# CuArrays not working as expected when broadcasting a function
**URL:** https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382
**Category:** Machine Learning
**Tags:** gpu
**Created:** [November 22, 2019, 10:45am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382 "2019-11-22T10:45:40Z")
**Posts on this page:** 8
**Page:** 1
### Author:  [@xiaodai](https://discourse.julialang.org/u/xiaodai)
#### Post date: [November 22, 2019, 10:45am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/1 "2019-11-22T10:45:40Z")
```julia
using CuArrays
t = cu(rand(150_000))
w = cu(rand(150_000))
t .+ w
```
I define the following function
```julia
logloss(t, w) = -(t * log(1 / (1 + exp(-w))) + (1 - t) * log(1 - 1 / (1 + exp(-w))))
```
but broadcasting it for CuArrays doesn’t work, see
```julia
logloss.(t, w)
```
```julia
Warning: calls to Base intrinsics might be GPU incompatible
│ exception =
│ You called exp(x::T) where T<:Union{Float32, Float64} in Base.Math at special/exp.jl:75, maybe you intended to call exp(x::Float32) in CUDAnative at C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\device\cuda\math.jl:99 instead?
│ Stacktrace:
│ [1] exp at special/exp.jl:75
│ [2] logloss at C:\scratch\cu-test\ok.jl:11
│ [3] #25 at C:\Users\RTX2080\.julia\packages\GPUArrays\0lvhc\src\broadcast.jl:49
└ @ CUDAnative C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\compiler\irgen.jl:116
┌ Warning: calls to Base intrinsics might be GPU incompatible
│ exception =
│ You called log(x::Float32) in Base.Math at special/log.jl:290, maybe you intended to call log(x::Float32) in CUDAnative at C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\device\cuda\math.jl:71 instead?
│ Stacktrace:
│ [1] log at special/log.jl:290
│ [2] logloss at C:\scratch\cu-test\ok.jl:11
│ [3] #25 at C:\Users\RTX2080\.julia\packages\GPUArrays\0lvhc\src\broadcast.jl:49
└ @ CUDAnative C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\compiler\irgen.jl:116
┌ Warning: calls to Base intrinsics might be GPU incompatible
│ exception =
│ You called exp(x::T) where T<:Union{Float32, Float64} in Base.Math at special/exp.jl:75, maybe you intended to call exp(x::Float32) in CUDAnative at C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\device\cuda\math.jl:99 instead?
│ Stacktrace:
│ [1] exp at special/exp.jl:75
│ [2] logloss at C:\scratch\cu-test\ok.jl:11
│ [3] #25 at C:\Users\RTX2080\.julia\packages\GPUArrays\0lvhc\src\broadcast.jl:49
└ @ CUDAnative C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\compiler\irgen.jl:116
┌ Warning: calls to Base intrinsics might be GPU incompatible
│ exception =
│ You called log(x::Float32) in Base.Math at special/log.jl:290, maybe you intended to call log(x::Float32) in CUDAnative at C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\device\cuda\math.jl:71 instead?
