# How to copy view of CuArray to Array efficiently?
**URL:** https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960
**Category:** GPU
**Tags:** question, cuda
**Created:** [October 5, 2024, 5:26pm UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960 "2024-10-05T17:26:22Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@0samuraiE](https://discourse.julialang.org/u/0samuraiE)
#### Post date: [October 5, 2024, 5:26pm UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960/1 "2024-10-05T17:26:22Z")
Hi all. For some reason, I encountered a GPU allocation problem when I copied a CuArray view. I tried several copying methods, but the third result was much slower.
Should I avoid copying the CuArray view to the host?
```julia
0.001308 seconds (6 CPU allocations: 96 bytes)
0.001590 seconds (46 CPU allocations: 1.344 KiB) (1 GPU allocation: 30.518 MiB, 0.56% memmgmt time)
0.181835 seconds (200.00 k CPU allocations: 3.052 MiB)
```
```julia
using CUDA
A1 = CUDA.rand(202, 202, 202);
B1 = CUDA.pin(zeros(eltype(A1), size(A1)));
copyto!(B1, A1)
B1 == Array(A1)
ind = CartesianIndices((200, 200, 200))
A2 = @view CUDA.rand(202, 202, 202)[ind];
B2 = CUDA.pin(zeros(eltype(A2), size(A2)));
copyto!(B2, A2)
B2 == Array(A2)
ind = CartesianIndices((200, 200, 200))
A3 = CUDA.rand(202, 202, 202);
B3 = CUDA.pin(zeros(eltype(A3), size(ind)));
copyto!(B3, ind, A3, ind)
B3[ind] == Array(A3[ind])
CUDA.@time CUDA.@sync copyto!(B1, A1);
CUDA.@time CUDA.@sync copyto!(B2, A2);
CUDA.@time CUDA.@sync copyto!(B3, ind, A3, ind);
```
---
### Author:  [@Ahmed\_Salih](https://discourse.julialang.org/u/Ahmed_Salih)
#### Post date: [October 6, 2024, 8:22am UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960/2 "2024-10-06T08:22:41Z")
In general when coding on GPU, you should not copy the arrays to host (CPU) until you actually need to do so. The longer you can keep it on GPU, the faster your overall code will be.
Transferring data between GPU and CPU all the time, will slow down your application, especially if the tasks are on a smaller scale.
If your GPU calc takes 1000 s and then you need 0.18s to copy over, then it will not be a bottle neck.
Kind regards
---
### Author:  [@0samuraiE](https://discourse.julialang.org/u/0samuraiE)
#### Post date: [October 6, 2024, 11:00am UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960/3 "2024-10-06T11:00:04Z")
Thank you. ~~But this problem is a gpu allocation problem, not a time problem. GPU allocation in 2nd example is as same size as CuArray to copy.
It seems like a waste of valuable GPU memory.~~
the 3rd is the best after all.
---
### Author:  [@maleadt](https://discourse.julialang.org/u/maleadt)
#### Post date: [October 6, 2024, 11:01am UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960/4 "2024-10-06T11:01:33Z")
> [@0samuraiE](#):
>
> I encountered a GPU allocation problem when I copied a CuArray view
If your view is non-contiguous, it will be squashed into a contiguous `CuArray` first before copying to the host `Array` using an API call. Alternatives are possible, such as performing multiple API calls to copy each contiguous slice, or by using a `CuArray` representing the host array (e.g., using `unsafe_wrap(CuArray, ::Array)`) and performing a broadcast assignment. None of these are guaranteed to improve performance in all cases though, so we default to the simplest solution, which is to allocate a temporary `CuArray`.
---
### Author:  [@0samuraiE](https://discourse.julialang.org/u/0samuraiE)
#### Post date: [October 6, 2024, 11:08am UTC](https://discourse.julialang.org/t/how-to-copy-view-of-cuarray-to-array-efficiently/120960/5 "2024-10-06T11:08:53Z")
Thanks everyone for consideration, I will take the third way.