skills.rest
ROCm
ROCmOFFICIAL
Explore all skills by this author →
WebsiteGitHub

build-flydsl

Automate building and installing FlyDSL from source on remote hosts or containers.

260|104|Updated Nov 23, 2025
Search Tags:#build#installation#llvm#toolchain#remote#mlir#flydsl
One-click install
npx skills add https://github.com/ROCm/FlyDSL --skill build-flydsl-rocm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: build-flydsl
Source: https://github.com/ROCm/FlyDSL/tree/main/.claude/skills/build-flydsl
Command: npx skills add https://github.com/ROCm/FlyDSL --skill build-flydsl-rocm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build and install FlyDSL from source on a remote host or Docker container, simplifying a complex LLVM/MLIR toolchain setup for GPU development.

Core Features & Use Cases

  • Automates the end-to-end build of LLVM/MLIR, Fly dialect, and Python bindings for a reproducible environment.
  • Supports remote or container-based installations with clear prerequisites and verification steps.
  • Use Case: Set up a consistent FlyDSL toolchain on an on-prem cluster or CI runner with minimal manual configuration.

Quick Start

Run the full build sequence on a remote host or container to compile LLVM/MLIR, FlyDSL, and Python bindings.

Frequently Asked Questions about build-flydsl

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build and install FlyDSL from source on a remote host?▼

You can build FlyDSL on a remote host by running an automated sequence that bootstraps LLVM/MLIR from source, configures the Fly dialect, compiles C++ and Python components, and verifies the final installation.

What is the best way to set up an LLVM and MLIR toolchain for AMD GPU development?▼

The best way to set up an LLVM and MLIR toolchain for AMD GPU development is to automate bootstrapping LLVM/MLIR from source alongside the Fly dialect and Python bindings for a reproducible build.

Can I use this FlyDSL build process for CI runners and on-prem clusters?▼

Yes, you can use this FlyDSL build process for CI runners and on-prem clusters to deploy a consistent, reproducible AMD GPU toolchain across remote hosts or Docker containers with minimal manual configuration.

Do I need Docker to compile FlyDSL and its Python bindings?▼

No, Docker is not strictly required to compile FlyDSL and Python bindings; the build process supports both remote host installations and Docker containers to compile LLVM/MLIR and Fly dialect components.

What are the prerequisites for configuring the Fly dialect with MLIR?▼

Configuring the Fly dialect with MLIR requires bootstrapping LLVM/MLIR from source first, then configuring the Fly dialect, building C++ and Python components, and verifying the installation on your remote host or container.

Why does my FlyDSL compilation fail during remote host setup?▼

FlyDSL compilation might fail during remote host setup if the LLVM/MLIR toolchain is not properly bootstrapped from source, or if prerequisites for building the Fly dialect and Python bindings are missing before installation verification.

Related Skills

Explore More Software Engineering Skills→
fsx950223fsx950223
2

build-flydsl

Build and install FlyDSL with LLVM/MLIR on remote hosts or Docker containers.

Community
Advanced
ROCmROCm
260

FlyDSL Tile Programming

Generate and validate FlyDSL GPU kernels from kernel specifications using tile programming.

Official
Advanced
NeverSightNeverSight
69

mlir-development

Develop MLIR dialects and passes for transforming compiler IR.

Official
Advanced
hw-native-syshw-native-sys
30

build-ptoas-wsl

Build and validate the PTOAS compiler toolchain from source in WSL.

Official
Advanced