x5-performance-diagnostics
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
关联 X5 hb_perf 静态估计、Runtime 实测、BPU ratio、温度频率和 CPU/I/O 开销以定位性能瓶颈;当模型太慢、静态与板端差异大或 BPU 利用率异常时使用。默认只读,不自动改 O3、core、频率或系统进程。
In this repository59 other files it gives its agents.
- bsp-bootloader-buildSkill
- bsp-deb-buildSkill
- bsp-env-setupSkill
- bsp-image-buildSkill
- bsp-kernel-buildSkill
- bsp-rootfs-customSkill
- bsp-source-syncSkill
- bsp-s-seriesSkill
- hmct-workflowSkill
- horizon-routerSkill
- ucpSkill
- x5-accuracy-diagnosticsSkill
- x5-board-monitorSkill
- x5-bpu-python-apiSkill
- x5-calibration-data-prepareSkill
- x5-consistency-diagnosticsSkill
- x5-environment-installSkill
- x5-environment-probeSkill
- x5-environment-setupSkill
- x5-model-diagnosticsSkill
- x5-model-preflightSkill
- x5-ptq-compileSkill
- x5-ptq-config-authoringSkill
- x5-ptq-deploySkill
- x5-qat-adaptationSkill
- x5-qat-compileSkill
- x5-qat-deploySkill
- x5-qat-trainingSkill
- x5-routerSkill
- x5-runtime-cpp-inferSkill
- x5-runtime-deploySkill
- x5-runtime-perf-evalSkill
- rdk-accessoriesSkill
- rdk-board-delegateSkill
- rdk-board-knowledgeSkill
- rdk-camera-setupSkill
- rdk-command-manualSkill
- rdk-diagnosticSkill
- rdk-docs-referenceSkill
- rdk-ecosystemSkill
- rdk-embodied-lerobotSkill
- rdk-gpio-40pinSkill
- rdk-hardwareSkill
- rdk-headless-modeSkill
- rdk-llm-deploymentSkill
- rdk-log-forensicsSkill
- rdk-memory-auditSkill
- rdk-model-benchmarkSkill
- rdk-model-deploySkill
- rdk-model-zooSkill
- rdk-multimediaSkill
- rdk-network-remoteSkill
- rdk-peripheral-cookbookSkill
- rdk-source-mapSkill
- rdk-system-configSkill
- rdk-system-maintainSkill
- rdk-tros-setupSkill
- rdk-vision-pipelineSkill
- d-robotics-pack-installerSkill
The file
Files
X5 性能诊断
目标与边界
区分模型图/编译、Runtime 调度、CPU 前后处理、数据搬运、系统负载和热/频率限制。单一平均延时或 BPU ratio 不能独立证明根因。
输入合同
hb_perf/编译静态报告、板端原始延时、测试矩阵和模型哈希。board-resource.json、温度/频率、Runtime/镜像版本和后台负载。- 输入准备、后处理和计时边界说明。
前置检查
- 功能正确性已通过,测试输入和 warmup/重复次数一致。
- 静态估计与实测使用同一模型版本、core/batch 和输入 shape。
- 性能日志没有把上传、解码、后处理或日志打印混进 BPU 时间而未说明。
执行步骤
- 分解总延时:输入准备 → Runtime submit/wait → 输出回读 → 后处理。
- 对比静态 BPU 估计与实测 BPU 段;检查 CPU fallback、图切分和频繁小 function call。
- 关联 BPU ratio、温度、当前频率、DDR/内存和后台负载。
- 选一个受控实验:编译选项、core/batch、输入 source、前处理位置或 Runtime 调度,仅改变一项。
- 定义改善阈值、回归正确性检查和停止条件。
产物与完成标准
bottleneck-report将证据归类为模型/编译、Runtime、CPU/I/O 或系统资源。- 指标带命令、版本、模型哈希和测试口径。
- 给出一个优先实验及预期效果;没有证据时不建议盲目 O3/fast-perf。
风险与确认
分析为低风险。重新编译/长压测为中风险;调频、停止进程、修改电源策略为高风险并需明确确认。
失败与交接
编译配置 → x5-ptq-config-authoring;实测 → x5-runtime-perf-eval;资源采样 → x5-board-monitor。
按需参考
_sources/oe_mapper/source/tune_content/performance_tune.rst.txt_sources/oe_mapper/source/ptq/ptq_tool/hb_perf.rst.txt
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

