Stream: helpdesk (published)

Topic: Does constant propagation work with GPU kernels?

view this post on Zulip Nathan Zimmerberg (Apr 19 2026 at 21:50):

When writing a GPU kernel is it a bad idea to rely on constant propagation?

For example if I have the kernel helper function u01 from PhiloxRNG.jl

@inline function u01(::Type{Float32}, u::UInt32)::Float32
    fma(Float32(u), Float32(2)^(-32), Float32(2)^(-33))
end

Is it better to instead do:

const _f32_2_to_the_neg_32 = Float32(2)^(-32)
const _f32_2_to_the_neg_33 = Float32(2)^(-33)
@inline function u01(::Type{Float32}, u::UInt32)::Float32
    fma(Float32(u), _f32_2_to_the_neg_32, _f32_2_to_the_neg_33)
end

Because in the first case the ^ will need to be done on the GPU?

I see in the C++ version of this function they also needed to do some workarounds to get this to work.

Background is I am trying to understand why https://github.com/JuliaGPU/OpenCL.jl/pull/428 was needed, but this seems like a more general question for how to write GPU kernels in Julia.

Last updated: Apr 21 2026 at 06:18 UTC