AI Accelerator Whiteboard Framework

Whiteboard flow

1. Draw ingress -> mapping -> memory -> compute -> completion.
2. Mark failing metric and first mechanism loss.
3. Add dataflow and precision constraints.
4. Name proving artifact and owner.
5. End with bounded fix and rollback trigger.

Key takeaways

• Strong answers connect product symptoms to hardware and runtime mechanisms.

• Never skip ownership and rollback criteria in release decisions.

AI accelerator deep dive

Accelerator outcomes are cross-layer effects of mapping, memory behavior, and runtime policy.

Concept diagram

workload -> mapping -> memory and compute behavior -> SLA outcome

Metric graph

throughput / latency / perf-per-watt trend

Metrics and artifacts to collect

• throughput and latency profile

• power and thermal telemetry

• root-cause artifact packet

Mini case study

Freeze revisions and isolate first failing workload slice before optimization debate.

Debug branches

• Classify bottleneck

• Collect reproducible evidence

• Apply bounded fix

Senior review question

Ask: which first-principles bottleneck class explains the symptom, and what artifact proves it reproducibly?

Key takeaways

• Tie every accelerator claim to a reproducible workload slice and one primary metric trend.

• Prefer bounded fixes with clear owner and rollback boundary over broad tuning bundles.

Common pitfalls

• Optimizing synthetic kernels without production-shape validation.

• Reading average latency while ignoring p95 and p99 behavior.

• Declaring sparse or precision wins without fallback and quality evidence.