https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #14 from Jonathan Wakely ---
The testcase now scales with the number of CPUs, instead of running effectively
single-threaded.
If the global locale is changed so std::locale() != std::locale::classic() then
every thread contends for t
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
Jonathan Wakely changed:
What|Removed |Added
Status|ASSIGNED|RESOLVED
Resolution|---
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #12 from Jonathan Wakely ---
Author: redi
Date: Wed Oct 3 11:27:40 2018
New Revision: 264811
URL: https://gcc.gnu.org/viewcvs?rev=264811&root=gcc&view=rev
Log:
PR libstdc++/59439 optimize uses of classic ("C") std::locale
The globa
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
Jonathan Wakely changed:
What|Removed |Added
Status|NEW |ASSIGNED
Assignee|unassigned
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
Jonathan Wakely changed:
What|Removed |Added
Status|UNCONFIRMED |NEW
Last reconfirmed|
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #9 from Jonathan Wakely ---
Using current trunk and -O2 to compile the benchmark in comment 8 I get:
snprintf
1 threads took 11 ms
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
Jonathan Wakely changed:
What|Removed |Added
Attachment #31405|0 |1
is obsolete|
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
Antony Polukhin changed:
What|Removed |Added
CC||antoshkka at gmail dot com
--- Comment
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #6 from Ben Maurer ---
I agree this isn't necessarily the cleanest way to accomplish this task.
My discovery of this bug came through a real life application which was
deployed to real users and had a noticeable impact due to this iss
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #5 from Jonathan Wakely ---
Don't do that then ;-)
Noone ever claimed std::stringstream is a good way to convert integers to
strings in performance critical code. Even if the std::locale construction is
optimized further, stringstream
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #4 from Ben Maurer ---
Also, here's where perf says time is being spent. While only 25% is shown as
being in the locale constructor/destructor, I suspect that the time spent in
other methods is actually related to the ping-ponging of c
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #3 from Ben Maurer ---
Created attachment 31405
--> http://gcc.gnu.org/bugzilla/attachment.cgi?id=31405&action=edit
Benchmark
_build/opt/experimental/bmaurer/benchmark
snprintf
1 threads took 20 ms
2 threads took 20 ms
3 threads to
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #2 from Andrew Pinski ---
Is there a simple performance testcase you could provide?
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59439
--- Comment #1 from Ben Maurer ---
Facebook is putting a $50 bounty on this bug via bountysource:
https://www.bountysource.com/issues/1350875
14 matches
Mail list logo