Huge performance drop using @spawn

General Usage
1

Using Jeff’s article https://julialang.org/blog/2019/07/multithreading

using
julia> VERSION
v"1.3.1"
I simply tried the first example with JULIA_NUM_THREADS=4 on a 12 core machine with 64GB RAM

import Base.Threads.@spawn

function fib(n::Int)
    if n < 2
        return n
    end
    t = @spawn fib(n - 2)
    return fib(n - 1) + fetch(t)
end

julia> @btime fib(20)
4.473 ms (93843 allocations: 8.11 MiB)
6765

While running the same without @spawn we get
julia> @btime fib(20)
26.614 μs (0 allocations: 0 bytes)
6765

Conclusion using @spawn just brings huge counter perf and heavy memory usage.

Can anyone clarify for me please why
Thanks

2

The problem is that almost all of the calls fib makes are to fib(1) and fib(2). Since spawn has about a 1 msec time, you would only want to use it when the inside computation takes more than that amount of time.

3

I get the Point Oscar, thks for you immediate reply :wink:

4

See also this as it was already discussed in detail!

tl;dr start using spawn only with big enough ns.