Closed chriselrod closed 3 years ago
Bump @m-j-w
I have a PR to add Project.toml
in https://github.com/staticfloat/CpuId.jl/pull/1, which targets #40, but I'm not sure @staticfloat ever saw that (not that this repo is super active, either).
Edit: well, I guess I can close https://github.com/staticfloat/CpuId.jl/pull/1
Thank you, @chiselrod.
cacheinclusive
indicates whether each cache includes lower cachelevels.When experimenting with block sizes for matrix multiplication, I realized my Cascadelake CPU (which has a non-inclusive L3) liked to use a much larger % of its L3 than my Haswell (with an inclusive L3). Then again, the Cascadelake also liked to use a larger percentage of its much larger L2 cache as well, and neither of them have inclusive L2 caches.
Figured this would be generally useful for those using cache sizes.