Hello, I am surprised that when using the below code, I have the following execution time: using .Threads n=10000; s=1 Y=zeros(n,n); @time begin for i in 1:n for m in 1:30 if s == 1 Y[i,i] += m; end end end end 0.039520 seconds (629…

Threads can have have pretty high overhead – see for example [cbk] Julia Threads.@threads slower than single thread performance multithreading, parallel-processing, julia, pde answered by cbk on 12:59AM - 09 Jul 21 UTC …

Though actually one should switch to timing with @btime before drawing any serious conclusions from the above

While threads do have overhead, there are some other issues, you are using variables in a global scope, so their type can’t be inferred during compilation, you are also running in global scope, which can have issues, you are also including compilation time with your @time measurements, which shows t…

Here you go, should’ve included it on the first one julia> @benchmark foo() BechmarkTools.Trial: 282 samples with 1 evaluations. Range (min … max): 14.471 ms … 41.847 ms ┊ GC (min … max): 0.00% … 63.10% Time (median): 16.291 ms ┊ GC (median): 0.00% Time (mean ± σ): 17.7…

Yeah, similarly: julia> Threads.nthreads() 4 julia> @btime begin for i in 1:$n for m in 1:30 if $s == 1 $Y[i,i] += m end end end end 316.747 μs (0 allocations: 0 bytes) julia> @btime…

I will always recommend taking a look at Performance Tips · The Julia Language there you will find most of the pitfalls I explained and some others, leading to better perfomance and less issues while benchmarking.

Yeah, https://github.com/JuliaSIMD/LoopVectorization.jl , https://github.com/JuliaSIMD/LoopVectorization.jl and GitHub - JuliaFolds/FLoops.jl: Fast sequential, threaded, and distributed for-loops for Julia—fold for humans™ are good resources for speeding things up.

I am really confused when I am running my code using .Threads function foo() n=10000; s=1 Y=zeros(n,n); for i in 1:n for m in 1:30 if s == 1 Y[i,i] += m; end end end end julia> @time foo() 0.162492 seconds (2 allocations: 762.940 …

The top one in your screenshot is counting compilation again. You should probably use @btime or @benchmark to avoid that happening by accident all the time.

[44] Is this way in using @benchmark is correct?

Question for lower performance by using @threads in for loop

New to Julia

brenhinkeller July 9, 2021, 1:25am 2

Threads can have have pretty high overhead – see for example

1 Like

Topic		Replies	Views
Slower execution with multi-threading using @threads macro Performance question , parallel , multithreading	5	785	August 13, 2020
Julia Threads.@threads slower than single thread performance Performance multithreading , pde	11	2968	April 24, 2023
Why with @threads, the execution time is worse? Performance question , multithreading	19	2891	September 16, 2021
Threads.@threads with ONE thread: how to remove the overhead? Performance threads	10	4131	April 2, 2021
Threaded loop far slower than sequential loop (+ high compilation time) Performance multithreading	3	867	September 17, 2021

Question for lower performance by using @threads in for loop

Related topics