NoC Topology & QoS: Review Checklist

Review checklist

Review Checklist for NoC Topology & QoS focuses on fabric latency p99, starvation incidents, QoS target hit-rate. The goal is to map symptoms to boundary contracts, owner actions, and regression-proof closure.

• Baseline manifest and revision are explicit.

• Boundary contracts for this topic are current and approved.

• Ownership map covers all open issues.

• Focused and full regression evidence both exist.

• Residual risks are either closed or bounded via waiver policy.

• Owners signed: NoC architect, performance owner, integration owner.

Signoff ownership

OWNERSHIP MAP — NoC Topology & QoS

artifact             owner
-----------------    -----------------
primary owner     NoC architect
co-owner          performance owner
review owner      integration owner

No top-level issue should remain ownerless beyond one review cycle.

SoC deep dive

Fabric correctness and contention behavior must be proven together.

Concept diagram

FABRIC FLOW
masters -> routers/VCs -> slaves + memory

Metric graph

LATENCY TAIL
p50 ███
p95 ██████
p99 ██████████

Reports and artifacts

• NoC contention heatmap

• ordering violation report

• QoS fairness summary

• protocol trace

Mini case study

Bandwidth looked fine at average load, but p99 tail violated SLA due to arbitration starvation.

Debug branches

• Isolate traffic class

• Check ordering assumptions

• Audit arbitration policy

Senior review question

Ask: what baseline, owner, and artifact prove this topic is truly closed?

Key takeaways

• State baseline manifest and owner with every closure metric.

• Run cross-domain regression after every top-level fix.

Common pitfalls

• Comparing results across different manifests.

• Unowned issues slipping through review cycles.

• Waiving risks without expiry and validation plan.

Principal SoC review addendum

NoC topology, virtual channels, and QoS policies shape contention behavior under mixed traffic and determine predictable latency.

Metric: fabric latency p99, starvation incidents, QoS target hit-rate