Re:Bubble sort slower with -O3 than -O2 with GCC
by MauranKilom on Sunday October 17, 2021 @02:00PM
(#28898350)
Not sure if that would have an impact here. GCC is just unaware of the latency implications of store forwarding. I mean, it's definitely worth a shot, but you'd just be more or less hoping that your mentioned techniques disable the right optimization pass.
[ Parent
| on HN ]
Re:Bubble sort slower with -O3 than -O2 with GCC
by mhh__ on Sunday October 17, 2021 @08:06PM
(#28900862)
That's true, although I'm curious if any compiler really understands the microarchitecture at that level without being coerced by a compiler dev writing a pass (i.e. won't happen straight from a pipeline description)