Computer Architecture · All levels

Cache Debug and Coherency Triage — Debug Playbook

Debug Playbook for Cache Debug and Coherency Triage (Memory Hierarchy).

On-call / interview prompt

Cache Debug and Coherency Triage looks wrong — walk your first five debug steps.

diagram

ARCHITECTURE ANALYSIS CHAIN

1. METRIC     — IPC, CPI, MPKI, bandwidth, latency, queue depth, stall cycles
2. HYPOTHESIS — microarch or system cause ordered by likelihood
3. EXPERIMENT — trace, PMU counter, simulation, or RTL probe
4. CHANGE      — pipeline, cache, NoC, or memory hierarchy adjustment
5. VALIDATION  — workload replay, regression suite, PPA impact

Reference workflow

diagram

1. Reproduce on controlled firmware build with fixed power-state sequence.
2. Capture coherence transaction traces around first replay storm onset.
3. Validate protocol invariants (single owner, ordering, ack completion) against logs.
4. Compare affected and unaffected clusters for state-machine divergence.
5. Deploy minimal fix and rerun power-transition regression plus long soak.

Mechanism to narrate

Separate symptom from root cause
Fix systematic clusters before one-offs

Common pitfalls

Random optimization without metric
Skipping regression after local fix

Staff-level debug discipline

For Cache Debug and Coherency Triage, senior debug is branch-and-bound: reduce the search space quickly, keep experiments reversible, and avoid hiding a systematic issue behind one local fix.

Debug decision tree

Reproduce the failure with the same workload, model tag, seed, and counter setup.
Classify the failure as workload issue, model issue, microarchitecture issue, software issue, implementation issue, or true product limitation.
Run one cheap experiment that can falsify the leading hypothesis.
Prefer a fix that improves a cluster over one that only hides the worst line.
After the fix, re-check Coherence replay storm diagnostic report and the likely regression surface: System reliability, low-power qualification, and customer confidence depend on robust cache debug closure..

Escalation triggers

The failure crosses architecture, RTL, verification, software, PD, or product ownership.
The proposed fix consumes area, power, latency, or verification margin needed elsewhere.
The issue repeats across workloads or blocks, suggesting methodology or model root cause.
The remaining risk is silicon-facing: Unresolved cache/coherency defects can cause field hangs, silent corruption risk, and emergency firmware workarounds..

Debug branch diagram

diagram

VISUAL MODEL — Memory Hierarchy / Cache Debug and Coherency Triage

        workload / trace
              │
              ▼
   metric symptom (Coherence replay storm diagnostic report)
              │
              ▼
     likely microarchitectural mechanism
              │
      ┌───────┼────────┐
      ▼       ▼        ▼
  pipeline  memory    fabric/coherency
  stalls    misses    queues / ordering
      │       │        │
      └───────┼────────┘
              ▼
        bounded design change
              │
              ▼
   validation workload + PPA regression

Tradeoff matrix

diagram

TRADEOFF MATRIX — Cache Debug and Coherency Triage

+----------------------+----------------------+----------------------+----------------------+
| Option               | Helps                | Can hurt             | Validation needed    |
+----------------------+----------------------+----------------------+----------------------+
| Larger / wider block | peak perf, miss rate | area, power, timing  | workload sweep       |
| Smarter policy       | hit rate, QoS, IPC   | verification risk    | corner cases + PMU   |
| More buffering       | latency tails, stalls| deadlock, leakage    | stress traffic tests |
| Software contract    | locality, ordering   | portability, APIs    | production workload  |
+----------------------+----------------------+----------------------+----------------------+

Senior rule: pick the smallest change that proves or disproves the mechanism.

Architecture deep dive

Cache hierarchy trades area and power for AMAT and bandwidth.

Concept diagram

diagram

MEMORY HIERARCHY

Core
 ├─ L1I / L1D  (cycles: 1-4, tiny, latency critical)
 ├─ L2         (cycles: 8-20, private or cluster)
 ├─ LLC / SLC  (shared, bandwidth + coherency point)
 ├─ NoC        (queueing + arbitration)
 └─ DRAM/HBM   (large penalty, high energy)

AMAT = hit_time + miss_rate × miss_penalty
But senior analysis also asks: MLP, bandwidth, QoS, and tail latency.

Metric graph

diagram

MISS PENALTY WATERFALL

L1 hit          ██  3 cyc
L2 hit          ████████  12 cyc
LLC hit         ███████████████  32 cyc
DRAM miss       ████████████████████████████████████  180 cyc

Small MPKI can still dominate if miss penalty is huge.

Metrics and artifacts

MPKI per level
L2/L3 bandwidth utilization
replacement policy stats
prefetch accuracy

Mini case study

Doubling L2 size reduces capacity misses but IPC improves only 3% because conflict misses dominate a shared workload. Fix data layout and false sharing before more SRAM.

Debug branches

If MPKI high but bandwidth low, footprint may exceed capacity.
If bandwidth saturated, coherency or DMA may be the real limit.

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.

Practice this lesson