AI Infra Interviews logo
← CUDA, Triton & Kernel Engineering / 11
mediumOpenAITogether AI

When do you write a kernel in Triton, and when do you have to drop down to CUDA?

Start with the operation, supported hardware and performance target. Compare ordinary Triton, lower-level Triton interfaces and CUDA using a measured gap that is large enough to justify maintaining custom code.

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

Start with the operation, supported hardware and performance target. Compare ordinary Triton, lower-level Triton interfaces and CUDA using a measured gap that is large enough to justify maintaining custom code.

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.

Foundational
⚡ Kernels & Compilers
Kernel FusionKernel fusion combines operations so intermediate results can stay on-chip. It can reduce memory traffic and launch overhead, but may increase resource pressure.
Core
⚡ Kernels & CompilersSign in
Triton Programming ModelTriton expresses GPU work as operations on blocks of values. You choose shapes, addresses and masks while the compiler maps the work onto hardware.
Advanced
⚡ Kernels & Compilers🔒 Premium
CUDA Compilation: PTX, Cubins and SASSCUDA source, PTX and native GPU instructions describe different stages of execution. Inspect the selected binary and its resource use before explaining a performance change.
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 trackHere is an Nsight Compute report for a slow kernel. Read it, name the bottleneck, and tell me what you would change.Next in this trackSum 100 million floats on the GPU as fast as the hardware allows. Write the kernel and justify each step.Next in this trackTranspose a large matrix at close to copy bandwidth. Why is the naive version slow, and what does each fix buy?
FEDITOR'S NOTE

Explain who controls the data layout and scheduling, check the installed compiler’s capabilities, and convert a measured kernel improvement into an end-to-end benefit before choosing a lower-level implementation.

DISCUSSION · 0

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