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_weight_none_cacheable.md

View on GitHub
# 权重矩阵批量 NONE_CACHEABLE(Pangu 7B Fused Layer,优化点 I-2)

## 基本信息
- 算子类别:misc
- 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` 调优案例库,含 5 轮迭代失败分析与实测数字)

## 链接
- PR/出处链接:https://gitcode.com/cann/cannbot-skills/blob/master/ops/pypto-op-perf-tune/tune-incocases/weight-none-l2-cacheable.md( 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-2] 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;出处链接即为案例原文,内含完整优化前后代码与迭代记录

## 问题与瓶颈
Pangu 7B 单 Kernel 融合 Layer 算子(7 个 matmul + 2 个 RMSNorm + softmax + SwiGLU,Decode M=1,目标 ≤400us),经前端+泳道图调优后降至 437.28us 进入瓶颈。算子含 5 个只读一次的大型 BF16 权重矩阵(qkv 50MB / o 33MB / gate 25MB / up 25MB / down 50MB,合计约 183MB)。属核内调优(PHASE_INCORE)阶段案例。

## 优化方法(理论手段)
对 5 个权重**同时**设置 `tensor.set_cache_policy(pypto.CachePolicy.NONE_CACHEABLE, True)`,使其访问绕过 L2 Cache 直接访问 HBM。机制:

1. 只读一次、不复用的常量权重没有进 L2 的必要——L2 命中率为零却污染 Cache;
2. **融合算子中必须批量设置**:单独绕过某个权重会打破 L2 平衡,导致其他权重访问变慢(案例 5 轮迭代的核心教训);全部绕过才能把 L2 容量释放给 KV Cache 等真正频繁访问的数据;
3. 输入/输出 Tensor 不适合 NONE_CACHEABLE:输入数据量小、硬件预取已足够;输出需写回主存,绕过 L2 增加写回延迟;
4. Cache 策略效果高度依赖数据访问模式与硬件状态,无法仅凭理论判断,必须逐个实测验证(简单算子场景)。

## 性能对比
| 指标 | 优化前 | 优化后 | 变化 |
|---|---|---|---|
| 耗时 | 437.28 us | 354 us | -19.1% |

## 适用范围与警示
- 适用:含只读一次、不复用的大型常量权重矩阵的融合算子(如 Pangu 7B Fused Layer)。
- 警示:融合算子中必须批量设置,单独绕过某个权重会打破 L2 平衡导致其他权重访问变慢(5 轮迭代的核心教训);输入/输出 Tensor 不适合 NONE_CACHEABLE;Cache 策略效果高度依赖数据访问模式与硬件状态,必须逐个实测验证。
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