Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Writing CUDA kernels in C/C++ v1.0.0

Use this resource to write and optimize CUDA kernels for NVIDIA GPUs

New

  • 505 downloads
  • 129 likes
  • 246 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install cuda-kernel-programming

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent helps you set the launch configuration, organize memory accesses and use asynchronous streams. It also gives the nvcc options for your target and the basics of the Thrust library.

Mostly picked by

Updated November 2, 2026

Card for the “Writing CUDA kernels in C/C++” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: minimal kernel, memory hierarchy and launch configuration
  • SKILL.md: streams and async copies, nvcc options and compilation

Good fit for

  • You are writing a matrix multiplication or reduction kernel
  • Your kernel is slow because of memory access or occupancy

Not for

    Tags

    • cuda
    • gpu
    • nvidia
    • kernel

    About

    You say

    “Write a CUDA sum reduction kernel with shared memory for an array of 10 million floats.”

    Card for the “Writing CUDA kernels in C/C++” skill

    Skill published by mohitmishra786 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to write and optimize CUDA kernels for NVIDIA GPUs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md7.8 KB

    Origin and licence

    Listed unmodified

    Author
    mohitmishra786
    Source
    github.com/mohitmishra786/low-level-dev-skills/tree/bdc58472fa9f309ed1b3f7d985a0d8e9bd8f4608/skills/gpu/cuda
    Licence
    MIT

    Notice

    « cuda » (mohitmishra786, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.