Weight-Stationary Dataflow: Interview Drills

Interview drills

Interview Drills for Weight-Stationary Dataflow is anchored on Weight reuse factor and off-array weight bandwidth per tera-operations for representative inference layers.. Convert measurements into mechanism-backed decisions with clear owner accountability.

PROMPT
You observe regression in Weight reuse factor and off-array weight bandwidth per tera-operations for representative inference layers. for Weight-Stationary Dataflow. Explain root cause and release decision.

STRONG ANSWER
1. Defines workload and first failing mechanism.
2. Explains mechanism: In weight-stationary scheduling, each PE holds a weight value (or small filter fragment) for multiple cycles while activations stream through the mesh. Keeping weights local reduces expensive weight fetch traffic and is especially attractive for convolutional and batched inference workloads where filters are reused heavily across many input windows. The tradeoff is that activation movement and partial-sum routing can become dominant bandwidth or latency bottlenecks if tiling is not aligned to on-chip buffer capacity. Effective designs co-optimize filter blocking, activation prefetch, and reload cadence so stationary weights remain fully productive instead of idling between tiles.
3. Requests proving artifact: Dataflow mapping report showing weight residency, activation traffic, and buffer pressure by layer type.
4. Proposes bounded fix + owner + rollback-safe validation.

WEAK ANSWER
Gives generic optimization ideas without mechanism proof or ownership.

AI accelerator deep dive

Systolic efficiency is governed by feed quality, tile fit, and bubble control.

Concept diagram

SYSTOLIC WAVEFLOW

operand stream -> wavefront launch -> PE mesh compute -> reduction/writeback
                         ^ bubbles and feed stalls reduce realized throughput

Metric graph

UTILIZATION LOSSES

tile mismatch      ███████
feed stalls        █████████
sync bubbles       █████

Metrics and artifacts to collect

• mesh occupancy timeline

• fill-drain overhead

• tile mismatch histogram

• DRAM stall attribution

Mini case study

Increasing mesh size did not help until scheduling and tile alignment removed persistent wavefront bubbles.

Debug branches

• Measure bubble source first

• Classify compute vs memory starvation

• Tune tile policy before frequency changes

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.

Interview answer expansion

A strong answer on Weight-Stationary Dataflow names the workload symptom, explains mechanism (In weight-stationary scheduling, each PE holds a weight value (or small filter fragment) for multiple cycles while activations stream through the mesh. Keeping weights local reduces expensive weight fetch traffic and is especially attractive for convolutional and batched inference workloads where filters are reused heavily across many input windows. The tradeoff is that activation movement and partial-sum routing can become dominant bandwidth or latency bottlenecks if tiling is not aligned to on-chip buffer capacity. Effective designs co-optimize filter blocking, activation prefetch, and reload cadence so stationary weights remain fully productive instead of idling between tiles.), and proposes one measurable validation plan.

Then it identifies owner and fallback action if the proposed fix under-delivers.

The goal is practical engineering reasoning, not keyword listing.