Microbenchmarks on my laptop now show that TLSSlot::with is just as fast (2 ns/op) as the alloc_tls_fast_with! macro. If memory serves, these microbenchmarks used to show (on this same model of laptop) that TLSSlot::with took 4 ns/op. Thus, it's worth looking into whether elfmalloc's macrobenchmarks no longer show a difference in speed between TLSSlot::with and alloc_tls_fast_with!, and if so, to consider removing the latter.
Microbenchmarks on my laptop now show that
TLSSlot::withis just as fast (2 ns/op) as thealloc_tls_fast_with!macro. If memory serves, these microbenchmarks used to show (on this same model of laptop) thatTLSSlot::withtook 4 ns/op. Thus, it's worth looking into whetherelfmalloc's macrobenchmarks no longer show a difference in speed betweenTLSSlot::withandalloc_tls_fast_with!, and if so, to consider removing the latter.