On Thu, 2019-11-07 at 12:40 -0600, Jonathon Anderson wrote: > I haven't benchmarked this version, but I did benchmark the equivalent > earlier version (this version is almost quite literally a rebase of the > other). I don't have the exact results on hand, what I remember is that > the pthread_key method was faster (and handled the many-thread case > better), by maybe a factor of 1.5x-2x in parallel. In serial the > overhead was minimal (just an extra pointer indirection on allocations).
I just tested the single-threaded case a bit and is not measurable slower than the previous version, and compared to 0.177 things are maybe ~1% slower (so probably in the noise). A factor 1.5x-2.0x slower in parallel does seem significant. Is that in the case of many-threads that are colliding a lot or in general? Thanks, Mark