│ Stacktrace:
│ [1] log at special/log.jl:290
│ [2] logloss at C:\scratch\cu-test\ok.jl:11
│ [3] #25 at C:\Users\RTX2080\.julia\packages\GPUArrays\0lvhc\src\broadcast.jl:49
└ @ CUDAnative C:\Users\RTX2080\.julia\packages\CUDAnative\2WQzk\src\compiler\irgen.jl:116
```
But v2 works which broadcasts inside the function instead of broadcasting the function
```julia
logloss_v2(t, w) = -(t .* log.(1 ./ (1 .+ exp.(-w))) .+ (1 .- t) .* log.(1 .- 1 ./ (1 .+ exp.(-w))))
logloss_v2(t, w) #works
```
Here are my info
```julia
(cu-test) pkg> st
Status `C:\scratch\cu-test\Project.toml`
[c5f51814] CUDAdrv v4.0.4
[be33ccc6] CUDAnative v2.5.5
[3a865a2d] CuArrays v1.4.7
Activating environment at `c:\scratch\cu-test\Project.toml`
┌ Warning: calls to Base intrinsics might be GPU incompatible
Julia Version 1.3.0-rc5.1
Commit 36c4eb251e (2019-11-17 19:04 UTC)
Platform Info:
OS: Windows (x86_64-w64-mingw32)
CPU: Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz
WORD_SIZE: 64
LIBM: libopenlibm
LLVM: libLLVM-6.0.1 (ORCJIT, skylake)
Environment:
JULIA_EDITOR = "C:\Users\RTX2080\AppData\Local\atom\app-1.41.0\atom.exe" -a
JULIA_NUM_THREADS = 6
JULIA_PKG_DEVDIR = c:/git/
```
---
### Author:  [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)
#### Post date: [November 22, 2019, 11:05am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/2 "2019-11-22T11:05:43Z")
> [@xiaodai](#):
>
> logloss(t, w) = -(t \* log(1 / (1 + exp(-w))) + (1 - t) \* log(1 - 1 / (1 + exp(-w))))
Try the following
```julia
logloss(t, w) = -(t * log(1 / (1 + exp(-w))) + (1 - t) * log(1 - 1 / (1 + exp(-w))))
CuArrays.@cufunc logloss(t, w) = -(t * log(1 / (1 + exp(-w))) + (1 - t) * log(1 - 1 / (1 + exp(-w))))
```
---
### Author:  [@xiaodai](https://discourse.julialang.org/u/xiaodai)
#### Post date: [November 22, 2019, 11:08am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/3 "2019-11-22T11:08:46Z")
Now it’s working. So I need to do `@cufunc` macro now?
---
### Author:  [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)
#### Post date: [November 22, 2019, 11:20am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/4 "2019-11-22T11:20:03Z")
Function like `log/sin` only work when broadcasted over a CuArray since then the type information is there. If you loop over the vector, like when you broadcast your outer function, you are calling the base version of `log/sin` with a scalar that lives on the GPU. The macro rewrites the function to use the CUDAnative version of log/sin so that it works and is performant
---
### Author:  [@xiaodai](https://discourse.julialang.org/u/xiaodai)
#### Post date: [November 22, 2019, 11:22am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/5 "2019-11-22T11:22:13Z")
This is a little odd for me. Of corse, I don’t undertand the technical reasons, but this makes Julia less generic in a way. I have to sprinkle `CuArrays.@cufunc` everywhere now right?
---
### Author:  [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)
#### Post date: [November 22, 2019, 11:28am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/6 "2019-11-22T11:28:57Z")
> [@xiaodai](#):
>
> I have to sprinkle `CuArrays.@cufunc` everywhere now right?
No, you need to place it where appropriate. I think it’s quite remarkable that all you need to do is to add `@cufunc` in your julia code to have it operate on a GPU. A gpu fundamentally operates by doing similar operations over large arrays. You could restrict your function logloss to only accept arrays and do broadcasting internally, sacrificing some potential performance from fusing. However, if you do intend to use your code for GPU computatoins, `@cufunc` is probably what’s recommended at the moment.
You can also write stuff using GPUifyLoops, which is supposed to make stuff run on both cpu and gpu.
`@cufunc` essentially writes the CUDA kernel for you, so that you do not ave to write CUDA C yourself.
---
### Author:  [@xiaodai](https://discourse.julialang.org/u/xiaodai)
#### Post date: [December 1, 2019, 9:58am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/7 "2019-12-01T09:58:19Z")
> [@baggepinnen](#):
>
> Function like `log/sin` only work when broadcasted over a CuArray since then the type information is there.
I don’t quite understand this bit
---
### Author:  [@baggepinnen](https://discourse.julialang.org/u/baggepinnen)
#### Post date: [December 1, 2019, 11:02am UTC](https://discourse.julialang.org/t/cuarrays-not-working-as-expected-when-broadcasting-a-function/31382/8 "2019-12-01T11:02:55Z")
`broadcasted(sin, a) ` can be overloaded for various types of `a` to use `sin` on the GPU.