liveBook · Manning

Hardware portability

As explained in GPU Programming with Triton

Hardware portability is the ability to execute the same program source across different hardware targets through backend-specific compilation.

Hardware portability in Triton comes from expressing kernels as tile operations rather than vendor-specific instructions. The compiler maps those operations to each target, allowing the same kernel source to run across different GPU vendors. section 1.1.1

A kernel written for NVIDIA GPUs can run on AMD GPUs through ROCm or Intel GPUs through the XPU backend without source changes. Toolchain updates can also expose newer hardware capabilities to existing kernels without a rewrite. section 1.1.1

Attention kernels across vendors

vLLM and SGLang run Triton attention kernels on AMD hardware through ROCm, avoiding separate vendor-specific implementations. section 1.1.1

How GPU Programming with Triton covers it

How deep it goes
Traces portability from tile operations to target-specific compilation, but stops short of explaining backend internals.
Examples
Names vLLM and SGLang attention kernels running on AMD hardware through ROCm.
What you can do after
Apply it by writing one Triton kernel source for NVIDIA, AMD, and Intel targets without vendor-specific rewrites.
How it connects
Connects Triton kernels with ROCm, AMDGPU IR, and GPU compiler backends.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of GPU Programming with Triton. The section links point to the parts of the book it draws on.