Ways to fill an array and performance. Peculiar to me that f6! does less allocations than the others and that f4! – f6! are faster than f1!. Is there an “official” way to fill an array? Does the performance difference come down to bounds checking? All benchmarks are done with self compiled Julia …

I do not get the same performance differences … f1! to f3! take ~350 μs, f4! to f7! take ~250 μs, f8! takes ~650 μs. I think fill! is intended for the ‘official’ way (if there can be one). Differences are indeed related to bounds checking for f8! as running julia with --check-bounds=no speeds it…

Looks kind of similar to [image] Possible inefficiency in randn! Performance I was confused in the previous post, sorry. That has nothing to do with simd: using Random broadcast_randn(x) = (x .= randn.()) inplace_randn(x) = randn!(x) function myrandn!(x) @inbounds @s…

Hah, that’s funny. Try it with any value other than 0: julia> x = Array{Float64}(undef, 1000, 1000) f1!(x) = fill!(x, 1.0) f2!(x) = x .= 1.0; f3!(x) = x .= 1; f4!(x) = x[:] .= 1.0; f5!(x) = x[:] .= 1; f6!(x) = x[:,:] .= 1; function f7!(x) …

As far as why some of these forms allow for constant propagation and some don’t, it appears as though there was a strange edge case in the compiler back in the 0.7 timeframe that prompted a simple workaround . That’s no longer necessary. Revert #26…

That’s great! But do you know why x[:] .= 0 is faster than x .= 0? foo!(x, val) = (x .= val) bar!(x, val) = (x[:] .= val) julia> @btime foo!($x, 0); 379.111 μs (0 allocations: 0 bytes) julia> @btime bar!($x, 0); 280.690 μs (1 allocation: 48 bytes)

Yes, it’s because we have a peephole “performance optimization” in broadcast to use fill! for simple cases — because that should be the fastest way to do it. But it backfired here… JuliaLang/julia/blob/d43c23b1d19616fabf7e593497299d4cc59acf82/base/broadcast.jl#L844-L850 …

I can’t reproduce these differences on my system, I get 325.541 μs and 327.219 μs respectively.

OK, so it should be fixed once fill! is fixed, then?

[image] under-Peter: I can’t reproduce these differences on my system, I get 325.541 μs and 327.219 μs respectively. It’s likely you have an older processor that doesn’t have the AVX-512 (wide SIMD) instruction set. [image] DNF: OK, so it should be fixed once fill! is fixed, then? Yup…

Performance of filling an array

General Usage

baggepinnen April 5, 2019, 2:00pm 3

Looks kind of similar to

Topic		Replies	Views
Could fill! be twice as fast? Internals & Design	13	2386	May 15, 2017
Performance degradation of `fill` in latest Julia 0.7 Dev? Performance	2	931	March 11, 2018
How to resize and fill more efficiently? GPU	14	1115	February 9, 2023
Fastest way of getting a long zero vector? General Usage	29	1084	March 15, 2024
Create initialized arrays of structs General Usage	2	3832	November 30, 2017

Performance of filling an array

Related topics