# Elegant kernel for vectors in matrix

**URL:** <https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648>\
**Category:** GPU\
**Tags:** cuda\
**Created:** [February 4, 2021, 8:38pm UTC](https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648 "2021-02-04T20:38:37Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ribeiro](https://avatars.discourse-cdn.com/v4/letter/r/d9b06d/32.png) [@Ribeiro](https://discourse.julialang.org/u/Ribeiro)\
**Post date:** [February 4, 2021, 8:38pm UTC](https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648/1 "2021-02-04T20:38:37Z")

</div>

Hello,  
I’m trying to write a kernel that does some operations on vectors using CUDA.jl and @cuda. My code is essentially this:

```julia
points = Nx3 matrix with x,y,z coordinates of points
elements = Nx4 matrix with integers that list rows in "points" making up quadrilaterals
A = NxN matrix
for i in 1:N
 for j in 1:N
   a bunch of operations (and, unfortunately, some if statements) involving the points in elements[i,:] and elements[j,:]
   A[i,j] = a function of those operations
 end
end

```

A lot of the operations involve `dot` and `cross`. On the CPU I deal with that in a pretty clean way. Say:

```julia
point1=points[elements[i,1],:] # gives me an array with 3 numbers x,y,z
...
vec1 = point1-point2;
...
foo = dot(vec1,vec2)
bar = cross(vec1,vec2)

```

Is there an elegant way to do that on the GPU? Trying to use `[i,:]` doesn’t seem to work and extracting subvectors of an array doesn’t seem too easy (also, assigning subvectors of an array! Say A[1,:] = b).  
I don’t even know how to create an array in a kernel. The only way that I managed to do some math was to index each individual position and do the calculations in the classic way (i.e., old school C-style, not Matlab-style).  
Thanks a lot!

---

<div class="post-metadata">

**Author:** ![dpsanders](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/dpsanders/32/3573_2.png) [@dpsanders](https://discourse.julialang.org/u/dpsanders)\
**Post date:** [February 4, 2021, 9:33pm UTC](https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648/2 "2021-02-04T21:33:46Z")

</div>

Check out the StaticArrays.jl package. Make points into a Vector containing SVectors.

---

<div class="post-metadata">

**Author:** ![Ribeiro](https://avatars.discourse-cdn.com/v4/letter/r/d9b06d/32.png) [@Ribeiro](https://discourse.julialang.org/u/Ribeiro)\
**Post date:** [February 5, 2021, 8:56am UTC](https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648/3 "2021-02-05T08:56:10Z")

</div>

Ah, that does seem more elegant than what I’m doing on the CPU! `A=CuArray(Vector{SVector{3,Float64}}(undef,10))`  
works and I can do dot and cross! Thanks a lot!

---

<div class="post-metadata">

**Author:** ![Ribeiro](https://avatars.discourse-cdn.com/v4/letter/r/d9b06d/32.png) [@Ribeiro](https://discourse.julialang.org/u/Ribeiro)\
**Post date:** [February 5, 2021, 12:57pm UTC](https://discourse.julialang.org/t/elegant-kernel-for-vectors-in-matrix/54648/4 "2021-02-05T12:57:32Z")

</div>

@dpsanders you, sir, have just sped up a certain part of my code 10x on the CPU! Many thanks!  
Now on to the GPU.