QoS and Arbitration Policies — Extended Case Study

Extended case study

A review is called because a workload regresses after a QoS and Arbitration Policies change.

Background

A stable baseline existed until a NoC and Interconnect Architecture change improved one benchmark and regressed a product workload on QoS service-level compliance report.

Symptoms observed

• Regression in QoS service-level compliance report

• Sim vs silicon disagreement

• Pressure to revert or ship risk

Investigation timeline

1. Freeze tags

2. Reproduce

3. Cluster

4. Experiment

5. Validate

6. Memo

Root cause

A hidden assumption in QoS and Arbitration Policies failed under an unrepresented workload phase.

Fix and validation

• Capture per-class enqueue/dequeue traces at each hop.

• Measure grant age and longest wait per class.

• Correlate deadline misses with competing burst windows.

• Apply one bounded arbitration adjustment and replay workload.

• Check for downstream starvation or throughput collapse.

Lessons learned

• Workload coverage beats clever microarchitecture

• Every change needs rollback triggers

QOS VALIDATION SNAPSHOT
  class_rt_cpu_p99_cycles: 52 (target <= 60)
  class_dma_bw_gbps: 188 (target >= 175)
  class_io_jitter_p95_cycles: 14
  starvation_watchdog_hits: 3
  top_offender: dma_channel_4_long_burst
  mitigation: token_bucket_refill_tune + arbiter_age_bias

Architecture deep dive

NoC is a queueing system — bandwidth, latency, and deadlock are coupled.

Concept diagram

NoC TOPOLOGY SKETCH

CPU0 ──┐      ┌── LLC0 ── DRAM0
       R0 ─── R1
CPU1 ──┘      │
              R2 ─── R3 ── GPU/DMA
              │      │
             NPU    LLC1 ── DRAM1

Look for: hot links, cyclic dependencies, VC starvation, and tail latency.

Metric graph

LATENCY DISTRIBUTION

p50    ██████  32 ns
p90    ████████████  71 ns
p99    ████████████████████████  210 ns
p99.9  █████████████████████████████████  480 ns

Averages hide QoS failures.

Metrics and artifacts

• link utilization

• average latency by master

• retry/backpressure counts

• QoS violation log

Mini case study

Average latency looks fine but tail latency spikes for CPU coherent reads when GPU DMA runs. QoS and separate VCs fix the starvation without doubling link width.

Debug branches

• If deadlock, check credit loops and routing restrictions first.

• If latency tail long, inspect arbitration and buffer depth.

Senior review question

Ask: what single metric would prove this concept is working or failing on your workload?

Key takeaways

• Connect every architecture claim to a workload and measurable metric.

• State verification and PPA impact before proposing design changes.

Common pitfalls

• Feature-driven design without MPKI/IPC/bandwidth evidence.

• Ignoring coherency and NoC traffic in cache and accelerator sizing.

Study notes

Re-read this topic with one concrete workload.