Re:Best Performance of a C++ Singleton
by menaerus on Monday March 09, 2026 @05:52AM
(#47306860)
Yeah ... and so it happens that this particular function in the profile is just a symptom, merely being an observation (single) data point of system behavior under given workload, and not the root cause for, let's say, load instruction burning 90% of the CPU cycles by waiting on some data from the memory, and consequently giving you a wrong clue about the actual code creating that memory bus contention.
I have to say that up until I grasped a pretty good understanding of CPU internals, memory subsystem, kernel, and generally the hardware, reading into the perf profiles was just a fun exercise giving me almost no meaningful results.
Re:Best Performance of a C++ Singleton
by halayli on Tuesday March 10, 2026 @12:52AM
(#47319199)
Totally. I always found joy solving critical performance problems because it naturally pave a path forward to peel the layers and untangle the system interactions which feeds my curiosity, and is highly rewarding.
I have to say that up until I grasped a pretty good understanding of CPU internals, memory subsystem, kernel, and generally the hardware, reading into the perf profiles was just a fun exercise giving me almost no meaningful results.