DenseChip

AI for VLSI · All levels

ML for Yield & Manufacturing: Debug Playbook

Debug Playbook for ML for Yield & Manufacturing.

Debug playbook

Debug Playbook for ML for Yield & Manufacturing focuses on yield excursion detection precision, false alarm rate, and root-cause turnaround. The goal is to connect model behavior to hardware-aware decisions and operational risk.

AI-VLSI debug is layer-first. Find the first failing layer and avoid random tuning before proving mechanism.

Root-cause tree

diagram
ROOT-CAUSE TREE — ML for Yield & Manufacturing

yield excursion detection precision, false alarm rate, and root-cause turnaround regressed
        |
   data/model drift?
     /             \
   yes              no
   |                 |
dataset / labels   runtime / hardware / mapping
check leakage      check bandwidth, precision,
and split policy   scheduling, implementation

Always isolate first failing layer before fixes.

  1. Freeze dataset, model, runtime, and hardware revision tags.

  2. Isolate first failing workload slice and metric shift.

  3. Classify issue: data drift, model behavior, runtime mismatch, or hardware bottleneck.

  4. Prove hypothesis with one reduced reproducible experiment.

  5. Patch smallest owner-controlled fix.

  6. Re-run full quality + performance + stability validation.

Review memo template

diagram
AI-VLSI REVIEW MEMO — AI in VLSI Workflows / ML for Yield & Manufacturing

1. Symptom
   - Watched metric: yield excursion detection precision, false alarm rate, and root-cause turnaround
   - Failing workload slice: <name>
   - Failing layer: <data/model/runtime/hardware>
   - Revision tags: <dataset, model, runtime, hardware>

2. Mechanism hypothesis
   - Primary mechanism: Statistical and ML models detect anomaly patterns in fab/test telemetry, enabling earlier diagnosis and corrective actions.
   - Competing hypotheses: <data drift, optimization bug, mapping bottleneck>
   - Missing evidence: <profile, calibration, signoff correlation>

3. Proposed action
   - Minimal reversible change: <config/model/runtime/hardware tweak>
   - Expected movement: <quality/latency/power>
   - Regression risk: distribution shift, stack incompatibility, owner handoff

4. Signoff
   - Re-run artifact: yield anomaly dashboard, fab telemetry model report, and corrective-action tracker
   - Required owners: yield engineer, manufacturing data owner, quality lead
   - Final decision: ship, rollback, bounded pilot, or escalate

AI-VLSI deep dive

EDA ML must prove signoff-correlated value with bounded risk and clear ownership.

Concept diagram

diagram
EDA ML GOVERNANCE

baseline flow -> ML assist -> confidence gate -> signoff confirmation

Metric graph

diagram
TRUST TREND

runtime gain            ███████
signoff correlation     ██████
false alarm rate        ███

Reports and artifacts

  • correlation-to-signoff

  • runtime savings dashboard

  • false-prediction audit

  • fallback decision log

Mini case study

A model improved placement runtime, but confidence gating avoided a high-cost false optimization suggestion.

Debug branches

  • Tie model output to signoff artifact

  • Audit confidence calibration

  • Preserve deterministic fallback

Senior review question

Ask: what evidence connects this ML claim to a concrete VLSI workflow decision and owner signoff?

Key takeaways

  • Every AI claim should map to a measurable engineering outcome.

  • Validate both model quality and hardware/runtime feasibility before adoption.

Common pitfalls

  • Optimizing benchmark metrics that do not correlate with signoff goals.

  • Ignoring data drift and calibration after deployment.

  • Shipping ML workflows without clear rollback ownership.

Execution drill pack 1

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 1

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 2

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 2

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 3

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 3

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 4

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 4

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 5

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 5

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 6

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 6

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 7

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 7

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 8

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 8

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 9

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 9

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 10

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 10

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 11

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 11

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 12

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 12

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Execution drill pack 13

Use this pack to rehearse AI-for-VLSI decision making on ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook: metric framing, mechanism proof, hardware implications, and release safety.

Evidence checklist

  • Metric context includes workload, dataset slice, and revision tags.

  • Mechanism explanation links model behavior to observed outcome.

  • Hardware/runtime feasibility is profiled, not assumed.

  • Owner and rollback path are documented before rollout.

Review prompts

  1. Which decision will this model output influence?

  2. What is the first failing layer when metric regresses?

  3. Which owner applies the smallest reversible fix?

  4. What validation matrix is required before deployment?

Evidence capsule

diagram
AI-VLSI EVIDENCE CAPSULE 13

PATH: ai-vlsi/ai-in-vlsi-workflows/ml-yield-and-manufacturing/debug-playbook
WORKLOAD SLICE: <name>
PRIMARY METRIC: <value/trend>
FIRST FAILING LAYER: <data/model/runtime/hardware>
OWNER: <name>
PRIMARY ARTIFACT: <report/profile/dashboard>
DECISION: <ship / rollback / escalate>

Principal AI-VLSI review addendum

Statistical and ML models detect anomaly patterns in fab/test telemetry, enabling earlier diagnosis and corrective actions.

Metric: yield excursion detection precision, false alarm rate, and root-cause turnaround

Practice this lesson