}) size exceeds the preset max value. Continue reading the file? [y/n]") if check_msg.lower() != "y": print(f"[WARNING] The user choose not to read the file: {file_path}") return [] diff --git a/profiler/compare_tools/utils/profiling_parser.py b/profiler/compare_tools/utils/profiling_parser.py index b49217b844bba89d97287fd6df91d4feac668255..ceb24e6c310c838e336f2b9e6ede878a7a416a68 100644 --- a/profiler/compare_tools/utils/profiling_parser.py +++ b/profiler/compare_tools/utils/profiling_parser.py @@ -1,4 +1,4 @@ -from abc import ABCMeta, abstractmethod +from abc import abstractmethod from math import ceil from utils.compare_event import KernelEvent @@ -7,31 +7,16 @@ from utils.file_reader import FileReader from utils.trace_event_data import TraceEventData -class ProfilingParser(metaclass=ABCMeta): - @abstractmethod - def get_torch_op_data(self): - raise NotImplementedError - - @abstractmethod - def get_kernel_dict(self): - raise NotImplementedError - - @abstractmethod - def get_memory_list(self): - raise NotImplementedError - - -class GPUProfilingParser(ProfilingParser): +class ProfilingParser: def __init__(self, args: any, path_dict: dict): self._args = args self._profiling_path = path_dict.get(Constant.PROFILING_PATH) - self._json_path = path_dict.get(Constant.PROFILING_PATH) self._torch_op_data = None self._kernel_dict = None self._memory_list = None self._communication_data = None self._communication_task_data = None - + @property def file_path(self) -> str: return self._profiling_path @@ -70,6 +55,24 @@ class GPUProfilingParser(ProfilingParser): self.get_communication_data() return self._communication_task_data + @abstractmethod + def get_torch_op_data(self): + raise NotImplementedError + + @abstractmethod + def get_kernel_dict(self): + raise NotImplementedError + + @abstractmethod + def get_memory_list(self): + raise NotImplementedError + + +class GPUProfilingParser(ProfilingParser): + def __init__(self, args: any, path_dict: dict): + super().__init__(args, path_dict) + self._json_path = path_dict.get(Constant.PROFILING_PATH) + def get_torch_op_data(self): torch_op_list = [] json_data = FileReader.read_trace_file(self._json_path) @@ -144,53 +147,9 @@ class GPUProfilingParser(ProfilingParser): class NPUProfilingParser(ProfilingParser): def __init__(self, args: any, path_dict: str): - self._args = args - self._profiling_path = path_dict.get(Constant.PROFILING_PATH) + super().__init__(args, path_dict) self._json_path = path_dict.get(Constant.TRACE_PATH) self._memory_data_path = path_dict.get(Constant.MEMORY_DATA_PATH) - self._torch_op_data = None - self._kernel_dict = None - self._memory_list = None - self._communication_data = None - self._communication_task_data = None - - @property - def file_path(self) -> str: - return self._profiling_path - - @property - def json_path(self) -> str: - return self._json_path - - @property - def torch_op_data(self) -> list: - if self._torch_op_data is None: - self.get_torch_op_data() - return self._torch_op_data - - @property - def kernel_dict(self) -> dict: - if self._kernel_dict is None: - self.get_kernel_dict() - return self._kernel_dict - - @property - def memory_list(self) -> list: - if self._memory_list is None: - self.get_memory_list() - return self._memory_list - - @property - def communication_data(self) -> dict: - if self._communication_data is None: - self.get_communication_data() - return self._communication_data - - @property - def communication_task_data(self) -> dict: - if self._communication_task_data is None: - self.get_communication_data() - return self._communication_task_data def get_torch_op_data(self): torch_op_list = [] @@ -272,55 +231,70 @@ class NPUProfilingParser(ProfilingParser): return dequeue_data[left] if end_time > ts_time else None def get_communication_data(self): + def get_pid(json_data): + pid = None + for data in json_data: + trace_event = TraceEventData(data) + if not trace_event.is_process_meta(): + continue + if trace_event.is_hccl_process(): + pid = trace_event.pid + break + return pid + + def get_tid_list(pid, tid_list, json_data): + for data in json_data: + trace_event = TraceEventData(data) + if not trace_event.is_thread_meta(): + continue + if trace_event.pid != pid: + continue + if trace_event.is_communication_op_thread(): + tid_list.append(trace_event.tid) + + def get_comm_data(pid, tid_list, json_data): + for data in json_data: + trace_event = TraceEventData(data) + if not trace_event.is_x_mode(): + continue + if trace_event.pid != pid: + continue + if trace_event.tid in tid_list: + self._communication_data.append(data) + + def get_comm_task_data(pid, tid_list, json_data): + for data in json_data: + trace_event = TraceEventData(data) + if not trace_event.is_x_mode(): + continue + if trace_event.pid != pid: + continue + if trace_event.tid in tid_list: + continue + ts = trace_event.start_time + for communication_op in self._communication_data: + comm_op_event = TraceEventData(communication_op) + if ts < comm_op_event.start_time or ts > comm_op_event.end_time: + continue + name_list = communication_op.get("name", "").split("_") + if len(name_list) >= 2: + self._communication_task_data.setdefault(name_list[1].lower(), []).append(data) + break + self._communication_data, self._communication_task_data = [], {} json_data = FileReader.read_trace_file(self._json_path) - pid = None - for data in json_data: - trace_event = TraceEventData(data) - if not trace_event.is_process_meta(): - continue - if trace_event.is_hccl_process(): - pid = trace_event.pid - break + + pid = get_pid(json_data) if pid is None: return - tid_list = [] - for data in json_data: - trace_event = TraceEventData(data) - if not trace_event.is_thread_meta(): - continue - if trace_event.pid != pid: - continue - if trace_event.is_communication_op_thread(): - tid_list.append(trace_event.tid) + tid_list = [] + get_tid_list(pid, tid_list, json_data) if not tid_list: return - for data in json_data: - trace_event = TraceEventData(data) - if not trace_event.is_x_mode(): - continue - if trace_event.pid != pid: - continue - if trace_event.tid in tid_list: - self._communication_data.append(data) + get_comm_data(pid, tid_list, json_data) if not self._communication_data: return - for data in json_data: - trace_event = TraceEventData(data) - if not trace_event.is_x_mode(): - continue - if trace_event.pid != pid: - continue - if trace_event.tid in tid_list: - continue - ts = trace_event.start_time - for communication_op in self._communication_data: - comm_op_event = TraceEventData(communication_op) - if ts < comm_op_event.start_time or ts > comm_op_event.end_time: - continue - name_list = communication_op.get("name", "").split("_") - if len(name_list) >= 2: - self._communication_task_data.setdefault(name_list[1].lower(), []).append(data) - break + + get_comm_task_data(pid, tid_list, json_data) diff --git a/profiler/compare_tools/utils/tree_builder.py b/profiler/compare_tools/utils/tree_builder.py index 6d765eb0d70b2c58e14c52ff66c09598d4ef2061..4010ba0c8855054f5c445ae1f9b41d8ab287b6f6 100644 --- a/profiler/compare_tools/utils/tree_builder.py +++ b/profiler/compare_tools/utils/tree_builder.py @@ -22,6 +22,16 @@ class TreeBuilder: @classmethod def update_tree_node(cls, root_node: TorchOpNode, flow_kernel_dict: dict = {}, memory_allocated_list: list = []): + def set_kernel_helper(node_queue, ts, kernel_num, kernel_list): + while not node_queue.empty(): + tree_node = node_queue.get() + tree_node.add_kernel_num(kernel_num) + matched_child_node = tree_node.match_child_node(ts) + if matched_child_node: + node_queue.put(matched_child_node) + else: + tree_node.set_kernel_list(kernel_list) + if flow_kernel_dict: for ts, kernel_list in flow_kernel_dict.items(): matched_child_node = root_node.match_child_node(ts) @@ -30,14 +40,8 @@ class TreeBuilder: kernel_num = len(kernel_list) node_queue = Queue() node_queue.put(matched_child_node) - while not node_queue.empty(): - tree_node = node_queue.get() - tree_node.add_kernel_num(kernel_num) - matched_child_node = tree_node.match_child_node(ts) - if matched_child_node: - node_queue.put(matched_child_node) - else: - tree_node.set_kernel_list(kernel_list) + set_kernel_helper(node_queue, ts, kernel_num, kernel_list) + for memory_allocated in memory_allocated_list: ts = memory_allocated.get(Constant.TS) matched_child_node = root_node.match_child_node(ts)