All the rand like function in CUDA.jl will get a CuArray. But memory allocation is not allowed in a kernel function. Thus, a CuArray can not be generated. So, are there any method to get a pure random number instead of an Array.
1 Like
Host rand calls don’t work on the GPU. We also don’t support the CURAND device API for now. See Generating Random Number from inside Kernel for possible workarounds.
IIRC @tkf also had a solution, maybe he can elaborate (Slack has eaten the history).
1 Like
tkf’s implementation here Monte-Carlo π · FoldsCUDA
4 Likes
I suggested Julia would use this:
https://sunoru.github.io/RandomNumbers.jl/stable/man/xorshifts/
Xoroshiro128, Xoroshiro128Star and Xoroshiro128Plus: The successor to Xorshift128 series. They make use of a carefully handcrafted shift/rotate-based linear transformation, resulting in a significant improvement in speed and in statistical quality. Therefore, Xoroshiro128Plus is the current best suggestion for replacing other low-quality generators.
I’ve not looked into issues with GPUs, maybe this works as is.
1 Like
FYI here’s a follow-up comment on the FoldsCUDA.jl link: Advice for improving Monte-Carlo code - #25 by tkf