Computer Architecture · All levels

Dataflow Architecture Choices — Debug Playbook

Debug Playbook for Dataflow Architecture Choices (Accelerator Architectures).

On-call / interview prompt

Dataflow Architecture Choices 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. Replay workloads with phase markers and dataflow telemetry enabled.
2. Compare compute-idle windows against transfer/synchronization events.
3. Identify tiles or stages with repeated spill/refill churn.
4. Test alternative scheduling or tile geometry under identical constraints.
5. Lock a mode-selection policy with measurable guardrails.

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 Dataflow Architecture Choices, 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 Accelerator Architectures closure dashboard and the likely regression surface: Memory subsystem sizing and runtime policy complexity..

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: late-stage schedule slip, silicon risk, or cross-stage regression.

Debug branch diagram

diagram

VISUAL MODEL — Accelerator Architectures / Dataflow Architecture Choices

        workload / trace
              │
              ▼
   metric symptom (IPC, MPKI, bandwidth, latency, stalls)
              │
              ▼
     likely microarchitectural mechanism
              │
      ┌───────┼────────┐
      ▼       ▼        ▼
  pipeline  memory    fabric/coherency
  stalls    misses    queues / ordering
      │       │        │
      └───────┼────────┘
              ▼
        bounded design change
              │
              ▼
   validation workload + PPA regression

Tradeoff matrix

diagram

TRADEOFF MATRIX — Dataflow Architecture Choices

+----------------------+----------------------+----------------------+----------------------+
| 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

Accelerators win on locality and bandwidth contracts, not peak OPS alone.

Concept diagram

diagram

ACCELERATOR DATAFLOW

Host CPU ── commands ──► Queue / scheduler
   ▲                         │
   │ completion              ▼
Coherent memory ◄── DMA ── Local SRAM ──► Compute array
                         ▲       │
                         └ tiles ┘

Peak TOPS matters only when data reaches the array at the needed rate.

Metric graph

diagram

UTILIZATION BREAKDOWN

compute active   ██████████████████  58%
DMA wait         ██████████          31%
host sync        █████               15%
cache/coherency  ████                12%
idle bubbles     ███████             22%

Low utilization is usually a system integration problem.

Metrics and artifacts

accelerator utilization
DMA bandwidth
kernel launch overhead
coherency invalidation rate

Mini case study

NPU met TOPs target but end-to-end inference slow — DMA and weight fetch dominated. Architecture added on-chip SRAM tile and double-buffering.

Debug branches

If util low, check launch overhead and host sync first.
If BW high, examine weight layout and sparsity support.

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