| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
refactor: 迁移 StanfordBench 到 bench_lab/stanford_bench，移除 thirdparty 目录 Co-authored-by: Developer user<suyueming@huawei.com> # message auto-generated for no-merge-commit merge: !124 merge master into master refactor: 迁移 StanfordBench 到 bench_lab/stanford_bench，移除 thirdparty 目录 Created-by: su-yueming Commit-by: Developer user Merged-by: cann-robot Description: ## 变更描述 / Description 1. baseline 数据迁移 - 将 tasks/ 和 bench_lab/ 下所有 cases.yaml 中的 baseline_perf_us/t_hw_us 字段剥离，数据集中存储到各评测集 metadata/910b2.json - 删除 data/stanford_baseline.json，StanfordBench baseline 改由 bench_lab/stanford_bench/metadata/910b2.json 加载 - 新增 scripts/migrate_baseline_to_data.py 迁移工具脚本 2. src 代码变更 - __init__.py: 版本号改为动态读取（_version.py → VERSION 文件） - perf_strategy.py: KernelDetailsStrategy 以 kernel_details.csv 为唯一权威源， 不再 fallback 到 trace_view；TraceViewStrategy 标注待收编 - cann_loader.py: 集成 BaselineStore，baseline 优先从 JSON 查询 - stanford_loader.py: baseline 改由 BaselineStore 加载，移除 _load_baseline - report 模块: 微调 HTML/MD 报告和 setup_info 输出 3. 新增文件 - tasks/metadata/910b2.json + VERSION - bench_lab/*/metadata/910b2.json (cv_agent_bench, kernel_bench, pypto_cann_bench, stanford_bench) - pyproject.toml, VERSION (根目录), _version.py, test_version_consistency.py - docs/design/micro_benchmark_selection.md, module_panorama.md - docs/guide/version_policy.md 4. tests 更新 - test_benchmark_pipeline: 适配 baseline 迁移 - test_cases_yaml_csv_consistency: 新增 metadata JSON 与 cases.yaml 一致性校验 - test_version_consistency: 版本号一致性测试 1. 新增 PLATFORM_ALIAS 和 resolve_hardware() - 在 baseline_resolver.py 中添加产品型号→逻辑名映射表 - 支持精确匹配（Ascend910_9362 → 910b2）和前缀匹配（Ascend310P* → 310p） - 最长前缀优先，避免短 key 误匹配 - BaselineStore/BaselineResolver/__init__ 统一调用 resolve_hardware - has_baseline_for/resolve_baseline_us 内部自动解析硬件名 - 导出 resolve_hardware 和 PLATFORM_ALIAS 至 utils/__init__.py 2. 将 examples/eval_task → examples/tasks - 按 tasks/ 结构重构：add → level2/add, sqrt → level1/sqrt - 新增 metadata/910b2.json（fixture baseline，值均为 0.0 placeholder） - 新增 metadata/VERSION - 新增 cases.csv（与生产 tasks 格式一致） - 重写 README.md（目录结构、路径引用） - 更新 docs/guide/quick_start.md 和根 README.md 的路径引用 - 删除旧 examples/eval_task/ 目录 - 移动 scripts/download_benchmarks.sh → bench_lab/stanford_bench/download.sh， 下载目标从 thirdparty/KernelBench 改为 bench_lab/stanford_bench/KernelBench 将 direct_launch_example 从仅支持 910B 扩展为支持多种 SOC， 与 aclnn_launch_example 的多 SOC 能力对齐。 <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> [#31](https://gitcode.com/cann/cann-bench/issues/31) ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [x] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/cann-bench!124 | 1 个月前 | |
refactor: 迁移 StanfordBench 到 bench_lab/stanford_bench，移除 thirdparty 目录 Co-authored-by: Developer user<suyueming@huawei.com> # message auto-generated for no-merge-commit merge: !124 merge master into master refactor: 迁移 StanfordBench 到 bench_lab/stanford_bench，移除 thirdparty 目录 Created-by: su-yueming Commit-by: Developer user Merged-by: cann-robot Description: ## 变更描述 / Description 1. baseline 数据迁移 - 将 tasks/ 和 bench_lab/ 下所有 cases.yaml 中的 baseline_perf_us/t_hw_us 字段剥离，数据集中存储到各评测集 metadata/910b2.json - 删除 data/stanford_baseline.json，StanfordBench baseline 改由 bench_lab/stanford_bench/metadata/910b2.json 加载 - 新增 scripts/migrate_baseline_to_data.py 迁移工具脚本 2. src 代码变更 - __init__.py: 版本号改为动态读取（_version.py → VERSION 文件） - perf_strategy.py: KernelDetailsStrategy 以 kernel_details.csv 为唯一权威源， 不再 fallback 到 trace_view；TraceViewStrategy 标注待收编 - cann_loader.py: 集成 BaselineStore，baseline 优先从 JSON 查询 - stanford_loader.py: baseline 改由 BaselineStore 加载，移除 _load_baseline - report 模块: 微调 HTML/MD 报告和 setup_info 输出 3. 