# CUDA.jl - Better GPU but Worse Performance

**URL:** <https://discourse.julialang.org/t/cuda-jl-better-gpu-but-worse-performance/83337>\
**Category:** GPU\
**Tags:** gpu, performance\
**Created:** [June 25, 2022, 4:39pm UTC](https://discourse.julialang.org/t/cuda-jl-better-gpu-but-worse-performance/83337 "2022-06-25T16:39:40Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![gvijqb](https://avatars.discourse-cdn.com/v4/letter/g/ecd19e/32.png) [@gvijqb](https://discourse.julialang.org/u/gvijqb)\
**Post date:** [June 27, 2022, 7:01pm UTC](https://discourse.julialang.org/t/cuda-jl-better-gpu-but-worse-performance/83337/7 "2022-06-27T19:01:21Z")

</div>

+1 to @LaurentPlagne

Gaming GPUs are best for FP16 and FP32. They are not performant for FP64 and are not designed for simulation workloads per se.

For FP64 you’d want to explore GPUs like Tesla V100 and A100s.

P2000 would be quite slow as well in comparison if you have large simulation workload.

---

_[View the full topic](https://discourse.julialang.org/t/cuda-jl-better-gpu-but-worse-performance/83337)._