public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug target/97142] New: __builtin_fmod not optimized on POWER
@ 2020-09-21 10:57 fx at gnu dot org
  2020-09-21 11:24 ` [Bug target/97142] " rguenth at gcc dot gnu.org
                   ` (21 more replies)
  0 siblings, 22 replies; 23+ messages in thread
From: fx at gnu dot org @ 2020-09-21 10:57 UTC (permalink / raw)
  To: gcc-bugs

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97142

            Bug ID: 97142
           Summary: __builtin_fmod not optimized on POWER
           Product: gcc
           Version: 10.2.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: fx at gnu dot org
  Target Milestone: ---

I ran some Fortran benchmarks (the "Polyhedron" set) on POWER9, and found one
of them has pathologically bad performance compared with xlf.  Profiling shows
that's due to spending most of its time in fmod via a random-number function. 
fmod isn't called when compiled with xlf -O5 or when compiling the same on
x86_64.  Although it's Fortran, this doesn't appear to be Fortran-specific as
the DMOD intrinsic is turned into __builtin_fmod.

The following is with gcc 10.2, comparing the two targets.

On RHEL7 POWER9 (and the same with -mcpu=native):

$ cat ggl.f90
      REAL FUNCTION GGL(Ds)
      DOUBLE PRECISION Ds , d2
      DATA d2/2147483647.D0/
      Ds = DMOD(16807.D0*Ds,d2)
      GGL = Ds/d2
      END
$ gfortran -O3 -fopt-info-all -c ggl.f90
ggl.f90:4:0: missed:   not inlinable: ggl/0 -> __builtin_fmod/2, function body
not available
Unit growth for small function inlining: 12->12 (0%)

Inlined 0 calls, eliminated 0 functions

ggl.f90:6:0: note: ***** Analysis failed with vector mode V2DF
$ nm ggl.o
                 U fmod
0000000000000000 T ggl_
                 U .TOC.

On Debian 10 SKX with the same source:

$ gfortran-10 -Ofast -fopt-info-all -c ggl.f90
ggl.f90:4:0: missed:   not inlinable: ggl/0 -> __builtin_fmod/2, function body
not available
Unit growth for small function inlining: 12->12 (0%)

Inlined 0 calls, eliminated 0 functions

ggl.f90:6:0: note: ***** Analysis failed with vector mode V2DF
ggl.f90:6:0: note: ***** Skipping vector mode V16QI, which would repeat the
analysis for V2DF
$ nm ggl.o
0000000000000000 r .LC0
0000000000000008 r .LC1
0000000000000010 r .LC2
0000000000000000 T ggl_

^ permalink raw reply	[flat|nested] 23+ messages in thread
end of thread, other threads:[~2021-09-14  5:36 UTC | newest]

Thread overview: 23+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-21 10:57 [Bug target/97142] New: __builtin_fmod not optimized on POWER fx at gnu dot org
2020-09-21 11:24 ` [Bug target/97142] " rguenth at gcc dot gnu.org
2020-09-21 11:26 ` rguenth at gcc dot gnu.org
2020-09-21 14:42 ` bergner at gcc dot gnu.org
2020-09-21 14:45 ` fx at gnu dot org
2020-09-21 14:47 ` fx at gnu dot org
2020-09-21 17:52 ` segher at gcc dot gnu.org
2020-09-21 18:10 ` bergner at gcc dot gnu.org
2020-09-21 19:33 ` segher at gcc dot gnu.org
2020-09-21 21:54 ` bergner at gcc dot gnu.org
2021-04-13  6:24 ` luoxhu at gcc dot gnu.org
2021-04-13 16:26 ` segher at gcc dot gnu.org
2021-05-27  0:54 ` luoxhu at gcc dot gnu.org
2021-09-02 22:05 ` bergner at gcc dot gnu.org
2021-09-02 22:38 ` segher at gcc dot gnu.org
2021-09-03  2:33 ` luoxhu at gcc dot gnu.org
2021-09-07  1:29 ` cvs-commit at gcc dot gnu.org
2021-09-07 17:58 ` bergner at gcc dot gnu.org
2021-09-07 19:34 ` segher at gcc dot gnu.org
2021-09-07 21:20 ` segher at gcc dot gnu.org
2021-09-14  5:33 ` cvs-commit at gcc dot gnu.org
2021-09-14  5:34 ` cvs-commit at gcc dot gnu.org
2021-09-14  5:36 ` luoxhu at gcc dot gnu.org

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).