# Triton: GPU Programming for Neural Networks

**URL:** <https://discourse.julialang.org/t/triton-gpu-programming-for-neural-networks/72033>\
**Category:** GPU\
**Tags:** machine-learning\
**Created:** [November 24, 2021, 9:51pm UTC](https://discourse.julialang.org/t/triton-gpu-programming-for-neural-networks/72033 "2021-11-24T21:51:34Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![stemann](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/stemann/32/4030_2.png) [@stemann](https://discourse.julialang.org/u/stemann)\
**Post date:** [November 24, 2021, 9:51pm UTC](https://discourse.julialang.org/t/triton-gpu-programming-for-neural-networks/72033/1 "2021-11-24T21:51:34Z")

</div>

Any thoughts on OpenAI’s [Triton](https://openai.com/blog/triton/)? @maleadt ?

---

<div class="post-metadata">

**Author:** ![maleadt](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/maleadt/32/10097_2.png) [@maleadt](https://discourse.julialang.org/u/maleadt)\
**Post date:** [November 25, 2021, 6:41am UTC](https://discourse.julialang.org/t/triton-gpu-programming-for-neural-networks/72033/2 "2021-11-25T06:41:28Z")

</div>

I haven’t looked at Triton in detail, but it looks like a nice DSL with great performance characteristics. Especially matching CUBLAS on GEMMM, that’s not an easy feat. With CUDA.jl etc we focus on the lower-level programming experience, exposing all of the hardware’s capabilities, and a DSL like Triton could be built on top of that. KernelAbstractions.jl is pretty much that, and could probably learn from the abstractions and techniques used in Triton.

---

<div class="post-metadata">

**Author:** ![stemann](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/stemann/32/4030_2.png) [@stemann](https://discourse.julialang.org/u/stemann)\
**Post date:** [November 25, 2021, 9:06am UTC](https://discourse.julialang.org/t/triton-gpu-programming-for-neural-networks/72033/3 "2021-11-25T09:06:42Z")

</div>

Sounds just right 🙂