新增文件 - tasks/metadata/910b2.json + VERSION - bench_lab/*/metadata/910b2.json (cv_agent_bench, kernel_bench, pypto_cann_bench, stanford_bench) - pyproject.toml, VERSION (根目录), _version.py, test_version_consistency.py - docs/design/micro_benchmark_selection.md, module_panorama.md - docs/guide/version_policy.md 4. tests 更新 - test_benchmark_pipeline: 适配 baseline 迁移 - test_cases_yaml_csv_consistency: 新增 metadata JSON 与 cases.yaml 一致性校验 - test_version_consistency: 版本号一致性测试 1. 新增 PLATFORM_ALIAS 和 resolve_hardware() - 在 baseline_resolver.py 中添加产品型号→逻辑名映射表 - 支持精确匹配（Ascend910_9362 → 910b2）和前缀匹配（Ascend310P* → 310p） - 最长前缀优先，避免短 key 误匹配 - BaselineStore/BaselineResolver/__init__ 统一调用 resolve_hardware - has_baseline_for/resolve_baseline_us 内部自动解析硬件名 - 导出 resolve_hardware 和 PLATFORM_ALIAS 至 utils/__init__.py 2. 将 examples/eval_task → examples/tasks - 按 tasks/ 结构重构：add → level2/add, sqrt → level1/sqrt - 新增 metadata/910b2.json（fixture baseline，值均为 0.0 placeholder） - 新增 metadata/VERSION - 新增 cases.csv（与生产 tasks 格式一致） - 重写 README.md（目录结构、路径引用） - 更新 docs/guide/quick_start.md 和根 README.md 的路径引用 - 删除旧 examples/eval_task/ 目录 - 移动 scripts/download_benchmarks.sh → bench_lab/stanford_bench/download.sh， 下载目标从 thirdparty/KernelBench 改为 bench_lab/stanford_bench/KernelBench 将 direct_launch_example 从仅支持 910B 扩展为支持多种 SOC， 与 aclnn_launch_example 的多 SOC 能力对齐。 <!-- 本 PR 做了什么，为什么需要 / What does this PR do and why --> [#31](https://gitcode.com/cann/cann-bench/issues/31) ## 改动类型 / Change Type - [ ] Bug 修复 / Bug Fix - [ ] 新功能 / New Feature - [ ] 性能优化 / Performance - [x] 代码重构 / Refactoring - [ ] 文档更新 / Documentation - [ ] 测试相关 / Test - [ ] 其它 / Other ## 关联 Issue / Related Issues <!-- Closes #000 可自动关闭 / Closes #000 to auto-close --> - Closes # - References # ## 测试信息 / Testing <!-- 简要测试说明或关键结果 / Brief test description or key results --> - [ ] 单元测试通过 / UT passed - [ ] 集成测试通过 / ST passed - [ ] 人工验证通过 / Manual verified ## 检查清单 / Checklist - [ ] 代码符合规范 / Code follows style guide - [ ] 测试添加并通过 / Tests added and passed - [ ] 文档已更新 / Docs updated if needed - [ ] 无硬编码敏感信息 / No secrets hardcoded - [ ] 提交信息符合规范 / Commit message follows convention See merge request: cann/cann-bench!124 | 1 个月前 | |
docs: add 支持范围 to remaining level1-4 operator descriptors Co-authored-by: gxj1123<gao.xuejian1@huawei.com> # message auto-generated for no-merge-commit merge: !63 merge docs/support-ranges-l1-4 into master docs: add 支持范围 to remaining level1-4 operator descriptors Created-by: gxj1123 Commit-by: gxj1123 Merged-by: cann-robot Description: Sweeps desc.md across **53 operator entries** (L1–4), adding a **支持范围** (supported-range) section plus the related **约束** (input restrictions) paragraphs. ### Coverage - **level1** (8 