[Bug other/48696] Horrible bitfield code generation on x86
torvalds@linux-foundation.org
gcc-bugzilla@gcc.gnu.org
Wed Apr 20 04:28:00 GMT 2011
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48696
--- Comment #1 from Linus Torvalds <torvalds@linux-foundation.org> 2011-04-20 04:28:18 UTC ---
Side note, this is talked about in the Intel optimization manual
3.6.4 Store Forwarding
Under "General Optimization Guidelines" -> "Optimizing Memory Accesses" ->
"Store Forwarding".
I'm sure people are aware of it, but I'm not certain people realize how
horrible the performance hit can be. I have to admit to having been a bit
surprised myself just _how_ clearly it shows up in profiles.
More information about the Gcc-bugs
mailing list