Skip to content

Ascend/msagent / skills/operator/ops-performance-tuning

ops-performance-tuning

Verified

Compile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures.

FileKindSize
SKILL.mdskill md15.4 KB
evals/evals.jsonconfig3.6 KB
references/case-routing.mdmarkdown30.0 KB
references/cases/ascendc/pr_ascendc_allgathermm_scalar_align.mdmarkdown1.7 KB
references/cases/ascendc/pr_ascendc_cann_samples_perf_story.mdmarkdown3.9 KB
references/cases/ascendc/pr_ascendc_cgdr_vf_inverse.mdmarkdown1.6 KB
references/cases/ascendc/pr_ascendc_conv3ddx_tque_tbuf.mdmarkdown1.6 KB
references/cases/ascendc/pr_ascendc_layernorm_areg.mdmarkdown1.6 KB
references/cases/ascendc/pr_ascendc_logit_a5_microapi.mdmarkdown1.9 KB
references/cases/ascendc/pr_ascendc_matmul_case_18x.mdmarkdown1.5 KB
references/cases/ascendc/pr_ascendc_matmul_full_load_wiki.mdmarkdown1.6 KB
references/cases/ascendc/pr_ascendc_matmul_vcv_wiki.mdmarkdown1.8 KB
references/cases/ascendc/pr_ascendc_mc2_fusion.mdmarkdown1.4 KB
references/cases/ascendc/pr_ascendc_mhc_24x.mdmarkdown1.2 KB
references/cases/ascendc/pr_ascendc_msopprof_add_block_imbalance.mdmarkdown1.7 KB
references/cases/ascendc/pr_ascendc_quantize_a2_micro_opt.mdmarkdown2.0 KB
references/cases/ascendc/pr_ascendc_rotate_quant_blaze.mdmarkdown2.8 KB
references/cases/ascendc/pr_ascendc_tiling_l2_official.mdmarkdown1.6 KB
references/cases/catlass/pr_catlass_baseline.mdmarkdown1.3 KB
references/cases/catlass/pr_catlass_fixpipe_dualdst.mdmarkdown1.6 KB
references/cases/catlass/pr_catlass_grouped_matmul_tiling.mdmarkdown1.5 KB
references/cases/catlass/pr_catlass_mstuner_3p8x.mdmarkdown1.9 KB
references/cases/catlass/pr_catlass_swizzle_balance.mdmarkdown1.6 KB
references/cases/pypto/pr_pypto_gqa_decode_vector_merge.mdmarkdown2.4 KB
references/cases/pypto/pr_pypto_l2_hit_layout_s13.mdmarkdown1.9 KB
references/cases/pypto/pr_pypto_per_matmul_tile_shapes.mdmarkdown2.4 KB
references/cases/pypto/pr_pypto_small_shape_matmul.mdmarkdown2.3 KB
references/cases/pypto/pr_pypto_weight_none_cacheable.mdmarkdown2.6 KB
references/cases/shmem/pr_shmem_alltoallv_mr152.mdmarkdown2.4 KB
references/cases/shmem/pr_shmem_reduce_scatter_serial.mdmarkdown2.6 KB
references/cases/tilelang/pr_tilelang_benchmark_vs_ascendc.mdmarkdown1.7 KB
references/cases/tilelang/pr_tilelang_compiler_prs.mdmarkdown2.3 KB
references/cases/tilelang/pr_tilelang_fa_pr698.mdmarkdown1.5 KB
references/cases/tilelang/pr_tilelang_gqa_bwd_pr1494.mdmarkdown1.3 KB
references/cases/tilelang/pr_tilelang_persistent_mqa_decode.mdmarkdown2.2 KB
references/cases/tilelang/pr_tilelang_sfa_pr665.mdmarkdown914 B
references/cases/triton/pr_triton_atomic_simd_24x.mdmarkdown1.8 KB
references/cases/triton/pr_triton_autotune_background.mdmarkdown1.0 KB
references/cases/triton/pr_triton_constexpr_recompile.mdmarkdown1.1 KB
references/cases/triton/pr_triton_lgamma_simt.mdmarkdown1.6 KB
references/compile/compile-ascendc.mdmarkdown9.0 KB
references/compile/compile-catlass.mdmarkdown2.4 KB
references/compile/compile-pypto.mdmarkdown2.0 KB
references/compile/compile-shmem.mdmarkdown2.6 KB
references/compile/compile-tilelang.mdmarkdown2.7 KB
references/compile/compile-triton.mdmarkdown4.4 KB
references/diagnose/diagnose-l2-cache.mdmarkdown2.2 KB
references/diagnose/diagnose-occupancy.mdmarkdown4.0 KB
references/diagnose/diagnose-pipeline.mdmarkdown4.1 KB
references/diagnose/diagnose-roofline.mdmarkdown3.1 KB
references/optimize/optimize-api-usage.mdmarkdown1.7 KB
references/optimize/optimize-ascendc-regbase-vf.mdmarkdown5.9 KB
references/optimize/optimize-ascendc-tiling.mdmarkdown935 B
references/optimize/optimize-catlass.mdmarkdown3.0 KB
references/optimize/optimize-data-copy.mdmarkdown870 B
references/optimize/optimize-index.mdmarkdown3.6 KB
references/optimize/optimize-memory-hierarchy.mdmarkdown599 B
references/optimize/optimize-pipeline.mdmarkdown1.0 KB
references/optimize/optimize-pypto.mdmarkdown1.5 KB
references/optimize/optimize-shmem.mdmarkdown5.1 KB
references/optimize/optimize-tilelang.mdmarkdown1.7 KB
references/optimize/optimize-triton.mdmarkdown3.8 KB
references/profile/benchmark-harness.mdmarkdown2.2 KB
references/profile/profile-msopprof.mdmarkdown7.4 KB
references/troubleshooting.mdmarkdown5.8 KB
scripts/bound_analyzer.pyscript9.0 KB
scripts/delta_report.pyscript4.8 KB
scripts/env_check.shscript5.0 KB
scripts/result_saver.pyscript5.0 KB

