ggml-cpu : set openmp wait time if not set

[slaren]

Sets the OpenMP wait policy to active if not set. On some implementations this can significantly increase performance when using OpenMP.

Edit: changed to setting the thread block time instead, otherwise threads will continue spinning indefinitely. This is not a standard OpenMP setting, but it works in clang/windows. In my system setting it to 200ms results in the same performance as active wait policy.

[CISC]

Strange, according to the LLVM docs 200ms is the default?

[slaren]

I noticed that too. However I don't think the documentation is accurate. Actually even setting it to just 1us is enough to improve generation performance by 50% on my system.

[slaren]

On hybrid CPUs the default value is actually zero.
https://github.com/llvm/llvm-project/blob/7ff0cf6138f30db4f361a20eda7d18692337d351/openmp/runtime/src/kmp.h#L1278