With FSA I get around a factor 50 speedup (when I don't use the iterative
corrector):
function \{T}(A::FixedMatrix{2, 2, T}, b::FixedVector{2, T})
x = unroll_LU(A[1,1], A[1,2], b[1], A[2,1], A[2,2], b[2])
return x
end
@inline function unroll_LU{T <: Number}(a::T ,b::T ,c::T , d::T ,e::T ,f::T)
if a == 0 && d == 0
throw(ArgumentError("singular matrix"))
end
if abs(a) >= abs(d)
a⁻¹ = 1/a
α = d * a⁻¹
β = e - b * α
β == 0 && throw(ArgumentError("singular matrix"))
γ = f - c * α
y = γ / β
x = (c - b * y) * a⁻¹
return Vec{2, T}(x, y)
else
unroll_LU(d,e,f, a,b,c)
end
end
m = Mat{2,2, Float64}(rand(2,2))^C
c = Vec{2, Float64}(rand(2))
julia> @benchmark foo(m,c)
================ Benchmark Results ========================
Time per evaluation: 13.60 ns [13.42 ns, 13.78 ns]
julia> @benchmark foo(rand(2,2),rand(2))
================ Benchmark Results ========================
Time per evaluation: 564.77 ns [548.25 ns, 581.28 ns]
On Wednesday, November 18, 2015 at 11:53:59 AM UTC+1, Tim Holy wrote:
>
> If allocating the arrays is a big bottleneck, you might consider making
> use
> of/adding this to FixedSizeArrays.
>
> --Tim
>
> On Tuesday, November 17, 2015 05:12:13 PM Pavel wrote:
> > Quite useful, thank you. Essentially choosing the form of exact
> expression
> > based on matrix element comparison. Appears to be reasonably stable and
> > over 10 times speedup!
> >
> > On Tuesday, November 17, 2015 at 12:57:33 AM UTC-8, Kristoffer Carlsson
> >
> > wrote:
> > > Maybe this link is of use? http://stackoverflow.com/a/10188318
>
>
