Random numbers in [0.f0,1.f0]

[jling]

you can try to do something like this:

GPU randn way slower than rand?

Hi Tim, Thanks for the reply. I understand that testing once in global is not accurate, it’s just that the difference is too large to be normal. Here the new result following your code ac = Array{Float64}(undef, 2^20) ag = cu(ac) @btime randn!(ac) @btime CuArrays.@sync randn!(ag) 6.788 ms (0 allocations: 0 bytes) 7.626 s (5242883 allocations: 288.00 MiB) So the allocations are clearly the problem, but I can’t really figure out the reason. Even with rand there are some extra allocations @…

but as you noted bits are bytes anyways, so maybe you can just use a if < 0.5 or something.