Rafael Schouten

Seems its because my workgroup size was 4 - I guess you're expecting much larger workgroups on CPU? I never totally got my head around what workgroup size means on...

I guess its kind of academic if you can get around it with large workgroups. But comparing a workgroup 1 and 64: ```julia using KernelAbstractions kernel1! = copy_kernel!(CPU(), 1) kernel64!...

I've been wondering if the CPU workgroup size should mean "how much we unroll"

It seems DynamicCheck is only half the problem - it helps a lot removing it, but something else is also blocking the compiler constant propagating size information (its like a...

The problem here seems to be that I'm iterating over an object and each of its contents is passed to a method that again checks `istable`. ~It benchmarks at 160ns...

Its not related to Unitful.jl - its a generic problem with `Number`. See here: https://github.com/rafaqz/ModelParameters.jl/issues/51 I don't have bandwidth (or the required knowledge) to make this "optimal" or think through...

Totally, why use another package when we have the constants already.

Thats a good point about `Float64`. PhyisicalUnits.jl is not listed in the readme here, adding it would be a good step. But still, will these constants be deleted here?

`view(v, :)` maybe?

Instead of the full Unchunked(), this is where doing the minimum rechunking that can get sequential indices could help.