JuliaLang / julia / #37920

20%

Build Type

push

local

Committed by web-flow

Commit Message

Limit `@inbounds` to indexing in the dual-iterator branch in `copyto_unaliased!` (#55919)

This simplifies the `copyto_unalised!` implementation where the source
and destination have different `IndexStyle`s, and limits the `@inbounds`
to only the indexing operation. In particular, the iteration over
`eachindex(dest)` is not marked as `@inbounds` anymore. This seems to
help with performance when the destination uses Cartesian indexing.
Reduced implementation of the branch:
```julia
function copyto_proposed!(dest, src)
    axes(dest) == axes(src) || throw(ArgumentError("incompatible sizes"))
    iterdest, itersrc = eachindex(dest), eachindex(src)
    for (destind, srcind) in zip(iterdest, itersrc)
        @inbounds dest[destind] = src[srcind]
    end
    dest
end

function copyto_current!(dest, src)
    axes(dest) == axes(src) || throw(ArgumentError("incompatible sizes"))
    iterdest, itersrc = eachindex(dest), eachindex(src)
    ret = iterate(iterdest)
    @inbounds for a in src
        idx, state = ret::NTuple{2,Any}
        dest[idx] = a
        ret = iterate(iterdest, state)
    end
    dest
end

function copyto_current_limitinbounds!(dest, src)
    axes(dest) == axes(src) || throw(ArgumentError("incompatible sizes"))
    iterdest, itersrc = eachindex(dest), eachindex(src)
    ret = iterate(iterdest)
    for isrc in itersrc
        idx, state = ret::NTuple{2,Any}
        @inbounds dest[idx] = src[isrc]
        ret = iterate(iterdest, state)
    end
    dest
end
```
```julia
julia> a = zeros(40000,4000); b = rand(size(a)...);

julia> av = view(a, UnitRange.(axes(a))...);

julia> @btime copyto_current!($av, $b);
  617.704 ms (0 allocations: 0 bytes)

julia> @btime copyto_current_limitinbounds!($av, $b);
  304.146 ms (0 allocations: 0 bytes)

julia> @btime copyto_proposed!($av, $b);
  240.217 ms (0 allocations: 0 bytes)

julia> versioninfo()
Julia Version 1.12.0-DEV.1260
Commit 4a4ca9c8152 (2024-09-28 01:49 UTC)
Build Info:
  Official https://julialan... (continued)

Run Details

2 of 2 new or added lines in 1 file covered. (100.0%)

1045 existing lines in 21 files now uncovered.

78714 of 89727 relevant lines covered (87.73%)

16568013.59 hits per line