https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #17 from Richard Biener ---
(In reply to Richard Biener from comment #16)
> r15-9175 on x86_64 now shows (with release checking, built with GCC 7, not
> bootstrapped):
>
> Samples: 112K of event 'cycles:Pu', Event count (approx.): 1
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #16 from Richard Biener ---
r15-9175 on x86_64 now shows (with release checking, built with GCC 7, not
bootstrapped):
Samples: 112K of event 'cycles:Pu', Event count (approx.): 139897585915
Overhead Samples Command
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #15 from Richard Biener ---
(In reply to ak from comment #13)
> This patch gives another 23% speedup due to reducing time handling the
> linked lists for lazy bitmaps. Probably there is more tuning potential in
> bitmaps
> (most of t
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
Andrew Pinski changed:
What|Removed |Added
Ever confirmed|0 |1
Status|UNCONFIRMED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #13 from ak at gcc dot gnu.org ---
This patch gives another 23% speedup due to reducing time handling the linked
lists for lazy bitmaps. Probably there is more tuning potential in bitmaps
(most of the top 10 hot functions are bitmap r
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
Andi Kleen changed:
What|Removed |Added
CC||andi-gcc at firstfloor dot org
--- Comment
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #11 from GCC Commits ---
The trunk branch has been updated by Andi Kleen :
https://gcc.gnu.org/g:063fbd5a10d47d4957d605ca917480d02e054249
commit r15-9143-g063fbd5a10d47d4957d605ca917480d02e054249
Author: Andi Kleen
Date: Tue Apr
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
Bug 119482 depends on bug 119584, which changed state.
Bug 119584 Summary: [14/15 Regression] flatten attribute calling a function
with concept requires an ICE during inlining at -O2
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119584
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #10 from Sam James ---
(In reply to ak from comment #9)
> For the ICE i'm not sure why i'm not seeing it. The input file should have
> had flatten enabled.
> gcc_checking_assert (to->calls_comdat_local);
--enable-checking=rel
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #9 from ak at gcc dot gnu.org ---
For the ICE i'm not sure why i'm not seeing it. The input file should have had
flatten enabled.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #8 from ak at gcc dot gnu.org ---
The workload does a lot of bitmap manipulations:
#
5.62% cc1plus cc1plus [.] bitmap_and_into(bitmap_head*,
bitmap_head const*)
5.30% cc1plus cc1plus [.]
bitm
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #7 from Andrew Pinski ---
(In reply to Andrew Pinski from comment #6)
> With flatten enabled at -O2 I get an ICE:
> during IPA pass: inline
> Interpreter.cpp:3841:1: internal compiler error: in redirect_callee, at
> cgraph.cc:1391
>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #6 from Andrew Pinski ---
With flatten enabled at -O2 I get an ICE:
during IPA pass: inline
Interpreter.cpp:3841:1: internal compiler error: in redirect_callee, at
cgraph.cc:1391
0x293749f internal_error(char const*, ...)
/ho
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #5 from ak at gcc dot gnu.org ---
Also I should add that the Ladybird developers report a 40% performance
improvement from adding flatten to clang.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #4 from ak at gcc dot gnu.org ---
Created attachment 60902
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=60902&action=edit
input file for clang testing
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
--- Comment #3 from ak at gcc dot gnu.org ---
I ran a full comparison now. There is actually a significant regression between
g++-13 and g++-14, but -15 is roughly the same as -14. All are significantly
slower than clang:
clang++-19 -std=gnu++20
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
Richard Biener changed:
What|Removed |Added
CC||rguenth at gcc dot gnu.org
--- Comment
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=119482
Andrew Pinski changed:
What|Removed |Added
Keywords||compile-time-hog
Component|tre
18 matches
Mail list logo
