Trying to get Julia to emit an efficient sequence of SIMD instructions with the aid of llvmcall

TestSIMD2.jl

module TestSIMD2

# requires Julia 0.4 for llvmcall

typealias Uint64x2 NTuple{2, Uint64}
function ($)(x::Uint64x2, y::Uint64x2)
    Base.llvmcall("""%3 = xor <2 x i64> %1, %0
                     ret <2 x i64> %3""",
                  Uint64x2, (Uint64x2, Uint64x2), x, y)
end

function innerloop!{T}(dest::Vector{T}, dest_ofs, src::Vector{T}, src_ofs)
    @inbounds s = ( src[1 + 2*src_ofs],   src[2 + 2*src_ofs])
    @inbounds d = (dest[1 + 2*dest_ofs], dest[2 + 2*dest_ofs])
    d $= s
    @inbounds (dest[1 + 2*dest_ofs], dest[2 + 2*dest_ofs]) = d
end

T = Uint64
code_native(innerloop!, (Vector{T}, Int, Vector{T}, Int))

end

Note: If you really want you can use llvmcall with a load <2xi64> ... align 16 to get the desired behavior.