ops): exp, foreach_addcdiv_scalar, foreach_norm, gelu, masked_scale, mish, sigmoid, swi_glu - **level2** (16 ops): apply_adam_w, apply_rotary_pos_emb, arg_max, cross_entropy_loss, cummin, dynamic_quant, gather, gcd, grid_sampler_3d, group_norm, maximum, resize_bilinear, rms_norm, scatter, softmax, unsorted_segment_sum - **level3**: adaptive_avg_pool_3d, add_rms_norm_dynamic_quant, conv_2d, conv_3d_backprop_filter, depthwise_conv_2d, dequant_swiglu_quant, dilation_2d, engram_gate_fusion, grouped_matmul, mhc_sinkhorn, moe_finalize_routing, moe_gating_top_k_softmax, moe_re_routing, nms, quant_matmul, roi_align, strided_slice, top_k, transpose, unique, weight_quant_batch_matmul - **level4**: gqa, grouped_matmul_swiglu_quant, gru, lstm, mha, mla, mla_prolog, sparse_flash_attention For L4 attention ops the supported range is intentionally tightened to match the kernel templates that are actually compiled in CANN 9.0.0-beta.2 (MLA-only template — attention_mode=2 + rope=64 + qk_dim=512 + Nkv=1 path). Other parameter combinations are listed as "not supported in current release". Pure documentation; no code, no cases, no proto changes. **53 files, +1012 / -45.** See merge request: cann/cann-bench!63 | 2 个月前 | |
fix(level3/moe): add expert_id bounds-check to guard sentinel tokens Co-authored-by: machengdi123<machengdi@huawei.com> # message auto-generated for no-merge-commit merge: !79 merge fix/moe-expert-idx-sentinel into master fix(level3/moe): add expert_id bounds-check to guard sentinel tokens Created-by: machengdi123 Commit-by: machengdi123 Merged-by: cann-robot Description: ### Summary - moe_gating_top_k_softmax/golden.py — document that num_expert (== E, out-of-range) is used as a sentinel for finished tokens, not a valid expert index; downstream consumers must handle this contract - moe_finalize_routing/golden.py — add bounds check 0 <= expert_id < num_experts before bias[expert_id, :]; sentinel/finished tokens skip the bias term and contribute the unbiased value, preventing out-of-bounds reads See merge request: cann/cann-bench!79 | 2 个月前 | |
fix(tasks): proto.yaml consistency — drop_pad_mode int default, dilation_2d float type signaling Co-authored-by: gxj1123<gao.xuejian1@huawei.com> # message auto-generated for no-merge-commit merge: !70 merge fix/tasks-proto-consistency into master fix(tasks): proto.yaml consistency — drop_pad_mode int default, dilation_2d float type signaling Created-by: gxj1123 Commit-by: gxj1123 Merged-by: cann-robot Description: **4 proto.yaml files, +8 / -8.** Static-only changes to operator descriptors; no golden / cases / runtime code touched. - level3/moe_finalize_routing/proto.yaml: drop_pad_mode default "0" (string) → 0 (int) — type-correct now matches the int attr. - level3/moe_gating_top_k_softmax/proto.yaml: same kind of fix. - level3/moe_re_routing/proto.yaml: same kind of fix. - level3/dilation_2d/proto.yaml: float-type signaling normalization for the dilation attr (was being emitted as bare integer when fractional dilation is supported by the underlying API). See merge request: cann/cann-bench!70 | 2 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 1 个月前 | ||
| 1 个月前 | ||
| 2 个月前 | ||
| 2 个月前 | ||
| 2 个月前 |