# Max.(v1,v2) on the GPU
**URL:** https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386
**Category:** GPU
**Tags:** question
**Created:** [September 18, 2021, 11:31pm UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386 "2021-09-18T23:31:43Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@gianmariomanca](https://discourse.julialang.org/u/gianmariomanca)
#### Post date: [September 18, 2021, 11:31pm UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/1 "2021-09-18T23:31:43Z")
What’s the best way to implement the element wise maximum of for 2 vectors of the same length on the GPU using CUDA.jl or any other package?
```julia
julia> v1 = [1, 2, 3]
3-element Vector{Int64}:
1
2
3
julia> v2 = [4, 3, 2]
3-element Vector{Int64}:
4
3
2
julia> max.(v1,v2)
3-element Vector{Int64}:
4
3
3
```
You can assume float32.
---
### Author:  [@stillyslalom](https://discourse.julialang.org/u/stillyslalom)
#### Post date: [September 19, 2021, 1:45am UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/2 "2021-09-19T01:45:34Z")
It’s just as you’ve written it, except with device arrays:
```julia
julia> using CUDA
julia> v1 = cu(Float32[1, 2, 3])
3-element CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}:
1.0
2.0
3.0
julia> v2 = cu(Float32[4, 3, 2])
3-element CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}:
4.0
3.0
2.0
julia> max.(v1, v2)
3-element CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}:
4.0
3.0
3.0
```
---
### Author:  [@gianmariomanca](https://discourse.julialang.org/u/gianmariomanca)
#### Post date: [September 19, 2021, 2:36am UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/3 "2021-09-19T02:36:43Z")
Ahh… it was a Pluto “bug”:
I assumed the issue was the max operation but I guess it was Pluto trying to do some scalar indexing for IO?
Works fine in the REPL.
---
### Author:  [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)
#### Post date: [September 19, 2021, 4:32am UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/4 "2021-09-19T04:32:19Z")
Might be an instance of [https://github.com/JuliaGPU/CUDA.jl/issues/875](https://github.com/JuliaGPU/CUDA.jl/issues/875)
---
### Author:  [@maleadt](https://discourse.julialang.org/u/maleadt)
#### Post date: [September 20, 2021, 8:11am UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/5 "2021-09-20T08:11:29Z")
That’s probably Pluto.jl replacing the output stack, so GPUArrays.jl’s show methods (which first copy to the CPU as not to trigger scalar iteration) are not used.
---
### Author:  [@gianmariomanca](https://discourse.julialang.org/u/gianmariomanca)
#### Post date: [September 30, 2021, 3:19am UTC](https://discourse.julialang.org/t/max-v1-v2-on-the-gpu/68386/6 "2021-09-30T03:19:14Z")
@fonsp FYI