# CuArray/CUDAnative argmin paradoxical performance

**URL:** <https://discourse.julialang.org/t/cuarray-cudanative-argmin-paradoxical-performance/20194>\
**Category:** GPU\
**Created:** [January 28, 2019, 8:25pm UTC](https://discourse.julialang.org/t/cuarray-cudanative-argmin-paradoxical-performance/20194 "2019-01-28T20:25:04Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Alex\_Ellison](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/alex_ellison/32/5749_2.png) [@Alex\_Ellison](https://discourse.julialang.org/u/Alex_Ellison)\
**Post date:** [January 28, 2019, 8:25pm UTC](https://discourse.julialang.org/t/cuarray-cudanative-argmin-paradoxical-performance/20194/1 "2019-01-28T20:25:04Z")

</div>

Hey there,  
I have a kernel which computes some 3D CuArray of float32s, and I’d like to run argmin on one of the axes, resulting in a 2D set of indices. For some reason, if I invoke CUDAnative.argmin on the original host array directly, it is extremely fast, but if I run it on the device copy, it is prohibitively slow (slower than simply using the CPU, or a manual loop inside a GPU kernel). Below is a MWE and the output I get.

So my question is, is this possibly a bug? If not, why isn’t using the array already on the device faster?

```julia
using CUDAdrv, CUDAnative, CuArrays

function main()
	# iterate so JIT warms up
	for iteration in 1:3
		println("\niteration ", iteration)
		input = rand(4, 4, 1000)
		cpu_min = @time argmin(input, dims=3)
	        cu_in = CuArray(input)

		dt = CUDAdrv.@elapsed begin
			# this should be uploading and then doing argmin
	    	 gpu_min = CUDAnative.argmin(input, dims=3)
		end
		println(dt)
		@assert gpu_min == cpu_min

		dt = CUDAdrv.@elapsed begin
			 # `cu_in` is already on device?
	    	 gpu_min = CUDAnative.argmin(cu_in, dims=3)
		end
		println(dt)

		@assert gpu_min == cpu_min
	end
end

main()

```

**Output:**

```julia
iteration 1
  0.135498 seconds (19.47 k allocations: 884.571 KiB)
1.824e-6
6.534424

iteration 2
  0.000183 seconds (12 allocations: 1.016 KiB)
2.4e-6
1.3460175

iteration 3
  0.000180 seconds (12 allocations: 1.016 KiB)
2.432e-6
1.3351139

```

Thanks,  
Alex

---

<div class="post-metadata">

**Author:** ![maleadt](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/maleadt/32/10097_2.png) [@maleadt](https://discourse.julialang.org/u/maleadt)\
**Post date:** [January 29, 2019, 7:01am UTC](https://discourse.julialang.org/t/cuarray-cudanative-argmin-paradoxical-performance/20194/2 "2019-01-29T07:01:40Z")

</div>

> [@Alex\_Ellison](#):
>
> CUDAnative.argmin

There is no `CUDAnative.argmin`, this just resolves to Base. CUDAnative is for kernel programming, you are just using array abstractions here, ie. functionality that is implemented in CuArrays. but `argmin` isn’t optimized there, you’re just using the Base implementation.

As such, you should do the traditional steps of optimizing CuArrays code. The first is to disable scalar iteration:

```julia
julia> argmin(cu(rand(2,2,2)), dims=3)
ERROR: scalar getindex is disallowed
Stacktrace:
 [1] error(::String) at ./error.jl:33
 [2] assertscalar at /home/tbesard/Julia/GPUArrays/src/indexing.jl:8 [inlined]
 [3] getindex(::CuArray{Float32,3}, ::Int64) at /home/tbesard/Julia/GPUArrays/src/indexing.jl:44
 [4] _findmin at ./abstractarray.jl:270 [inlined]
 [5] #findmin#575 at ./reducedim.jl:764 [inlined]
 [6] #findmin at ./none:0 [inlined]
 [7] #argmin#578(::Int64, ::Function, ::CuArray{Float32,3}) at ./reducedim.jl:853

```

I haven’t looked at the problem in depth, but some of the lower-level kernels in the stack trace (eg. `findmin`) should probably be implemented in CuArrays, on top of the GPU `mapreduce` functionality there.

---

<div class="post-metadata">

**Author:** ![Alex\_Ellison](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/alex_ellison/32/5749_2.png) [@Alex\_Ellison](https://discourse.julialang.org/u/Alex_Ellison)\
**Post date:** [January 31, 2019, 5:35pm UTC](https://discourse.julialang.org/t/cuarray-cudanative-argmin-paradoxical-performance/20194/3 "2019-01-31T17:35:10Z")

</div>

Cheers