references/cases/pypto/pr_pypto_small_shape_matmul.md

View on GitHub
# 小 Shape 矩阵乘:Vector 预处理构造标准 Shape(优化点 I-1)

## 基本信息
- 算子类别:matmul
- DSL/框架:pypto
- 类型:非PR(内部案例库,cannbot-skills 官方调优案例库)
- 来源可信度:官方文档(cann/cannbot-skills 仓 `ops/pypto-op-perf-tune`;属核内调优 PHASE_INCORE 阶段,优先级 ⭐⭐⭐ P0)

## 链接
- PR/出处链接:https://gitcode.com/cann/cannbot-skills/blob/master/ops/pypto-op-perf-tune/tune-incore/SKILL.md(§1.1)( 已验证可达,验证日期 2026-08);另见 https://gitcode.com/cann/cannbot-skills/blob/master/ops/pypto-op-perf-tune/shared/optimization_catalog.md([I-1] 条目)( 已验证可达,验证日期 2026-08)
- 优化代码查看:非代码 MR 类案例,无 diff/files 页;上述出处链接原文内含关键代码片段(见下)

## 问题与瓶颈
左右矩阵 Shape 分别为 (884736, 16) 和 (16, 16) 的矩阵乘——M 极大、K/N 极小,Cube 单元无法在如此小的 K/N 上有效流水。

## 优化方法(理论手段)
用 Vector 操作提前处理输入矩阵,通过 `concat`/`reshape` 构造标准 Shape——将 4 个重复的右矩阵与零矩阵在对角线拼成 (64, 64),左矩阵 reshape 为 (221184, 64),再做一次标准 matmul 后 reshape/assemble 回原形状。关键代码:

```python
pypto.set_vec_tile_shapes(64, 64)
d = pypto.full([16, 16], 0.0, pypto.DT_BF16)
c = pypto.concat([...b 与 d 对角拼接...], 0)   # (16,16) → (64,64)
a = pypto.reshape(a, [221184, 64])
pypto.set_pass_options(cube_l1_reuse_setting={-1: 9})
pypto.set_cube_tile_shapes([512, 512], [64, 64], [64, 64], True)
e = pypto.matmul(a, c, pypto.DT_BF16)
```

机制:Cube 单元按 16×16 分形工作,K=N=16 时每次 MMAD 的有效计算占比极低、流水无法展开;把多个小右矩阵沿对角拼成大矩阵后,一次标准 Shape 的 matmul 即可等价完成原计算,Cube 利用率大幅提升;配合 `cube_l1_reuse_setting` 提升 L1 复用。

## 性能对比
| 指标 | 优化前 | 优化后 | 变化 |
|---|---|---|---|
| 耗时 | 500 us | 40 us | 约 12.5 倍提升 |

## 适用范围与警示
- 适用:M 极大、K/N 极小的小 shape 矩阵乘,Cube 流水无法展开的场景。
- 警示:需保证对角拼接的等价性(右矩阵可重复语义);优先级 ⭐⭐⭐ P0,属核内调优阶段手段。
planning-and-task-breakdownaddyosmani/agent-skillsBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
screenpipethedotmack/claude-memSearch screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
contact-widgetnexu-io/open-designSelf-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.Stars: 108kUpdated Claude CodeCodexVerifiedInstall
meeting-notesnexu-io/open-designMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a "next meeting" footer. Use when the brief mentions "meeting notes", "minutes", "1:1 notes", "all-hands recap", or "会议纪要".Stars: 108kUpdated Claude CodeCodexVerifiedInstall