Re: LuaJIT2 performance for number crunching

[Mike Pall <mikelu-1102@...>]

Luis Carvalho wrote:
> function set1 (u, v)
>   for i = 0, u.size - 1 do
>     u.data[i] = v.data[i]
>   end
>   return u
> end
> 
> function set (u, v)
>   for i = 0, u.size - 1 do
>     u.data[i * u.stride] = v.data[i * v.stride]
>   end
>   return u
> end
> 
> Are set1 and set comparable? (I'm not sure "set" is the best way of
> implementing a strided version...)

Currently the multiply is neither strength-reduced nor narrowed,
so it's kind of costly. If this code is performance-sensitive,
you'll probably want to dispatch to a dynamically specialized
version of the loop, based on the two stride values. Usually these
are powers of two, which enables further optimizations.

--Mike