kali20gakki/msAgent / skills/operator/msdebug-basic-usage
msdebug-basic-usage
Verified昇腾AscendC算子调试工具(msDebug)技能,含两大流程:①上板调试——算子加 -g -O0 编译后由 msdebug 拉起,支持断点、单步、变量/内存打印、核切换、寄存器读取;②coredump解析——用户指定 core 文件路径后,msdebug 加载解析挂掉代码行/异常调用栈/现场变量。触发关键词:msdebug、算子调试、上板调试、断点、单步调试、打印变量、读内存、核切换、寄存器、coredump、core文件、调用栈、崩溃解析
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.3 KB |
| evals/evals.json | config | 11.8 KB |
| references/official_workflow.md | markdown | 11.6 KB |
| references/sample_coredump/CMakeLists.txt | markdown | 1.3 KB |
| references/sample_coredump/README.md | markdown | 8.5 KB |
| references/sample_coredump/add.asc | other | 6.8 KB |
| references/sample_coredump/data_utils.h | other | 2.7 KB |
| references/sample_coredump/scripts/gen_data.py | script | 2.1 KB |
| references/sample_coredump/scripts/verify_result.py | script | 3.8 KB |
| references/sample_debug/CMakeLists.txt | markdown | 1.2 KB |
| references/sample_debug/README.md | markdown | 11.3 KB |
| references/sample_debug/debug.asc | other | 4.4 KB |
references/sample_coredump/scripts/verify_result.py
View on GitHub# -------------------------------------------------------------------------
# This file is part of the MindStudio project.
# Copyright (c) 2026 Huawei Technologies Co.,Ltd.
#
# MindStudio is licensed under Mulan PSL v2.
# You can use this software according to the terms and conditions of the Mulan PSL v2.
# You may obtain a copy of Mulan PSL v2 at:
#
# http://license.coscl.org.cn/MulanPSL2
#
# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
# EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT,
# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
# See the Mulan PSL v2 for more details.
# -------------------------------------------------------------------------
#!/usr/bin/python3
# coding=utf-8
# ----------------------------------------------------------------------------------------------------------
# Copyright (c) 2026 Huawei Technologies Co., Ltd.
# This program is free software, you can redistribute it and/or modify it under the terms and conditions of
# CANN Open Software License Agreement Version 2.0 (the "License").
# Please refer to the License for details. You may not use this file except in compliance with the License.
# THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
# INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
# See LICENSE in the root of the software repository for the full text of the License.
# ----------------------------------------------------------------------------------------------------------
import argparse
import sys
import numpy as np
# 数值容差
_RTOL = 1e-4 # 相对误差上限
_ATOL = 1e-5 # 绝对误差上限
_ERROR_TOL = 1e-4 # 允许的最大错误比例
_REPORT_LIMIT = 101 # 差异条目打印上限
def _load_f32(path):
"""读取 float32 二进制文件,返回 1 维 ndarray。"""
with open(path, "rb") as fh:
return np.frombuffer(fh.read(), dtype=np.float32)
def _locate_mismatch(actual, expect):
"""返回 actual 与 expect 逐元素不匹配的下标(NaN 视作相等)。"""
close = np.isclose(actual, expect, rtol=_RTOL, atol=_ATOL, equal_nan=True)
return np.flatnonzero(np.logical_not(close))
def _print_one(idx, actual, expect):
"""打印某个下标处期望值/实际值与相对差。"""
a = float(actual[idx])
e = float(expect[idx])
rd = abs(a - e) / e if e != 0.0 else float("nan")
print("data index: %06d, expected: %-.9f, actual: %-.9f, rdiff: %-.6f"
% (idx, e, a, rd))
def compare_files(actual_path, expect_path):
"""比对两个文件,返回是否通过及错误比例。"""
actual = _load_f32(actual_path)
expect = _load_f32(expect_path)
bad = _locate_mismatch(actual, expect)
shown = 0
for idx in bad:
if shown >= _REPORT_LIMIT:
break
_print_one(idx, actual, expect)
shown += 1
total = expect.size
ratio = float(bad.size) / total if total else 0.0
print("error ratio: %.4f, tolerance: %.4f" % (ratio, _ERROR_TOL))
return ratio <= _ERROR_TOL, ratio
def main(argv=None):
parser = argparse.ArgumentParser(
description="compare two float32 binary result files (actual vs golden)")
parser.add_argument("actual", help="算子实际输出文件路径")
parser.add_argument("golden", help="期望结果文件路径")
args = parser.parse_args(argv)
try:
ok, _ = compare_files(args.actual, args.golden)
except Exception as exc: # noqa: BLE001 - 统一失败出口
print("[ERROR] %s" % exc)
return 1
if ok:
print("test pass!")
return 0
print("[ERROR] result error")
return 1
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |