# CUDA.@atomic causes type instability?
**URL:** https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224
**Category:** GPU
**Tags:** question
**Created:** [November 29, 2021, 7:51am UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224 "2021-11-29T07:51:00Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@guyvdb](https://discourse.julialang.org/u/guyvdb)
#### Post date: [November 29, 2021, 7:51am UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/1 "2021-11-29T07:51:00Z")
I am not sure why adding `CUDA.@atomic` in the below code causes an error?
```julia
# works fine without CUDA.@atomic
function f(test)
broadcast(CuVector(1:2), transpose(CuVector(1:3))) do i,j
v::Float32 = j
test[i] += v
end
end
f(CUDA.zeros(Float32,2))
# ERROR with CUDA.@atomic
function g(test)
broadcast(CuVector(1:2), transpose(CuVector(1:3))) do i,j
v::Float32 = j
CUDA.@atomic test[i] += v
end
end
g(CUDA.zeros(Float32,2))
```
```julia
ERROR: LoadError: GPU broadcast resulted in non-concrete element type Union{}.
This probably means that the function you are broadcasting contains an error or type instability.
Stacktrace:
[1] error(s::String)
@ Base ./error.jl:33
[2] copy
@ ~/.julia/packages/GPUArrays/3sW6s/src/host/broadcast.jl:44 [inlined]
[3] materialize
@ ./broadcast.jl:883 [inlined]
[4] broadcast(::var"#45#46"{CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}, ::CuArray{Int64, 1, CUDA.Mem.DeviceBuffer}, ::LinearAlgebra.Transpose{Int64, CuArray{Int64, 1, CUDA.Mem.DeviceBuffer}})
@ Base.Broadcast ./broadcast.jl:821
[5] g(test::CuArray{Float32, 1, CUDA.Mem.DeviceBuffer})
```
---
### Author:  [@kristoffer.carlsson](https://discourse.julialang.org/u/kristoffer.carlsson)
#### Post date: [November 29, 2021, 8:10am UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/2 "2021-11-29T08:10:15Z")
> `GPU broadcast resulted in non-concrete element type Union{}.`
A return value of `Union{}` means that the function throws. Are you sure this is correct usage of `CUDA.@atomic`? For example:
```julia
julia> test = CuArray([1,2,3]);
julia> CUDA.@atomic test[1] += 1
ERROR: MethodError: no method matching atomic_add!(::CuPtr{Int64}, ::Int64)
Closest candidates are:
atomic_add!(::Union{Core.LLVMPtr{Int64, 0}, Core.LLVMPtr{Int64, 1}, Core.LLVMPtr{Int64, 3}}, ::Int64) at ...
```
---
### Author:  [@maleadt](https://discourse.julialang.org/u/maleadt)
#### Post date: [November 29, 2021, 9:02am UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/3 "2021-11-29T09:02:58Z")
`CUDA.@atomic` only works in kernel context.
This usage looks OK, so try in a regular kernel where you can use `@device_code_warntype` to look at what’s wrong instead of our `broadcast` implementation here just bailing out.
---
### Author:  [@guyvdb](https://discourse.julialang.org/u/guyvdb)
#### Post date: [November 29, 2021, 5:26pm UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/4 "2021-11-29T17:26:36Z")
Thanks, I was being lazy using `broadcast` to sidestep the need to manually launch a kernel, call occupancy API, assign blocks and threads, etc 😃
---
### Author:  [@maleadt](https://discourse.julialang.org/u/maleadt)
#### Post date: [November 29, 2021, 5:31pm UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/5 "2021-11-29T17:31:05Z")
It’s a pattern that should probably work though, so feel free to open an issue about it as well!
---
### Author:  [@guyvdb](https://discourse.julialang.org/u/guyvdb)
#### Post date: [November 29, 2021, 6:27pm UTC](https://discourse.julialang.org/t/cuda-atomic-causes-type-instability/72224/6 "2021-11-29T18:27:31Z")
Done: [https://github.com/JuliaGPU/CUDA.jl/issues/1253](https://github.com/JuliaGPU/CUDA.jl/issues/1253)