mediumNVIDIAFireworks

A kernel runs at 25% occupancy. Is that a problem? Walk me through what occupancy buys and when you would leave it low on purpose.

Derive a block-level occupancy limit, then compare the extra residency with spill traffic and lost reuse. Use a matched experiment rather than a target percentage.

Updated Oct 2026 · Learn how AI infrastructure works through explanations, worked examples and diagrams, then practise applying it to interview questions.

Derive a block-level occupancy limit, then compare the extra residency with spill traffic and lost reuse. Use a matched experiment rather than a target percentage.

This answer is included with a free account. Sign in to read it and save your progress.

free account · no card needed

Work through the numbers

Change the assumptions in a free calculator, then explain what the result establishes and what still needs measurement.

The concepts behind this question

Use these concept explanations to review the ideas behind this question.

Advanced

⚡ Kernels & Compilers🔒 Premium

Occupancy and Register PressureOccupancy measures how many warps are resident relative to an SM’s limit. Registers, shared memory and launch shape constrain it, but higher occupancy is not always faster.

Foundational

🧩 GPU & Accelerator Architecture

GPU Memory HierarchyTrace storage scope and data reuse from registers through shared memory, caches and HBM. Worked register and traffic examples explain why a source-level load is not automatically an HBM transfer.

Foundational

🧩 GPU & Accelerator Architecture

GPU Execution ModelCUDA groups threads into warps and blocks that run on streaming multiprocessors. Learn how ready warps hide waiting, why registers limit residency, and when higher occupancy fails to improve performance.

Advanced

⚡ Kernels & Compilers🔒 Premium

Tiled Matrix MultiplicationTiled matrix multiplication reuses input values across many output calculations. Shared-memory and register tiles reduce repeated data movement while consuming limited on-chip resources.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Next in this trackExplain what HBM is and why memory bandwidth, not compute, is the wall for LLM inference.Next in this trackWhat actually changes with Blackwell and the NVL72 rack, and what does it do to how you would serve a large MoE model?Next in this trackYou have trained on GPUs. What transfers to training on TPUs, and what do you have to relearn?

FEDITOR'S NOTE

Explain which resource limits resident blocks, then check whether reducing that resource adds spills or repeated work. Higher occupancy earns its place only if the complete kernel improves.

DISCUSSION · 0

No comments yet — be the first to share your approach.