Elliot Saba

@liushang0322 Sorry for such a late reply, I unfortunately don't see these issues unless I get pinged directly via `@staticfloat`. It looks to me like your ILP64 load failed; can...

It looks to me like LBT [should already know how to deal with BLIS](https://github.com/JuliaLinearAlgebra/libblastrampoline/blob/491f33022e002fa9c60116da64af5b00efcae5d2/src/threading.c#L14). There is a completely generic way in which you can [register get/set_numthreads functions](https://github.com/JuliaLinearAlgebra/libblastrampoline/blob/491f33022e002fa9c60116da64af5b00efcae5d2/src/threading.c#L29) for your own...

You can teach LBT about your thread function name with the following Julia code: ``` julia> using Libdl, blis_jll, libblastrampoline_jll getter = Libdl.dlsym(blis_jll.blis_handle, "bli_thread_get_num_threads_64_") setter = Libdl.dlsym(blis_jll.blis_handle, "bli_thread_set_num_threads_64_") @ccall libblastrampoline.lbt_register_thread_interface(getter::Ptr{Cvoid},...

> In BLIS only the setter has F77 interface: > > * `bli_thread_set_num_threads_64_` for 64-bit. > * `bli_thread_set_num_threads_` for 32-bit. > > while `bli_thread_set_num_threads` is presented as C interface. So...

It looks to me like it's failing because it can't find the `MKL_Set_Threading_Layer` symbol; I'm guessing that during precompilation, `libmkl_rt` doesn't point to where we think it should, and so...

> I guess we could also add preferences for the interface etc. but maybe the current option is just fine? You don't need to add a preference for this, because...

`#ci-dev` looked into this, and the following is a (more minimal) reproducer: ``` using SharedArrays # Arbitrary dims = (10,) T = Float64 # Create shared memory, truncate to the...

Confirmed that the equivalent C program fails in the same way: ``` #include #include #include /* For O_* constants */ #include /* For mode constants */ #include /* For shared...

Confirmed that updating the kernel from v5.4 -> v5.15 has solved this, so presumably this was a kernel bug! Huzzah! Our aarch64-linux worker has been updated, so this should be...

Update: looks like we solved the `SharedArrays` problem, but the `abstractarray` test is still failing 😂