julia> using LoopVectorization
[ Info: Precompiling LoopVectorization [bdcacae8-1622-11e9-2a5c-532679323890]

julia> function foofoo(xs::Vector{Int64})
           s = 0f0
           @inbounds @avx for i in 1:length(xs)
               s += Float32(xs[i])
           end
           return s
       end
foofoo (generic function with 1 method)

julia> foofoo(collect(1:10))
55.0f0

julia> using LoopVectorization

julia> function lv_test(A, B ,C)
           D = zero(promote_type(eltype(A),eltype(B),eltype(C)))
           @avx for i in axes(C,1), j in axes(C,2), k in axes(C,3)
               D += A[i,j] * B[i,k] * C[i,j,k]
           end
           D
       end
lv_test (generic function with 1 method)

julia> A = rand(2, 3); B = rand(2, 3); C = rand(2, 3, 3);

julia> lv_test(A, B, C)
3.162221675229055

julia> function fwd(r22::AbstractArray{T}, x, r312, ax_b=axes(x,2), ax_β=axes(r312,2), ax_a=axes(r312,2), ax_c=axes(r312,1)) where T
               acc = zero(T)
               # for c in ax_c  # works fine without @avx
               @avx for c in ax_c
                   for a in ax_a
                       for β in ax_β
                           for b in ax_b
                               acc = acc + r22[b, β] * x[a, b, c] * r312[c, a, β]
                           end
                       end
                   end
               end
               acc
       end
fwd (generic function with 5 methods)

julia> r22, x, r312 = rand(2,2), rand(1,2,3), rand(3,1,2);

julia> fwd(r22, x, r312) # UndefVarError: ####op#568_0 not defined
0.38040785607910943

julia> fwd(rand(3,3), rand(3,3,3), rand(3,3,3))
10.002254914427532

julia> function act!(R, A, B, ax_i=1:4, ax_j=Base.OneTo(4))
           for j in ax_j
               for i in ax_i
                   R[i, j] = A[2i + (j - 1) ÷ 2] + 0 * B[j]
               end
           end
           R
       end
act! (generic function with 3 methods)

julia> function act_avx!(R, A, B, ax_i=1:4, ax_j=Base.OneTo(4))
           @avx for j in ax_j
               for i in ax_i
                   R[i, j] = A[2i + (j - 1) ÷ 2] + 0 * B[j]
               end
           end
           R
       end
act_avx! (generic function with 3 methods)

julia> A, B = rand(10), rand(4)
([0.07679965771268082, 0.824045571092674, 0.936416792764375, 0.3251156875738792, 0.10978032932429849, 0.05916232379702535, 0.7161730794494576, 0.9125257528195947, 0.6873029017520635, 0.69167345196837], [0.992224771266325, 0.676384458821444, 0.8259595522815406, 0.18011831085812058])

julia> act!(zeros(4,4), A, B)
4×4 Matrix{Float64}:
 0.824046   0.824046   0.936417  0.936417
 0.325116   0.325116   0.10978   0.10978
 0.0591623  0.0591623  0.716173  0.716173
 0.912526   0.912526   0.687303  0.687303

julia> act_avx!(zeros(4,4), A, B)
4×4 Matrix{Float64}:
 0.824046   0.824046   0.936417  0.936417
 0.325116   0.325116   0.10978   0.10978
 0.0591623  0.0591623  0.716173  0.716173
 0.912526   0.912526   0.687303  0.687303

julia> SLEEFPirates
ERROR: UndefVarError: SLEEFPirates not defined

julia> using LoopVectorization

julia> let x=rand(10), y=zeros(10)
       @avx for i in 1:10
       y[i]= log10(x[i])  # same for log2, but log is OK
       end
       y
       end
10-element Vector{Float64}:
 -0.26098113144791735
 -0.002190298330183066
 -0.7032198454377777
 -0.1787018821076598
 -0.27671130090165763
 -0.029409238479290098
 -0.3669815600361895
 -0.22742360902320607
 -0.3405875544083138
 -0.06392385494065451