Chris Elrod

I'd prefer a higher level interface, if possible. For my purposes, the 32 KiB of L1 cache on Cascade Lake-X CPUs is only the second closest memory to the execution...

CPUSummary depends on Preferences.jl. It tries to check if `using Hwloc; Hwloc.gettopology()` works and doesn't segfault Julia: https://github.com/JuliaSIMD/CPUSummary.jl/blob/91846c77aed015cf2ba2fe738197e5b6aa64eb04/src/CPUSummary.jl#L14-L20 The problem is, this check always returns `false`, even though it works...

> I don't think that this is an issue with CPUSummary. CPUSummary sets a preference if Hwloc fails. The fact the test doesn't work, and it always reports that Hwloc...

`libR` is in `/usr/lib64/R/lib`: ```julia julia> ENV["R_HOME"] = "/usr/lib64/R/lib" "/usr/lib64/R/lib" (v1.3) pkg> build RCall Building Conda → `~/.julia/packages/Conda/kLXeC/deps/build.log` Building RCall → `~/.julia/packages/RCall/iojZI/deps/build.log` ┌ Error: Error building `RCall`: │ ERROR: LoadError:...

Great lead. On Clear Linux, I seem to have had a similar, but slightly different, problem: ```julia julia> using Libdl julia> Libdl.dlopen("/usr/lib64/R/lib/libR.so") ERROR: could not load library "/usr/lib64/R/lib/libR.so" libRblas.so: cannot...

> @chriselrod did you get to the bottom of this? I see it in #433 No. As of my last update here, it worked at work but not at home....

I want this. I'm perfectly fine with naming it `@bmean` or something else to preserve `@btime`.

> Yes, call it something else. Are you happy to rename it? Seems easy enough to make everyone happy this way.

Ah, re what I said earlier about using RF with 1 vs multiple threads: It doesn't benefit much from threading, but unlike OpenBLAS, Polyester won't weave a noose to hang...

> These days, should we ever go back to OpenBLAS? There's so many cases where it's just... bad. What do you get on your AMD machine? I'm guessing MKL is...